30:40 linear narratives, and then application shell which is kind of neat. Then we have some brief
30:45 little rules about different tools to use just based off of my own understanding of tooling. Um
30:50 as well as um some double-checking protocol down here. And on the right hand side, as you can see,
30:55 after I entered that little uh message, it's now asking me for the brand name, the core thesis, um
31:00 aesthetic archetype, structural typologies, three core pillars, and then the ultimate conversion
31:04 goal. So, all I'm going to do now is I'm going to close out of this. Okay. Make this way way
31:09 bigger just so I could see like most of it. And then I'm just going to enter my information. So,
31:15 uh my brand name, just so people are all on the same page as me, is called Leftclick. And
31:19 basically what we are to zoom way in there because the website looks like trash right now is we're
31:23 the definitive AI growth partner for fastmoving B2B companies. This is a website that I actually
31:28 had a real developer like I paid somebody money to put this together for me cuz I didn't have
31:32 the time. And the whole idea is we're like an AI automation boutique shop that helps people
31:37 generate revenue using high growth systems. This is typically stuff like cold email systems. It's
31:41 stuff like speed to lead systems for paid ads and so on and so forth. So it's pretty neat,
31:45 right? It's pretty sexy. We got the cool photo with Hormosi and Ovens over here. That's uh won me
31:49 some goodwill for sure. Basically, what I want to do is I just want to have AI try and generate uh
31:53 this website instead of me. And then I just want to compare and contrast the results. You'll see
31:57 there's some mild things here like there's a cool little animation that kind of follows my mouse
32:00 around. That's kind of neat, right? Obviously the text and the fonts and stuff that those are
32:03 very sexy. So, do you think AI could do as good of a job? Well, let's find out. I'm going to
32:07 answer some information here. Brand name is called Leftclick. We help high growth B2B companies scale
32:14 revenue using outbound methods like cold email. Two, pick best fit. Three, pick best fit. Four,
32:23 super low cost of acquiring a customer. Um, AI based personalization, which lets us attack at
32:31 both scale and high levels of perceived personalization. And then trusted vendor.
32:41 We've worked with multi-billion dollar portfolio companies. And then ultimate conversion goal is
32:48 book a growth mapping call 30 men consult. Just going to enter this information now. And I'm going
32:56 to have the model do everything else for me. The first thing that's going to pop up is this little
33:00 thinking tab. And so what it's doing if I scroll to the very top is it's focusing on refining the
33:04 initial approach particularly concerning file operations. It's prioritizing the use of more
33:08 specific resources to manage and manipulate information and so on and so forth. These are
33:12 all of its own thoughts. And basically the way that this works is at every step it's basically
33:17 like another it's like another run. It basically takes the prompt, it sends it, it does a bunch of
33:21 thinking and then it sends that back to another instance and says what's next over and over and
33:25 over and over again. So that's what's happening down over here at the bottom. Once you're done
33:29 something that requires a fair amount of planning, it'll actually pop open a planning uh section. And
33:33 this basically runs through the files that were edited as we saw earlier. Okay. the progress
33:38 updates of that, some additional thinking, and then finally a task list for what it's planning
33:43 on doing. When tasks lists pop up, they pop up in the middle over here. And as you can see, we have
33:48 a leftclick dashboard landing page. It's going to start by scaffolding the application using
33:51 a particular library. Then it's going to install dependencies, configure Tailwind, then it's going
33:56 to build a core layout, and then, you know, go through and do things in a really high quality
34:00 way. Okay. So over here, what it's doing now is it's running a terminal shell. Terminals just look
34:05 like this. uh running background command. Anytime you see anything like this with this little
34:09 terminal icon, it's basically just doing the thing in the terminal for you. Um you can actually just
34:13 jump to that anytime you want to. And here you can actually see like what it's communicating with,
34:18 what it's doing. You can also see the artifacts. So there's now two artifacts that it's created.
34:22 One's called uh the task and the other's called the implementation plan. Both of these here are
34:26 basically just resources for you to make things a little bit more visible. Like logically speaking,
34:31 this model is doing a lot under the hood, right? writing hundreds, thousands of of words basically
34:35 every few seconds. Um I have no insight into this. This is all just occurring behind the scenes.
34:39 And so one of the big issues right now with vibe coded apps is there's just no interpretability or
34:43 accountability about like what the model's doing underneath um you know behind everything. Well,
34:47 this implementation plan, the whole idea is it just like shows you behind the scenes what's going
34:51 on. Well, it's decided on some AR aesthetic and typology decisions like um B2B SAS dense. We want
34:57 gunmetal safety orange steel. The typography is going to be IBM Plex suns, IBM Plex mono, right?
35:03 These different fonts and so on and so forth. The application shell is going to look like this. The
35:07 proposed changes are going to look like that. As you saw a moment ago, we just added a file to our
35:11 folder called leftclick- dashboard. If I give this button a click, you'll see we now have a bunch
35:15 of files that it's written. The model just wrote all of this while I was just talking to you guys,
35:19 and it's currently writing more, right? Which is pretty neat. I don't know how any of this stuff
35:23 works, to be honest. And I don't need to anymore. I just vibe code. If I like it, fantastic. If not,
35:28 I I'll ask for changes and I'll show you guys what that loop looks like in a second. But yeah,
35:32 I mean, you know, as you guys see, a big chunk of this is just shephering AI and making sure
35:36 that it's operating in in the right direction, the direction that you want, as well as looking over
35:40 things like implementation plans, intermediary files that are created, and stuff like that to
35:44 just ensure that like everything is going the way that you initially planned. What I'm going to do
35:47 next is I'm going to go grab a sip of water and then I'll come back and hopefully this website
35:50 will be ready to go. Okay. And here is the result. Deploy the growth engine. We build growth systems
35:55 for high- rev B2B agencies. Pure information density, zero latency scaling. Wow, that's
35:59 cool. Ooh, I love that button. That's really nice. Uh, if you guys watched one of my recent videos on
36:04 website design, this is the same approach. So, I actually really like the background image as
36:08 well. And so, I uh turned I basically gave it the ability like the prompt that you guys are going to
36:12 use if you copy the prompt and use it in your own. Basically gave it the ability to like find stock
36:17 image websites and stuff like that. And that's how we end up with like this really nice clean like
36:21 glass ISO form thing up at the top. then have some cool uh you know sections here. Rapid revenue,
36:28 lowest cost, proven vendor. That's really cool. We focus on systemic growth. I like that. I like the
36:32 blue this time. We got some cool animations and stuff like that. You will find, you know, because
36:37 we're using the same icon libraries and stuff, some of these animations will be pretty similar.
36:40 If you redo this five or six times, but yeah, I mean like we just we just one-shoted a really cool
36:45 website, right? Um I'm just going to do the same thing now a couple times just to show you guys
36:48 that you don't have to stick just to the style. You could do it in a bunch of different ones,
36:51 too, if you wanted to. Okay. So, I'm just going to open up a new folder here. And then I'm just
36:54 going to make one website builder new. And then I'm just going to operate inside of this folder.
37:00 Okay. This is another rendition. So, I think this is supposed to be like kind of earthy and healthy,
37:05 which is why it says leftclick with the globe. That is definitely not our brand, but what are
37:09 you going to do? We're the architect of outbound scale. We weaponize personalization by designing
37:14 and deploying outbound architect for multi-billion dollar portfolios. Kind of really like that
37:18 section too much. Here's probably the weakest bit, though. This stuff looks really cool. Like like I
37:22 I really like this. Look at that. This looks nice as well. You know, it's like something it came up
37:27 with to showcase how we're verifying decision maker profiles. We're trusted by the best. You
37:31 know, we're architecting the revenue engine. So, this is a great example for me to show you how
37:34 you can change websites to make things better or uh I don't know, you know, include sections
37:38 that you want. So, what I have here is I have a voice transcription tool. And you know what? I
37:42 I I don't really like I don't know, I just don't really like the layout here. I think personally
37:46 the navbar is kind of an issue. So, what I'm going to do is I'm going to go and I'm going
37:50 to see if I could find a navbar from something else and I'm just going to include a screenshot.
37:57 So, like this navbar is actually really cool, right? Like this this is clean. So,
38:00 why don't I just take this navbar from my former site? Okay. And then why don't I also just create
38:06 a big voice prompt about all the things I want to change. Hey, I have a navbar that I've supplied
38:11 you with. I want you to make it that sort of pill style because I think it's really high-end
38:15 and clean. I don't need the Earth logo next to left click. You can just use uh left click. Um,
38:20 we should have buttons on the hero header. Also, just make the hero header way bigger. I want it to
38:24 be like huge. I want the content in there to just pop and and explode. There's some weird
38:29 numbers next to the hypereefficient acquisition graph. Um, they're outside of the bounds of that
38:34 little box. So, let's fix that up. Um, let's add another section between scale without compromise
38:40 and trusted by the best. That just talks about me. My name is Nick Sarif. I run Leftclick. I've
38:46 helped uh I don't know over 400 500,000 people now use AI automation and then outbound methods
38:53 to improve their lives and their businesses. Um you can do a quick little Google about me as
38:57 well if you want. And then down at the bottom, um let's just add a footer in addition to the CTA so
39:03 that it's just a little bit thicker and there's more going on. Okay. And then I'm just going to
39:06 dump that right here. And I'm just going to dump that right here. So boom. Let's just remove that.
39:12 Uh and then Yeah. And then I'm going to paste. I guess I got to paste the image, right? Yeah.
39:15 There you go. Cool. So, now that I've I pumped all this stuff inside, um I'm just going to wait
39:19 for it to finish the change and then I'm going to double back. Meanwhile, I designed another website
39:23 simultaneously uh for my content writing business. Once I can copy. So, I like this. This is really
39:28 clean. We then have that little pillow up top with similar three card design here with some
39:32 text. That's neat. Uh we also have these cards that kind of come up. I really love these cards.
39:37 These are really clean. And then down over here at the bottom, we have some pricing. So, that's nice.
39:42 Anyway, I just wanted to show you guys that while we're waiting for the other leftclick site. Okay,
39:45 and I can see it's saying the dev environment is still running. So, I'm just going to copy
39:49 this. Go back here and paste this in. And this is way bigger. Look at that. This is huge. Nice.
39:56 This is significantly better. I'd say that's about the size that I wanted. And then up here,
40:01 I think it's basically just one for one copied the font. So, I'll just make one more change, which
40:05 is to make sure that the style of this aligns with the style of the site. Hey, just want to make sure
40:08 the style of the pill navbar aligns with the rest of the style of the site. Super clean. Nice job on
40:15 everything else. Oh, and I'll supply you an image that you could use. Um, for me, that will help.
40:21 Really like the footer as well. It's pretty clean. Let's make the green just a little bit darker,
40:26 actually. Um, that's probably the last thing that I want to change. Everything else here looks nice,
40:30 though. Man, there's a lot of images of me out there. We'll go large. What makes sense? Which
40:34 one makes me not look like a seven-year-old? probably this one. Let's just do that. So, I'll
40:38 go here. I'm going to copy both the image and the agent, I think. So, we'll just dump that in. So,
40:45 I'm just going to copy this here, and then I'll paste this in. Okay. And then, yeah, I should be
40:51 good. And this is the finished product. Uh, what I like is when I load it, there's that little bubble
40:56 that goes out. You know, it expands at scale. Uh, navbar is looking nice and clean. When we mouse
41:00 over it, it's green. We have everything that I asked for, including a picture of myself with
41:04 like slightly darker green. And yeah, I mean, like, you know, is this again going to win any
41:08 awards? Probably not, especially since website design is so commoditized these days. But now
41:12 that I've showed you how to build sites, not just one site, multiple sites, by the way, and probably
41:16 a hundth of the time it would have taken you to do uh websites the old school way. And I know
41:20 that cuz I used to be a website designer. I used to get paid for stuff like this. Melts my heart.
41:24 Let me show you how to deploy it and how easy it is to actually get a website like this up live on
41:27 the internet uh with Vibe Coding. So, basically what you're going to need is you're going to need
41:31 a hosting provider. Now, I use Netifi because it's simple. It's uh free for a couple of sites anyway,
41:36 but you can also use Verscell and there are a few other ones that are like this. Basically,
41:40 what happens is they just take these sites that we just put together. Okay, so whatever this,
41:44 you know, link is here that I'm opening up and then it takes the static files on your
41:50 computer that you're currently accessing at localhost 5173 and then it just like puts
41:54 them on a web accessible URL. So, we're going to have something like gentlebeaver uh.netlifi.com
42:01 and we don't need to spend any money in order to get that done. It's completely free for us. Um,
42:05 it'll only cost us money if we require like a custom URL like leftclick.ai for instance. So, I'm
42:11 going to go over to netifi.com. Uh, and then I'm going to, you know, if it's your first time there,
42:15 sign up. I'm just going to click login. And I have a bunch of different projects down over here,
42:18 um, that I've hosted on Netlefi before, right? So, make money with make reply robot leftclick
42:23 go one second copies. You can see I've had quite a few startups that have failed. Uh, and what I'm
42:29 going to do now is I'm just going to click add new project. And then uh you know I'm going to click
42:34 deploy manually and then I can just drag my drop drag and drop my project folder here. So simply
42:41 put I'm going to go back to my um anti-gravity and then what I want is I just want to rightclick
42:45 this and say reveal and finder. I'm just going to drag this whole file in. Okay, this whole thing.
42:51 And what it's going to do is it's going to try building and deploying. Now the probability this
42:54 is going to work the very first go by the way is pretty low actually because we're not giving it
42:58 any additional settings or anything like that. So, I mean, I'm going to look for it, but I doubt that
43:02 it's actually going to oneshot it. If it does, I'd be quite surprised. Wow, that's so funny. It
43:06 just did. Uh, that's hilarious. I wasn't expecting that. I was going to expect communicating with an
43:10 agent to get it done. But anyway, yeah, we just drag and drop the folder in Endearing Salyaki.
43:14 And as you can see, our whole website is up. It's actually up on the internet now. It's not up um,
43:18 you know, where it was before. So, I'm just going to open an incognito window just so
43:21 you guys are 100% confident that it is on the internet. I just accessed this. Why don't I um,
43:26 load this up on my phone, too. endearing. Okay. And I don't know if you guys could see this,
43:32 but like that's the website. It's just on my phone now. It's on a totally different um you
43:37 know device. So yeah. Hey, I'm uh Nick Sarif and today I'm going to show you how to get a website
43:43 up on the internet in like a 45 seconds flat. Kind of neat, huh? So this is more or less going to
43:49 be the approach that I'm going to use to push all of our apps to production just because, you know,
43:52 I don't want us to have to spend a ton of money in order to like actually run server infer and stuff
43:55 like that. But yeah, in general, like you know, if you're using a predictable library like this,
43:59 it's pretty straightforward. Obviously, not every single time is going to go that easily. And I'm
44:03 going to show you guys what like more complex app pushes look like. In general, what I do now is I
44:07 just give my agent um an API key to the service like Netlify. And then I just say, "Hey, you know,
44:11 push this." And then it'll actually go through and then do all of the work. Um but hopefully
44:14 you guys see how easy it is to oneshot a website with Gemini 3.1 Pro. Cool. So that's how to design
44:20 a website. The issue with websites is websites are really simple. They have no authentication.
44:25 They have pretty cool UX as you can see and you can get progressively more complicated as the
44:29 models get smarter. Um, but there's no like actual like like security or or data transmission that's
44:34 really required, right? There's no interactivity. So when we migrate from uh you know websites to
44:41 apps, what we need to do is we need to understand a couple things about security. And if we don't
44:47 understand things about security, what'll end up happening is the same thing that happened to
44:50 some pretty popular libraries. You guys might be familiar with like OpenClaw pretty recently or a
44:54 Claudebot is what it was called before its 40th rebrand. And the reason why part of the reason
44:58 why I rebrand it so much is because there's just so many security problems with it. Like people
45:01 had 25,000 API keys leaked. API keys being like basically the equivalent of like a password to
45:06 a service. That's pretty important. Uh not to mention, you know, API bills that were run up
45:10 because hackers and stuff like that got access to it. Or just like leaked data from users that use
45:16 a specific thing. Never a good situation to be in. So, I don't want to pretend like I can solve 100%
45:21 of all security wos for you. I can't. The reality is everything on planet Earth is hackable. It's
45:27 just a question of how hackable. And the whole idea of like 8020ing security is just to get
45:32 your point get to a point where your app is less hackable than the amount of effort that it would
45:37 require to do it. And so almost like anybody could theoretically break into anybody's house,
45:43 but we don't because there's just like a little bit more effort is required to like, I don't know,
45:47 break my window than just walk into my front door. Um, if you just like do some 8020, I don't know,
45:52 put a fence in, have some camera outside your front door or something, you'll eliminate the
45:55 vast majority of like lowhanging fruit. Okay, so I just want to run through the 8020 here. 80%
46:01 of security problems in vibecoded apps will come from five things. The first is exposed environment
46:06 variables and API keys. The second is missing or broken rowle security RLS on your database. The
46:12 third is no server side validation which is where you trust the front end for all of the
46:16 validation steps. So verifying that a password is a password and email is an email. Verifying
46:21 your logic and your math and stuff like that. The fourth is using outdated or hallucinated packages.
46:25 Very important. And the fifth is not having what's called proper authentication middleware. Now again
46:30 you don't need to be a computer programmer to get all this stuff. I'm going to explain it while we
46:33 talk about it. What's really important is when you actually go through and develop, you know,
46:37 like a like a database for the most part, you just like click the RLS button. Um, when you set up an
46:43 app, you just tell Gemini 3.1 Pro High or, you know, Claude, hey, you know, I don't want you
46:48 to do server side validation. What's important is that you just have it run through all of its
46:52 packages afterwards or say, hey, do we have proper authentication middleware on every page? You know,
46:57 hey, are our environment variables and API keys exposed publicly? And so I guess what I'm trying
47:02 to get at is it's actually not that difficult to like hit the AD20. You literally just like create
47:05 one prompt and then you just feed it in as sort of like a postbu workflow similar to what I showed
47:10 you with the code review initially. So we can just pass all the stuff in as a prompt and I'm going
47:14 to do that and give you guys the prompt later and it'll do pretty good. But obviously you know it's
47:19 not perfect. No security ever is. This should just allow you to launch apps without feeling like a
47:23 fraud or needlessly endangering other people's credentials. So let's chat about the first
47:26 which is environment variables and then secret management. For those of you guys that don't know,
47:30 in computer programming, you typically have to deal with the equivalent of a password. And so
47:34 we call these passwords various things, tokens, authentication credentials, environment variables,
47:39 API keys, whatever. But they all sort of like come to the same idea, which is that it is something
47:43 that if uh a user has access to it, they can typically access a bunch of features of their
47:49 account and not somebody else's. And so the issue with vibecoded apps is a lot of people with their
47:55 agents actually hardcode authentication tokens and secrets and environment variables into their
48:02 code. And the way that I see it is this is kind of like putting a sticky note with your password on
48:06 the front of your monitor like you see in a lot of like older school cubicles where it's like Gmail
48:11 password 1 23123 Nick is super sexy.com whatever and like anybody that walks by will see that and
48:17 they will know your password. It's kind of like that with um exposing environment variables and
48:22 secrets inside of like a a front end. So, also a lot of hackers will go through the website and
48:28 app code and then just look for hard-coded mentions of a specific string like next_pub
48:33 uh you know whatever key or secret key or what and that's a common string prefix. And what I mean by
48:37 that is like you know if you load up the website that we just had a moment ago which I don't
48:40 actually remember the password I don't actually remember the thing. So one sec. Yeah. Yeah. So,
48:44 if you go through this website, we can actually like right click, we can press inspect. And uh
48:47 as we scroll through, we'll actually be able to like command F different elements on the page. So,
48:52 weaponize, for instance, is actually like written in the code of the page. I guess you
48:55 guys can't see cuz my fat head is in the way. You guys see how down here I just command F
48:59 weaponize and then we actually found the specific segment. What if we do personalization? Right,
49:03 that's there. How about initialize sequence when I'm selecting this element? So what I mean by uh
49:09 exposing your credentials is basically a lot of the time somewhere on the front end people will
49:13 write code so that when you click the map growth button up here which we just found down over here
49:18 um there'll be some additional thing like like I don't know on click equal and I don't even
49:24 remember like the actual function definition for this but uh whatever you know fire my API
49:29 key you know to whatever the website is and then I actually like expose my API key which
49:36 is right over here and so basically we is we just want to avoid situations where I actually have,
49:41 you know, on click fire my API key to this location and here it is in plain text. Um,
49:47 we also want to avoid the loca uh situation where you have something like next public key equals
49:52 whatever because if you have either of what I just mentioned, somebody can just go on your website
49:56 and then do the equivalent of like a command F or control F and just type in like next public
50:00 key and then they'll find something. It's really dumb, but um you'd be surprised at how many really
50:05 like high-profile libraries it's happened. That's one of the issues that I've had with
50:08 uh well anyway I'm not going to name any specific names but yeah I've had some issues with some some
50:12 recent vibe coded products because of this. So what do we do instead? Well basically you put
50:16 them in a file like av and then you just reference them using imports or you tell the model like hey
50:20 you know I want you to look in the specific place for all of my API keys and credentials. And so if
50:24 I show you guys a practical example just using you know anti-gravity basically what you do is
50:28 somewhere in the core of this you'd go env uh key and then it would look like this and then no like
50:36 um anthropic private key and then it would look like this right and so basically what you do is
50:42 you'd say hey what's my um enthropic key and uh if you ever needed to use it to like construct
50:49 something the model would instead of looking through your your code base here and finding
50:53 it like just written directly in a codebase. It would do like a command f through the entire
50:58 thing. It'd look for something like an enthropic key or something like that and then it would go
51:02 and it would actually find that it's 3 if4 and as you can see it's analyzing the specific file to do
51:06 so. So this is just like a programming convention. Just keep all your passwords everything like that
51:09 inside of av. Another benefit is you usually don't push keys to like an a repository on the
51:15 internet. Normally you just keep that locally on your computer and then you give that to whatever
51:19 like the app user or whatever to upload their own keys. Pretty simple stuff. Not rocket science. The
51:22 issue is just nobody actually does this. Nobody actually asks their agent to make sure that all
51:25 this stuff is done. The second is this idea of rowle security. So um as you guys are going to
51:29 see in the next project, we're going to use a database and the database that we're going to
51:32 use is going to called superbase. It's very very popular with most vibe coder projects right now.
51:36 And basically it's like the single most important security feature on planet earth. But um you know
51:41 these databases out there just don't enable this by default because it's just not something that
51:45 you know is enabled by default. I don't know. I'm not a super in-depth computer programmer.
51:49 but it changes a couple of things and some people don't want to use a database like that. Basically,
51:53 what this means is if you don't have this feature enabled called RLS, anybody who has
51:57 the Superbase URL and then what's called the anon key, which is public by design, can read, write,
52:01 and delete every single row in your database. And that's just how Superbase works by default. And so
52:05 some very popular vibe coded projects here did not have level security. And basically anybody that
52:09 signed up for them was given a key, sort of like a password, and then they just use that password to
52:14 search up all of the data about every other person on it. And that led to like a massive massive,
52:19 you know, issue. Try not to swear in these videos, but it was a cluster. And uh, you know,
52:24 that ended up with people's ability to delete rows and databases, which was stupid. All RLS's.
52:30 Basically says like, hey, user A can only see user A's data. User B can only see user B's data. Like,
52:36 obviously, it's not rocket science. Uh, but if you just turn this on, you'll fix like 90% of errors.
52:40 Okay, so 83% of exposed superbased databases involved RLS misconfigurations. uh 83%. That
52:46 means like only 17% of exposed superbase issues were not related directly to this one thing that
52:51 I'm telling you about that is basically just a button. So we're just going to click enable and
52:54 it'll be fine from now on. But just make sure to know RLS is like the main lowhanging fruit. Next
52:58 is something called serverside validation and um a big problem with that is like you know how we just
53:03 developed a website, right? Well, let's say on their website there was some form and the form was
53:07 um I don't know it was like a sign up form and it said you know enter your email here and then enter
53:11 your password and then let's say obviously in order to implement any sort of sign up mechanism
53:15 what we kind of have to do is we have to check to see does the email already exists in our database
53:18 and so what the server side thing what the front end thing would do is it would basically say okay
53:23 let's match the email to something in our database well um when you do this sort of ser uh front-end
53:29 validation where you validate like all of the logic on your on your website um it's massive
53:34 security risk because as you just saw a moment ago, anybody can jump into the code of any website
53:38 and then immediately change it. Like I could go to google.com and then I could, you know,
53:44 um hold command shift C or rightclick and then go inspect element and then I could select anything I
53:50 want on the page like this Google search button. Then I could actually change it from uh I don't
53:55 know this input class which is called Google search and I could change it to nick search.
54:01 And now I've just changed Google's website, right? Accordingly, what I could also do is if there's
54:05 some form here when I put my information in that does my email or whatever, I could actually like
54:10 have it go through a bunch of email addresses or a bunch of passwords and then it would change the
54:15 email and password that is being done the valid accordingly. If I had a forum and this forum,
54:20 you know, was like checking emails or checking passwords or something, I could actually go
54:23 through and then I could like see the data, see the function that is actually doing the checking
54:26 and then I could like look at it and I could be like, wow. So the logic that that guy is using
54:29 to check if passwords exist is he's checking to see if it's over uh I don't know three characters
54:34 and the maximum password length is 10 characters. That means that uh you know I could theoretically
54:39 enumerate through all passwords between three and 10 characters and then I'd be able to find
54:43 out anybody's password. You know it's like this just gives attackers way too much information.
54:47 Likewise, it also allows them to do things like, you know, if uh a specific email address already
54:52 exists in the database, what you could do is you could use that same email address, but you could
54:56 change the request that's being sent. You could sign up a million different email addresses using
55:01 some script. It's just not very scalable, I would say. Um, and it's not very intelligent to do. So,
55:06 instead, what we do is we actually do server side validation. And what that means is like basically
55:10 we have our site right over here. And our site in general communicates with some server. And instead
55:17 of doing all the validation over here, okay, what we do is we say, "No, what I want to do
55:23 is basically every time somebody tries to create a new account, I'm not actually going to check
55:26 on the site. What I'm going to do is I'm going to send a request over to another backend somewhere,
55:29 some server. The server is going to be much more secure. And then because it's not on the site,
55:34 nobody can like jump into the server and then make minor changes to, you know, check out the
55:38 logic and stuff like that. The only thing that an attacker would actually ever see is just the
55:42 fact that, oh, the site sent a request to the server. uh but you know the server is like super
55:46 password gated and you know requires specific authentication. It's not anything that you know
55:50 a person could actually use. So that's kind of easy. You just ask your AI model, hey you know
55:54 make sure to server side validate everything. Hey, is anything here not being serverside validated?
55:58 Okay, we'll make it serverside validated. And that takes me to number four, which is dependency and
56:01 package security. Um so when AI generates code, sometimes it references packages that don't
56:05 exist as in your AI will literally just make up a package name. In case you guys didn't know what
56:09 packages are. Basically inside of most folder most coding uh projects nowadays you have like
56:13 a node modules folder or something. And these are all the services that this um repository is using
56:19 in order to like build my website. And so it's using witch word zod yto q prelude puny code
56:26 react and so on and so forth. And so as you can see like most websites nowadays are actually like
56:30 very very heavily based on pre-existing libraries that other people have built which kind of makes
56:34 sense cuz like you know the longer the internet's around the more people have built libraries that
56:37 handle specific features and like obviously you're going to want to just use somebody else's solution
56:40 rather than build your own wheel and so that's what a lot of people here are doing. Tailwind
56:44 CSS for instance is a big design library that just does a lot of the design for you. Arg parse just
56:48 handles arguments and it's like a simple and easy way to you know do bash scripts and functions.
56:53 And so the issue is AI just came up with all this stuff, right? But sometimes it'll actually
56:58 download or it'll create a name of a module that doesn't actually exist. So for whatever reason,
57:04 I mean the training data or whatever or just because of the way statistics works,
57:08 maybe it'll create a folder here or uh whatever called acorns and it'll try and download a library
57:13 called Acorns and it turns out the library it wanted to download is actually called Acorn, but
57:17 instead it tries downloading Acorns. Now, people that have done a lot of stat stats and stuff like
57:21 that have like done a lot of this to see, you know, what libraries the um AI models typically
57:26 screw up on. And so, if it sees like, oh, you know, this always says acorns instead of acorn,
57:31 what it'll do is it'll actually these attackers will go through and they'll make a big list of
57:35 all these fake packages. And then they'll actually create packages on the internet that correspond
57:40 to these. And then these packages will just be malware. So, instead of you downloading Acorn,
57:45 now you're downloading Acorns. instead of it being empty and being nothing because it's fake,
57:49 now you're downloading somebody's package that actually has like a string in it that says, "Hey,
57:53 you know, when you download this package, I want you to send all of the API keys to this service."
57:57 They as like, "Oh, yeah, that makes sense. I'm downloading this package. This package is legit.
58:01 Let's do it." And then it sends all the API keys to the service. So, I mean, like in practice, it's
58:04 not anywhere near as big of a deal as just like server side validation um issues or RLS, but yeah,
58:10 I mean, like it can be a problem. Another issue is AI will typically download like older versions
58:14 and stuff like that if it's not constantly instructed not to which means you might be
58:18 pulling in a package with a security vulnerability that you know actually got patched months or years
58:22 ago. So in general the recommendation is ensure you get the most updated packages as possible
58:26 as opposed to like you know older ones. And then finally this authentication middleware bit. Um in
58:31 case you've ever accessed like an authenticated service before typically the way that it works
58:35 is you'll have some thing. So I'm just going to open up a new thing and I'll go cloud.ai. Um,
58:40 I don't know, slashnew. When I click on this, do you notice how it just immediately jump me back
58:45 to sluggin? Claw. New is like how you make a new thread, right? Well, there are some apps out there
58:51 where you'll pump in like claw.ai/ um I don't know, maybe chat or something like that. Okay.
58:59 And then basically you'll be able to act despite the fact that you're not logged in, you'll be
59:02 able to access chat if you just know that like the URL is chat. Now obviously these guys are a
59:07 major billion dollar maybe even trillion dollar company by now. So every time I try and access
59:11 this it immediately jumps you back to login. But this is behavior that is handled by this thing
59:15 called authentication middleware where basically when you try and access routes that aren't your
59:18 routes okay like settings and general and new and and chat u it just knows that okay well you're not
59:24 actually logged in so I can't show you that. I need to get you back to the login page first.
59:27 And so you know poor app design includes people forgetting to put in authentication middleware um
59:32 and then people have the ability to access pages they shouldn't. And then sometimes it like allows
59:36 them to manipulate things, rack up API usage uh calls and stuff like that. So you can fix this by
59:42 just ensuring middleware secures all routes. Okay, so like I didn't want to make this little module
59:47 here because it's boring as hell, but just know that you know most people that build vibe coded
59:51 apps will miss one of these five features and then vibe coding in general just gets a really
59:54 bad name because people just don't secure their [ __ ] right? The reality is like nothing is 100%
59:58 secure as I said, but if you just do these five things and then um you know ask your AI models
60:03 to fix them, uh you know, it'll do a reasonably good job and I'd say about 80% of your security
60:07 issues are going to be handled, especially that rowle security thing. So what I've done is I've
60:11 actually gone through and I've created a massive prompt for all of you guys that you can use
60:14 right over here. It's called the security audit prompt. You just copy everything below this line,
60:18 okay? And what you do is you give it to your model and you say, "Hey, you know, I want you to check
60:23 to see if all of this stuff is done." Then after you're done, um, you know, flag all of your issues
60:29 and then ask me what you want me to do about all these issues. So, hypothetically, I mean, I'm just
60:33 going to paste this whole prompt in, and I just did to our website. Um, the issue with the website
60:38 is obviously there's no real authentication going on, right? So, it's not like it really matters too
60:42 much. Uh, but still, you know, it's a reasonable way for us to at least run through this. And now,
60:47 uh, Gemini 3.1 Pro High, and I always recommend using the smartest model for this stuff, is now
60:51 just going to like take this prompt, pump through literally everything, and then just say like,
60:55 "Hey, this is good. Hey, this is bad. Hey, this is good. Hey, this is bad." And then we're going
60:58 to secure it by basically just saying, "Okay, fix everything that's bad." Okay. And now it's given
61:03 us a big returned checklist. It's saying that the codebase is a classic static front end. Here's
61:08 the systematic audit. No hard-coded secrets, no API keys, and so on and so forth. No git ignore,
61:15 which is something that they typically recommend to um prevent you pushing yourv, no console log
61:21 statements, you know, a bunch of things. And it looks like, you know, we didn't actually have
61:25 any to go off of for most of this. If you scroll all the way down, it'll actually show you like
61:29 here's the big checklist summary. Uh because this isn't an app with any authentication, right? So,
61:33 it's just like a website. And so, because of that, only these checklist features are the only things
61:36 that are relevant. But we did fail two. So, I'm going to say is fix the two that failed. And then
61:43 uh it's just going to go through. It's going to add the git ignore. It's going to add a couple
61:45 other things. You know, this takes time, right? I mean, it it's going to take me some token costs
61:49 as well. I'm going to spend some money on this essentially. So, unsurprisingly, people don't want
61:52 to do this and uh that people typically forget it. But, you know, this is an 8020 pass. It's
61:57 not going to fix everything, but it's going to fix the low hanging fruit, which is to be honest what
62:01 most people really just care about. When you vibe code an app and you publish it and then it starts
62:05 scaling and you start making some money from it obviously then you can take some of that money use
62:09 it to hire maybe an actual security engineer and have them audit your project and stuff like that.
62:13 Okay. And here you go. It did. So it updated this to add the get ignore and then it updated this to
62:18 um update eslint and resolve all four high high severity mini match vulnerabilities which is
62:23 cool. So yeah, looks like we are now solid. Let's move on to something a little more interesting,
62:27 which is taking everything that we now know about how to build a beautiful front end and then how to
62:31 do security audits and stuff like that and then combine it into a full stack app. So,
62:36 next up, we're going to build a fullyfledged SAS app. The app that I want to build today
62:40 is a client dashboard platform for a hypothetical content writing company. And so, like any typical
62:47 client dashboard, we're going to want to be able to create orders, um, view pending orders. We're
62:52 going to want to have like a nice sexy dashboard which gives us an overview of everything,
62:56 our stats and so on and so forth. Then we're also going to want some sort of like settings
62:59 or configuration page. Then on top of that, we're going to need some sort of login naturally. And
63:04 then I think at the very end, I'm also going to produce a nice sexy landing page just to tie it
63:07 all together. And then I'm going to push it uh live to production as well, just so you guys could
63:10 see how it all interacts. Before we actually do the building, I just want to run you guys through
63:14 what I consider to be the uh basically major vibe coding design loop as of right now. And obviously
63:20 there's a bunch of different ways to build apps. And I don't want you guys to think this is like
63:24 the the end- all beall. There are many many different ways to do this. But in my experience,
63:28 this is like one of the one of the good ones right now. And if you follow this sort of flow,
63:32 um you'll save yourself a fair amount of time later on just in terms of like the design and
63:35 then also security because um as I talked about in the security module, there's a fair amount
63:40 that goes into designing like a wellsecured app. So the way that this works in general is
63:44 we start with some sort of inspiration design. And so there are a variety of different places
63:48 you can go to for these inspiration designs, but in general, I like going to um this website here,
63:53 Dribble with threebs. I like going to this one called godly uh website. And basically,
63:59 there are a bunch of these sources on the internet that compile really high quality designs. And like
64:04 logically speaking, I'm not a designer, right? I haven't spent all the time and energy necessary to
64:09 know the right padding and the right color schemes and all that stuff. So it's like,
64:12 why would I worry about coming up with all that stuff myself? instead I could just borrow somebody
64:16 else's and then we can make some changes to it and then once it's all changed and and and all
64:20 nice and pretty. Um you know like we will have taken the design fundamentals that somebody spent
64:25 a lifetime putting together and then we could just work off of that instead of spending god knows how
64:29 long trying to figure out like the total amount of margin on the left and the right hand side of the
64:33 uh the elements. It's crazy stuff. So as somebody that's like been doing a fair amount of design,
64:38 I got paid for design. Uh it's not worth the time and energy that it goes into learning all that
64:41 stuff. So we start with an inspiration design. I'm going to grab a couple of these. And then you have
64:46 an optional step here which a lot of people are starting to do now where you animate. So the idea
64:50 is since Vibe coding now makes uh the ability to like replicate designs and have high-end
64:54 designs really really easy. You know you need a way to stand out. And so the way that people
64:58 are standing out now is through animations through um like kind of videos that are playing. The idea
65:02 being that you know a still can't make video based stuff super super high quality. So you could still
65:07 um stand out as like human created content or uh designs with something like that. I'm going
65:11 to show you guys how to do that. Anyway, uh this does cost a little bit of money
65:14 because there's some models out there that you need that can convert images to videos,
65:17 but I'll I'll run you guys through what that looks like um for the landing page. After that,
65:20 we need to build in the main functionality, which is always going to be the dashboard. It's going to
65:24 be things like, you know, your various widgets, your various pages, and stuff like that. Then,
65:28 we're going to do local testing and iteration. Local testing, just so we're all clear,
65:32 just means testing it on your device, and it also means testing it with uh without a database. So,
65:36 we're just going to do all the file and then, you know, uh, data and stuff like that in like a JSON
65:41 and then we'll just test it all locally, make sure that it works. Once we've made sure that it works,
65:45 we'll then push our data to a database. And then, in our case, we're going to use superbase. I'll
65:49 talk about that in a sec. But then, um, we'll test it all basically with the database. Once
65:53 we're done with that, then and finally then do we create an authentication page. And I find um,
65:57 doing O at the end is way better than doing O at the beginning because if you guys remember,
66:00 I mentioned like middleware, right? Well, like a big issue with the middleware is you'll just
66:04 like the low hanging fruit is you'll do the O first, then you'll make the pages and then the
66:07 O will only secure the first page that you do. So instead, we're just going to do our O at the
66:11 end and then the model will already have all the context to like produce um you know good
66:15 authentication middleware for all the pages and then at the very very end we're going to deploy
66:19 and then obviously the issue with you know testing back here when it's sort of on your machine and
66:25 then deploying is like you you need to test it again. So we're going to do some end toend tests.
66:28 We're going to do some miscellaneous designs and I'll probably just throw in the landing page there
66:31 since obviously the landing page doesn't really have much functionality to speak of. And uh yeah,
66:35 that's that's more or less the loop. And then you know like when you're ready what you do is
66:38 you just do the exact same thing. You just make a new product and then you start with
66:41 the inspiration design. Um you can do some video animations if necessary main functionality local
66:46 testing database testing off deployment and end tests and then landing page. Then my inspiration
66:50 design animate and so on and so on and so on and so forth. So I do this on basically all my
66:54 vibe coded apps and uh yeah works pretty well. So the common vibe coding stack which I'm just
66:58 calling the usual suspects here are going to be a combination of Nex.js for the front end
67:02 a superbase for the database and the off and then some sort of serverless backend which
67:07 um in our case is going to be netifi but you can use netlifi versell and a bunch of these
67:10 other tools but this is just what people mostly use because it's just very easy to spin up. So,
67:14 to make a long story short, in case you know, we have people here that aren't familiar with the
67:17 idea. Um, you know, when you sign onto a website, obviously this is my really crappy rectangle. Um,
67:23 and this is our browser with the three little dots, maybe the URL bar and stuff like that. And
67:26 you have like the app over here and I don't know, some sidebar. And then here's some other stuff,
67:31 you know, like what what you're seeing, what's rendered here is is the front end. And um there's
67:37 already different front-end languages, right? I mean, like HTML is hypertext markup language. It's
67:41 usually used to create the structure of the page. If you have CSS, which is cascading stylesheets,
67:45 that's usually used to like make the the rendered elements really pretty. And then,
67:50 you know, if you want functionality on top of that, you will use JavaScript and, you know,
67:54 TypeScript. And there's there's all these different languages, right? Well, basically
67:57 what happens is um using all these languages, there's just so many different ways you could
68:01 use them that all the developers were using them slightly differently. Some were more efficient,
68:04 some were less efficient. What people ended up doing is they created uh front-end frameworks.
68:09 Okay. Well, not even just a front-end framework. NexJS is technically also like it's like a full
68:12 stack framework but um they made frameworks which just encapsulate all three of these into you know
68:18 this thing next.js and so what this is this is basically like a full way to manage your HTML
68:24 CSS your JavaScript all these other programming languages and then builds they build it in a
68:28 very opinionated way that consistently produces similar outcomes and you know follows a consistent
68:33 and predictable pattern so that most developers can just spin up a site really quick. This is
68:38 doubly important in the age of AI where you know when if things aren't standardized there's like a
68:42 million billion different ways that an AI model could make a site and because usually there's a
68:45 lot less supervision when you're viing than um you know like a traditional development process. A lot
68:49 of these ways just like aren't really well thought out. You know AI just picked the simplest lowest
68:53 hanging fruit and went with it. So I recommend using these frameworks and stuff like that just
68:56 both to economize your work but also just to make sites predictable. If you ever hand them
69:00 off to anybody if you're doing these for clients and stuff like that you know next.js is the way
69:03 to go. Okay. So that's the front end. Um you know Superbase is going to be our database. So, I mean,
69:07 just think of it as like a big Google sheet with like a bunch of different tables and columns. Wow,
69:11 my drawing skills have gotten worse recently. Uh, but to make a long story short, you know,
69:16 the stuff that is visualized on our front end, like our bar charts and our little widget apps and
69:20 stuff like that. Obviously, we need to pull the data from somewhere, right? So, it doesn't make
69:23 sense to keep all the data like on the site cuz it's always changing. What we do is we're going
69:27 to pull from a database and then like use that to actually go and and change features. Obviously,
69:31 we're going to need a login screen, right, with like a little user uh portal and then
69:35 like a little password portal. Um, let's round that off so it quits looking phallic. And uh,
69:41 Superbase is going to help us with that as well. And then finally, you need what's like called a
69:45 backend, which is basically just like a server. And this server is actually going to manage the
69:49 interactions between our database, our front end, our off, and and you know, a lot of stuff. So, you
69:54 know, that's a little bit more cloud-based. You're not really going to fully I can't really just draw
69:58 something that makes sense there. But suffice to say, all these four components are going
70:01 to interact together really nicely. And then the stack that basically all the tools use is Nex.js,
70:05 JS superbase and then some sort of what's called serverless um back end. Okay, so we could go
70:11 into that or we could just build it and I'd much rather just build it and then you guys could learn
70:14 through the doing. So let's start with the very first step which is finding an inspiration design
70:18 and I'm going to immediately jump on dribble for that. So dribble for those of you guys that don't
70:23 know but just go on the website. It's basically just a big list of like different designs that
70:27 people have made and it's cool. It was it was initially meant to be like a way for designers to
70:32 create a portfolio and show off the work and stuff like that, which is pretty neat. Now, you know, to
70:36 be honest, I think a lot of people are just using this to source AI designs. I don't know how much
70:39 longer we're all going to have access to dribble, but uh we'll see. And, you know, in our case,
70:44 what we're looking for is we're looking for some sort of like client dashboard, right? So, I'm just
70:48 going to type client dashboard in here. Basically, what you'll see is a bunch of people have created
70:52 these really sexy client dashboards. So, I'm just going to click on a couple of these. Um,
70:57 yeah. So, I I already opened that one. So, let's click on this. Let's click on that. This one's
71:01 actually pretty nice. And then, hm, why don't I open up? No, I don't really like that one. That
71:05 one looks kind of dumb. This one here looks cool. Okay. And as you can see, you know, I now have
71:10 um like a list of, in this case, all clients on the lefth hand side. You know, this sort of like
71:14 nice gray pattern, and that's that's kind of cool. I don't really like this one a ton, though. So,
71:18 I'm just going to keep looking until I find one that I really really like. Um, what you'll find is
71:22 a lot of these are now videos as well. And there are a couple reasons why they're doing videos. One
71:26 of them is that they don't really like when people screenshot them like I'm about to. That design's
71:31 cool. Okay, this is reasonable. Um, this one's pretty interesting. But the one that I initially
71:37 picked that I just liked the look of was this here, which is super simple and it's very like
71:43 extensible and you guys can add on whatever the heck you want, right? So, I think I'm going to
71:46 use this. And uh, basically what we're going to do is I'm going to create a screenshot of this
71:51 and then I'm going to use the model to try and replicate this as closely as humanly possible.
71:55 And I have a prompt set up that I'm going to I'm going to send it to and stuff like that. And then
71:58 from this we're going to get like a really high quality design. And then I think I'm also going
72:01 to do the same thing for the landing page. Um you know this design is different from this design but
72:06 uh you know I'm just going to find a way to like meld the two together. And then I think at the
72:09 end we're going to have something that like has the color scheme of this but it actually has like
72:13 the design of this if that makes sense which is ultimately what I'm going for. I like that design.
72:16 I like this um I guess this is sans ser but I really like this font. So yeah let's uh let's
72:21 give it a go. So what I'm going to do first is I'm gonna head over to anti-gravity. Okay.
72:25 And then I'm going to open up a new folder. And I'm just going to call this full actually let's
72:31 go lowercase full stack client dashboard. That's going to be my very uh first full stack app with
72:38 you guys. And then what I'm going to do first is I'm going to talk a little bit about the different
72:42 types of models that we have available to us. Remember how before we designed our landing page
72:46 entirely using Gemini? Gemini 3.0 Pro is awesome, but personally I find that actual like system
72:50 plans and system designs are better done through Opus 4.6 right now. So, what I'm actually going to
72:54 do is I'm actually going to do the planning in Opus 4.6. I'll show you how to do that. First,
72:58 let me zoom in because this is pretty far out. And then I'm just going to go to um plan mode here. If
73:03 you just keep on cycling through, eventually it'll get to it. It's the one with the little
73:05 pause sign. And then I uh created a prompt here that I just want to go through with you guys. So,
73:10 the prompt says, "You're a world-class website designer with 15 years of experience designing
73:14 high quality, award-winning websites for Apple and Dribble. We'd like to build a full stack
73:18 SAS client dashboard app for our content writing business. It's very important that you get this
73:22 right. our career depends on it. This is a little hack that I picked up from um I think it was like
73:26 a former OpenAI dev or something, but they found that when uh you make it really really important,
73:31 like our career depends on it, the output quality actually goes up just by a few percentage points,
73:35 nothing major. And my prompt is not winning any awards here. So, uh anyway, I'll take every win
73:40 that I can get. As a client, we want the ability to view all pending content orders and progress
73:43 in a beautiful dashboard. We also want the ability to create new content orders using a
73:47 highquality but simple form. Let me just run this. We want the ability to configure various settings,
73:52 modes, etc. And we also want anything else. Your usual SAS app like this would include
73:56 the dashboard. SAS app should use superb. I said superbase here. What I meant to say was superbase,
74:00 but I was using a voice dictation. So, what are you going to do? Next.js and then tailwind.css.
74:05 And we will deploy using netlifi. I'll define the UX via screenshots. So, don't worry about design
74:11 particulars. The flow will be first we'll build the main functionality, which are the parts I
74:15 talked about above using a screenshot inspiration. You'll take the design style from the screenshot
74:19 and then use it to build all of the signed in pages. Then we'll make it interactive with local
74:23 data and ensure routes work. Then we'll add O and DB with superbase. Then we'll make a landing page
74:27 and finally do an endto-end sweep to ensure everything works including off, middleware,
74:30 security, testing, etc. Then deploy and retest. Then I'm saying think extremely hard and generate
74:35 a great plan. Once you've developed one that is comprehensive, report back here and I'll supply
74:39 some screenshots. That's how we can start the design process. Okay, so I gave it a fair amount
74:43 of context and you can see it's already done some thinking, right? put the text stack and looks like
74:48 it corrected my little issue there with superbase phased approach right they want me to plan this
74:52 out comprehensively there's nothing in the current um working directory so it looked it couldn't find
74:57 anything green field project and now it's actually going to go and create the architecture and that's
75:02 what's that's what it's doing right now that's why it's in plan mode now I should note here in the
75:06 bottom right hand corner you guys probably I don't know if you guys could see that's pretty small we
75:09 got this little lightning um what I've done is I've enabled this thing called fast mode just
75:13 because Opus 46 supports it and that allows it to go two and a half times is faster approximately
75:17 for I think like 3x the price. So little bit of an arbitrage there. Um I think the price is going
75:22 to jump up to 6x pretty soon. So it may not be available when you guys are on it. But personally
75:26 I find for building really comprehensive plans awesome tool and an awesome model. Okay. And
75:31 then uh basically what I wanted to do is I wanted to like produce this big plan and then I'm going
75:35 to pass off this giant plan over to Gemini who I think is actually just a better designer. Okay. So
75:40 once the uh thing is super comprehensively planned um then I can just pass all this stuff to Gemini
75:45 with the screenshots. But sometimes claude code will actually ask you or rather Opus 4.6 will use
75:51 cloud code to ask you questions and so that's why I'm doing all this planning and stuff like
75:54 that here just in case it asks me some questions for clarification. Okay. So I'm going to press
75:58 escape because uh it's basically like hey do you want me to start? Then here it's going all the way
76:04 to the top here. We want to build a full stack SAS dashboard. Here's the tech step. Here's the
76:09 phase one project setup in UI shell. And um I'll be honest, like I'm I'm usually not reading this
76:13 entire thing. What I'm doing is I'm skimming. I'm just making sure there's nothing that just
76:16 jumps out to me as stupid. Like what I want is I basically just want to see, hey, are there way too
76:20 many pages? Is this way too complicated? Is this model completely misunderstood what I want it to
76:24 do? And so what I'm seeing is there'll be like an app page, there'll be um a dashboard page,
76:31 orders, a new page, a settings page, notifications page, and that looks pretty reasonable, right?
76:35 There'll be a components page where it'll actually store all the components. Library page. Okay,
76:39 this looks pretty good. This looks pretty good. Interactive local data. So after that,
76:44 we'll define some types. Yeah, I don't even know what the hell that really means to be honest, but
76:47 that's okay. And then we have those actual pages, which look good to me. All of these are pages
76:51 that I would realistically want my app to have. Is there anything else I'd want? H dashboard orders.
76:55 No, I think I think this is fine. After that, we have the superbase off. So here, I'll like set
77:00 up the superbase, but that's okay. That's not for now. That's later. We'll finally have the landing
77:04 page which is going to be really nice and sexy and then we'll have some key architecture decisions.
77:10 Okay, cool. I mean, this seems pretty reasonable to me. I don't think there are any problems
77:13 here whatsoever. So, what I'm going to do is I'm actually just going to copy this whole plan. Okay,
77:18 this whole thing that this just created for me. I'm going to paste it into this now. Okay. And
77:24 then I'm also going to provide some initial screenshots of what I want the dashboard to
77:27 look like. So, I'm just going to command um you know on a Mac you can command shift control. So,
77:34 command shift control 4 and then I'm just going to go select this. Okay. And that'll actually
77:40 give me like a pretty high quality screenshot. I'm going to feed this in. Okay. And so now we
77:46 have the image of the dashboard and then I'll say design using this style as inspiration clean and
77:53 minimal. Okay. Okay. So, what I've done is I've now split the work up between these two agents.
77:58 I had um Claude Opus 4.6 design me the really comprehensive plan because as I mentioned I
78:02 think it's a little bit better at planning at least as of the time of this recording.
78:05 Then I'm going to hand off all of like the design and then you know basically just like grunt work
78:11 over to Gemini 3.1 Pro High, which I think is way better at actually like wiring up the components
78:15 and then putting together like that that really high class design. And uh you know at this point
78:20 all we really have to do is just wait for it to build. And this is realistically because it is,
78:23 you know, going to be a pretty comprehensive app. This isn't something that's going to happen in a
78:27 couple minutes. You're probably gonna be good to like go step away, have a coffee, come back. By
78:31 the time all that stuff's ready, this will have given you some sort of result. But it's always
78:36 good before you do that just to like wait for, I don't know, 30 seconds or so because sometimes
78:40 it'll give you a plan and then you can just review the plan um and just double and triple check that
78:44 it didn't do something super stupid or super terrible. And I don't think it has. Everything
78:49 here looks good to me. So, I think it can just go ahead and commence the project. Cool. So,
78:54 I'm actually going to go grab a coffee and I'll be right back. Okay. So, now it's telling me it's now
78:57 completed phase 2 interactive with local data. So, we should now have a site up and running with some
79:01 sort of local data. Immediately after I said let's open it. So, it's opened it. I tried doing some
79:06 initial debugging and stuff like that on its own. It it didn't end up doing so because there was an
79:10 additional error which I'm going to talk about. And just on the uh I guess concept of errors
79:15 when you create a full-fledged SAS app like one that has like back and forth and stuff like that,
79:18 not just a website where there's no interactivity, you know, you're going to have errors. And so it's
79:22 not about like will I screw up at some point. Will the model get this wrong? Just a matter
79:27 of when and then what you're going to do when uh it screws up. So basically what I've done is it
79:32 started the development server and opened this in my local browser. So I just click this open and
79:36 as you can see here we have the app set up, but the app looks a little funky. We don't have any
79:40 styles. Just looks like crap. So obviously this isn't what we want, right? What I'm going to do
79:44 instead is I'm just going to take a photo of this and then I'm just going to send it back. And then
79:47 I'm going say I don't think styles are loading also because I'm pretty sure there was some issue,
79:53 right? I initially got this problem as well where it said missing HTML and body tags in the root
79:57 layout. So I'm also going to copy this in. Also, I got this error. I'm going to paste that in. So,
80:03 you know, at least initially before you even get to be able to play around with the UX,
80:07 you may have some like initialization problems and config problems and stuff like that. And that's
80:11 okay. Basically, what you do, um, if I just show you guys sort of how I think about vibe coding
80:16 these things is it's almost like I don't know, you're in a cave. Uh, have you guys seen like the,
80:22 you know, mining meme where you're like mining for gold? Okay, basically you're in a cave and
80:27 every single time you run the thing, you're like this fella here. You just get a little bit further
80:32 and a little bit further and a little bit further and you know this fell here can't see anything.
80:38 It's just darkness in front of him, right? So every time he mines, he goes home and he's like,
80:42 "My god, I didn't make any progress today." But obviously if he just continues going, eventually
80:46 he gets to the point where there's a bunch of gems sort of on the other side. And so that's basically
80:49 what we're doing. We're just going to work through this initial sludge with initialization errors by
80:53 copying and pasting um any problems and then just giving it directly to uh the model until we get
80:58 to that little gold gem. Once we're here, we can actually start making real changes to our app. Um,
81:02 and all of that is reasonably well expected. Okay, speaking of which, it just modified some of the
81:06 CSS after I sent it this message. And as you can see, we now have a little dashboard set up,
81:10 one on the left hand side. So, we've already made some some reasonable progress. I'm just going to
81:13 dashboard, see if there are any issues. Okay, I'm not seeing any issues at all. So, we have five
81:16 total orders, one in progress, two completed. This is just some fake data made up. So,
81:20 you can see we can now mouse over each of these three things or uh five things. SAS growth guide,
81:25 Q3 newsletter, so on and so forth. So, these are all the orders that we have submitted as clients.
81:30 There's a little notification toggle. Um, if I click on the orders page, we're now here. So,
81:35 you can actually see the orders better. I'm just curious if I click new order, what happens? Okay,
81:40 so we're now on a new order page where I can actually add info. So, I'm going to say this
81:44 is an example. New order, content type, landing page. Hey, I want to build a really cool, sleek,
81:50 sexy landing page. And then, you know, I want some stuff here. And then here's my requested deadline.
81:57 I don't know. We'll say March the 1st. We want to add SEO meta tags and then require approval.
82:02 I'll click save order. Okay, cool. And it looks like it's got the functionality. And so I can now
82:07 actually add orders. If I go to settings, what do we got? Demo user, Acme Corp, email address,
82:11 cool preferences, email notice, weekly digest. Okay, so these aren't working. At least the
82:15 weekly digest isn't. But that might be intentional just because we don't have um access to, you know,
82:20 some sort of email. But yeah, I mean like to be honest, like the the core functionality
82:23 of the app's already made. So although the design is still pretty shitty, I would say
82:27 and obviously I'm going to want to fix that up. Um core functionality is done. We basically have
82:31 like I want to say a REST API, but we have like a little CRUD app here. We can create, we can read.
82:36 Um I don't actually know if we can update. Doesn't look like we can go to the specific order page to
82:41 update yet. So maybe I'll make a note of that. Um but we can presumably also Oh no, I don't think we
82:46 can delete either. Okay, cool. Anyway, this notice page also has notice. That's kind of neat. Um,
82:50 I think what I'm going to do now is I'm just going to voice dump in all of the problems that I see.
82:54 And then we're just going to go back and forth until we can eliminate just the minor little
82:58 errors like styles and stuff. And then once we've tested and confirmed the functionality here, then
83:02 I'm going to do a big stylistic upgrade. After we've done the stylistic upgrade, I will uh then
83:07 make this database friendly. And then once it's on the database, then we can actually push. Hey,
83:11 this is really well done. Nice job. When I click on a new page, there's initially some there's a
83:17 there's a brief initial load where it says loading orders or loading settings or a loading dashboard.
83:23 I'd like you to remove that. I don't want any sort of loading um widget here because it just makes it
83:28 look lower value. Instead, I want you to maintain the structure of the page and just leave all of
83:33 the various sections blank. So, for instance, if I were to click on orders, rather than it say
83:39 loading orders before it populates the rest of the page, uh where it shows me the table and stuff,
83:43 I just want you to present the table to me immediately and then just leave it blank. That
83:47 way, we could fill in the text um afterwards. Um right now the navigation text is in light gray.
83:58 I'll take a screenshot and I'll show you what I mean. But on the orders page, for instance,
84:03 um the text that says orders at the top lefthand corner is very similar to the background color.
84:08 So that's annoying. I'd like some sort of graph on the main dashboard page cuz right now I don't
84:12 have any. I'd like a way on the dashboard page to click into the recent orders as well. Uh
84:17 right now I am capable of mousing over them and something changes, but it's just a style effect.
84:21 I actually want the ability to click on them. In addition to being able to create, I also want to
84:25 um be able to click on each individual article on the orders page and then view it. Right now,
84:31 when I click view, it says either order not found or it takes me to some error page, which is not
84:38 what I want. The notifications page has a mark all red button that is currently grayed out. When I
84:44 click on the notifications at the top right hand corner, that little icon, nothing happens. So,
84:49 I'd like that to just take me to the notifications page. There's also nothing that happens when
84:52 I click on my little profile picture in the top right hand corner. Under settings, when
84:58 I toggle weekly digest, nothing happens. Email notifications works, but the weekly digest toggle
85:03 doesn't. There's a nextjs error here called param property was accessed directly with params.id.
85:09 Params is a promise and must be unwrapped with react use before accessing its own properties.
85:14 Nothing happens when I click on the little demo user button in the bottom lefthand corner either.
85:20 This is quite a promising start. We just have a few adjustments that we have to make. Uh so
85:24 that functionality is perfect. Once you're done with that, let me know and then we can proceed.
85:28 Cool. So I've just added all this context and I'm just going to take a screenshot now of that
85:32 issue that I talked about where the orders text was um you know kind of gray. That'll
85:38 provide some more context. I'm keeping this small intentionally because every new pixel is like
85:43 more tokens than I'm consuming, right? There's some other minor stylistic changes and stuff,
85:47 but for now I'm not going to worry about the style. And the another reason why is because
85:50 um once you have an app that's like up and running like where all the functionality is right then you
85:54 can just like open a new Gemini instance and not have any context and then just say like hey here's
85:58 my app I just want you to change a design and then it can just go into the style sheets and stuff
86:01 like that make it really sexy. Uh whereas if you try and mix all of this stuff into one big long
86:06 context window sometimes it can get messed up. So you know I just want this specific chat right now
86:11 to focus on the main functionality and then we can worry about the design afterwards. Anyway,
86:14 let me just make sure I didn't add in any additional information. Cool. Cool. That looks
86:19 good. Grade out. Okay. Why don't I do this? There you go. Cool. So, now deliver that information.
86:26 And just like um last time, uh I'm just going to sit tight and wait for it to relaunch. Okay. It's
86:30 telling me that it's now updated everything. I'm just going to click accept all. And then
86:33 we'll go back to the specific page. Let me click on settings. Cool. We don't have any issues there.
86:39 Um everything there looks fine. Oh, you know, I think there's one thing I forgot to point out,
86:43 which is this um notifications button. I think that's going to be okay because we're probably
86:47 just going to massively change the style here. But yeah, that looks fine. Let's actually click on a
86:51 specific order. Nice. This is now pushed all the way to the left. The order um arrow looks really
86:54 nice. I don't know if there's a way for us to uh mark this as completed now, right? Okay,
87:00 cool. It also says start work. That seems kind of odd. I wonder why it says start work. Um yeah, I'm
87:05 noticing that as well. So, I think we're probably going to have to remove that. The model might like
87:08 fundamentally misunderstand what I want. What I basically want is I just want the client to have
87:11 like a dashboard where they could see it all. Hey, I'm noticing there's like a start work button. Um,
87:16 just to be clear, this is a dashboard for a client to look at the work that is currently being done
87:21 by the agency. So, they don't have the ability to start work or anything like that. Just go
87:26 through and fix this. So, if there are any other idiosyncrasies, um, those are taken care of. Okay,
87:30 cool. We got that last change here. And it looks like everything is now super clean. Um, no major
87:35 issues whatsoever. If I click on this button, uh, we only have readon access. Essentially,
87:40 clients can't make any changes. they can only download stuff and the HC is what initiates that.
87:44 So that's what I wanted. From now on, what we're going to do, rather from here on, what we're going
87:47 to do is we're going to redesign this because I think the design is kind of elementary at the
87:50 moment. And I'm going to use that same approach that we talked about earlier. We're going to find
87:53 a really high quality pre-existing design and I'm going to have Gem and I basically go through and
87:57 then modify this to match. Um, and the idea is it should be able to modify this to basically be like
88:01 almost pixel perfect. Uh, we're just going to like change the fonts and stuff like that. Okay. So,
88:06 I'm going to go through dribble again. And I mean, I like this idea of like a light mode dashboard.
88:11 Uh, I really do. Uh, what we had before is kind of mid. So, I don't want that. I do like the idea of
88:19 like something dark on the left hand side, though. Kind of break it up a bit. So, I'm going to see if
88:24 I could find something that is dark. Let's take a quick peek at this one. This one looks all right.
88:30 You know, I really, really like this one. This one looks super clean. Check that out. Okay. So,
88:34 I'm a big fan of this. Super big fan of that. I think what I'm going to do now is I'm going to
88:39 take this screenshot. Okay, copy that in. And then I'm going go back to Gemini. I'm going to paste it
88:46 and I'll say, "Hey, this is great. I'd now like to change the design significantly. You should
88:51 do the vast majority of your work in Tailwind or whatever stylesheets that you're currently
88:55 using to build this." Um, in short, I think the design right now is very basic and super simple.
89:01 I want you to add significantly more complexity um using things like cool
89:06 mouseover effects on navbar elements on the lefth hand side. I want you to add really highquality
89:12 icons. I'd like you to modernize the design significantly. I want you to try different fonts,
89:17 higher quality fonts. I want you to use like cutting edge um new ones that are on Google fonts,
89:23 etc. I want you to use some placeholder images so that the design feels alive. And I also want
89:28 you to significantly upgrade the graph. What I've done is I've given you a screenshot from a similar
89:33 design that I like a lot and I want you to mimic more or less everything that you see here just as
89:38 a uh just as a start point. I'll modify the design slightly afterwards, but try and really nail the
89:46 font colors. Uh try and mimic the font styles. Try and mimic the um encapsulation, the border styles,
89:53 cards, etc. Okay, this is looking a lot cleaner. I'm loving how it did this design. You also see
89:59 way higher bar charts, way cooler bar charts. Um, this takes me to what looks like a mini landing
90:04 page that I put together. That's interesting. I wasn't even like looking for a landing page,
90:08 but it's nice that it did. So, and we even have like a little look at that. It's like a little
90:11 notion um avatar up top. Cool. Um, my tasks are still the same. When I click this button,
90:16 you see we do have that higher quality design, which is nice. And nothing pops up for calendar.
90:22 Nothing pops up for reports. Nothing pops up for portfolio. Nothing pops up for these buttons.
90:27 Neither does it pop up for those buttons. Let me just check the bottom. Okay. And then yeah, the
90:31 settings work. So, basically, it's just populated this with a bunch of additional buttons that we
90:34 don't need. I'm just going to tell it to remove all the stuff that we don't need. And then I'm
90:37 also going to have it adjust the font a little bit cuz I think the font's the same. Hey, this looks
90:41 much better. Fonts are the same though. So, I want you to adjust the fonts. Um, I'd also like you to
90:47 change all of the major titles from title case to sentence case. For instance, task completion over
90:54 time should be sentence case. Apply this to all other elements and boxes. I'm liking the design
91:00 quite a bit. Nice job on the avatars. I think you should add borders rather than shadows around
91:06 things to better match the task beto design. I'm also noticing that you put a bunch of additional
91:11 buttons that we don't need. Like for instance, calendar, reports, portfolio, product management,
91:15 project management, real estate website, my first portfolio, all team product team, invite team,
91:21 supports, that little thumbtack icon, the play icon, the integrate icon. These aren't things
91:30 that we actually need because there's no pages that will address them and I don't plan on making
91:34 them. So, I'd like you to remove all elements for whom we don't have pages because that's
91:38 not really relevant. um make the search bar apply to our current list of orders and then update the
91:47 design of the settings page because right now it looks the same as it did before. And then finally
91:52 in inbox the button that says mark all as red is um almost completely transparent. It's very
91:58 difficult to see unless you mouse over it. So fix that as well. I think that's more or less the last
92:03 round of edits and then we can get into publishing this. Cool. And this is the final result. I have
92:07 a very clean dashboard. You see with that scroll on the right hand side, we don't have any issues.
92:12 Down at the bottom, we have only the pages that are actually relevant to us. Now, of course,
92:16 I could add like a million pages here if I wanted to, but I don't really. I mean, like this is just
92:19 the purpose of the app, right? I think in our uh crazy vibe coded economy, you're going to
92:24 find that like a lot of apps are going to have unnecessary features and whatnot just because they
92:27 can. I think simplicity is actually going to end up being quite the moat. So, yeah, I'm going to
92:31 keep things as simple as humanly possible. Uh but yeah, everything works, which is really nice. So,
92:35 you know, if I click on this app, uh, sorry, if I click on this specific content page, you know,
92:39 you can see that I'm I'm here. Content's being written and stuff like that. I don't have the
92:42 ability to modify like I had last time, you know, I can download stuff if necessary. If I go back to
92:47 the dashboard, this um graph is interactive. Uh, you know, and I I can jump into this anywhere I
92:52 want, which is kind of neat. And then down at the very bottom, which you guys can't see cuz
92:56 my fat head's in the way, I have the settings page, which is pretty neat. Um, and then, yeah,
93:00 we also have the ability to search tasks up here, which is really, really cool. Um, I could type SAS
93:05 growth guide and then that's an initial piece an additional piece of functionality that was added.
93:10 Okay, so I'm just going to clear that notif. And now that we've like really basically built this
93:14 whole app directly on the computer, it's time to take this to the cloud. So, what I'm going to do
93:19 next is I'm going to go to anti-gravity and just before we proceed with our next step, I'm going to
93:24 ask it to save everything that it's done so far into a gemini.mmd that effectively encapsulates
93:30 what this app is, everything we've done so far, and then provides instructions for future models
93:33 in case we need to pass this off. And the reason why I do this is because you might actually run
93:38 out of like context. Um, that happens pretty often. For those of you guys that don't know,
93:41 there's only a certain number of tokens that you can actually fit into one conversation with an AI
93:45 model these days. Whether it's like Opus 4.6 six with a 200,000 context window. They have
93:50 a 1 million context window option as well. Whether it's, you know, Gemini 3.1 Pro high,
93:55 I think I think it has a 200k context window, might have a million. The point I'm making is
93:58 like a lot of that context just used up by the internal thinking of the model as it does tasks,
94:02 right? So, in my case, like I I just don't want to risk it. I don't want to like get the thing to the
94:06 point where it's gone a little too far and then it barely remembers what we talked about initially.
94:10 Instead, what I want to do is I basically want to like have this almost like a backup of where we
94:14 are right now. This gemini.mmd file which uh you know in my case is just a very highle summary that
94:19 talks about where we currently are in the process and you know what we need to do and stuff like
94:23 that and then also gives instructions for you know where to go from here. So once we're done with all
94:29 this and now we have this which is sort of like my fallback what we can do is we can um move on with
94:34 the next step. So I'm going to say fantastic the current design looks great. What I want to do next
94:38 is I want to ensure that it works not only locally but with Superbase as our database. Walk me
94:45 through everything I need to do. In case you guys didn't know, Superbase being our database. Um,
94:49 this isn't something the model can actually set up entirely for us. Instead, what we're going to
94:53 do is I'm just going to ask it to walk me through. And that's what it's done. Create a new Superbase
94:57 project up here. Set up the Superbase client and so on and so forth. Create the database
95:01 schema. Enforce RLS. That's really important like we talked about. Then replace hooks. and
95:05 we're actually going to have it do some of this stuff, but we'll start with database.new. So, I'm
95:09 just going to jump over there. It'll now ask us to create a new project. Now, in my case, I'm already
95:13 signed into Superbase. So, I can just click that button and then boom, it's done, right? They own
95:17 the freaking domain name database.new. They got a lot of this, right? And they've streamlined the
95:21 setup to match. But, uh, if you don't already have a Superbase account, just open up an incognito
95:25 window and then just go to superbase.com and then just click start your project in the top rightand
95:31 corner and then just enter your information down over here. email, password, you can continue
95:34 with GitHub, SSO, whatever, and just make an account. They're fantastic. This is like a really,
95:38 really solid app, and uh it simplified the development of like vibecoded sites 100x over. So,
95:44 once you're done with that sign up, um you'll be at a page like looks like this. I'm just going to
95:47 type I don't know, Nikki Poof. I really got to get more mature names for these. Uh okay, why don't we
95:55 do I don't know. We'll just do client dashboard app. Next up, we need a database password. So,
96:03 I'm actually just going to make like a my own fake one and then I'm going to copy it over. Actually,
96:07 maybe we'll just generate one. The generated one's weaker. So, I'm just going to copy that.
96:12 We'll enable the data API. This stuff looks good. Then I'll click create a new project. Okay. So,
96:17 we have our database passwords right here. So, just so that I don't lose this, I'm actually
96:19 going to give it the password right here. And then I'm just going to have some additional
96:24 other lines. So, boom. It's now created the um thing for me. And then I think what I do next
96:31 is I have to go to project settings. There's a project ID over here. So I'm going to copy this
96:36 over and then I'll go project ID. Paste that in. And then I need the superbase superbase URL as
96:43 well. So I don't actually know exactly what that URL is, but I'm just going to copy the dashboard
96:48 name as well. So the project name, paste that in. Let me just see if there's anything else.
96:52 Project URL and on public key. So I think we need to go to API, which might be over here. API keys,
96:58 which is right over here. We're going to create a publishable key. That's one that we want. And
97:03 then I'm going to copy this. And then I'll say publishable key. I'm just going to paste that in.
97:11 Okay. So now this should be everything the model needs. I'm not entirely sure. I think it is. So
97:15 we're just going to give it all that information. We're going to have it do the rest of this for us.
97:20 Um and then cool. Looks like this is going to take care of that. That's going to take care of
97:25 the database schema. Oh, sorry. We need to take care of the database schema as well. So anyway,
97:28 I'm just going to give this its information and then we'll have it tell us what to do next. And
97:32 now we'll have edited an ANEV file, which is pretty clean. It's going through and it's adding
97:37 the information that we just gave it a moment ago. And now what it's going to do is it's going to
97:40 give us what's called an SQL schema, which is just like the next step. And I imagine it'll just ask
97:44 us to copy and paste something. It's also doing things like wiring up the login and signup forms
97:47 to Superbase O, which is super cool. So I mean, we should have basically everything good to go aside
97:52 from the landing page after this is done. Okay. Okay. And then it's told us to go over here to SQL
97:55 editor and then paste this giant file in. Um, so I just did that. Since these are comments, this is
98:00 just going to run a bunch of these simultaneously. So I'm going to click run selected. Okay. And then
98:03 it told me to go over here and then paste all the stuff in and then just press run. So that's what
98:07 I'm going to do. This will basically create us a bunch of um tables and whatnot in our database.
98:13 So if I go to database now, we we're going to have a bunch of different tables and they're all going
98:16 to connect in a specific way. And this is now taking us to a signup page here. We obviously
98:20 still have some changes that we need to make. So, I'm going to do that after I verify whether
98:23 or not this works. Now that it says signing up, account created successfully. Please check your
98:26 email to confirm your account. I don't know if um we're going to get that because sometimes we have
98:30 issues receiving emails. So, let me just pump over to my own Gmail real quick. Okay. Yeah,
98:34 looks like we did. So, I can now confirm my mail. Um that's taken us to I think like this
98:38 hastily putting together landing page, which is not actually the page that we want. So, I'm going
98:43 to click sign in. And then I think my email was this. I'm not entirely sure. And then my password
98:48 was that. Let's click sign in. Okay, cool. Yeah, we actually did sign in. That's wonderful. Um,
98:53 perfect. Now we have this dashboard, which is kind of neat. My tasks. Uh, cool. We can click
98:57 new task. Now we can create a new content order. So, I'm going to go example content order. Make
99:03 XYZ. Cool. And then we may have to change the order options here, too, cuz I don't think I uh
99:09 included that. Let's just select that. Click save. Okay. Let's just make more characters. Okay. So,
99:16 there's some issue with the database because it's not refreshing. So now what I'm going to
99:21 do is previously we're just testing the design and then iterating on that. Um now I'm going to
99:24 discuss like functionality. Hey, this looks great. I created a new task using the new task button,
99:30 but when I went back to check the list of tasks, I didn't have a content order in the database.
99:34 So I'd like you to double check why that is. It may be an issue with the adding to the database
99:39 or it may be an issue with the pulling from the database. If there's a table problem or something
99:42 like that, let me know. While I was doing that, I noticed that there was an order options section
99:47 on the right hand side of um the new orders page. It looks like uh there aren't buttons or anything
99:52 here. Like I can't really toggle this on or off. So just refactor that so there's toggles
99:57 um and those toggles actually do something and they're meaningful. And then also make sure that
100:02 whatever we're seeing in this chart, it accurately reflects the data in the database. And then I also
100:09 noticed when I tried oh on the landing page here it's a mixture of orange and purple designs. I
100:15 just want you to make everything here purple. The signin button is um almost transparent. It's very
100:21 difficult to see. And I'm noticing that there's no way to log out once you're logged in. So just add
100:25 that functionality as well. I need to be able to log out. Can't just stay logged in forever.
100:30 Cool. So I'm just going to pump all that stuff in and then I'm going to go. So we're getting
100:35 closer and closer to the end result. Cool. also just made some additional changes. I'm just going
100:39 to head over to new task. I'll say five ways to increase XYZ. See in the right hand side we now
100:44 have some toggles which looks nice. And I'm just going to add some keywords. I like the idea that
100:49 we could pick those. So I'll click save. And I'm still not seeing it in the database, which is kind
100:54 of annoying. Uh must be some problem. Okay. And I'm just retesting this now. Create new content
100:59 order. Blah blah blah. I'm click save. And looks like we actually got it in. There is still some
101:04 fake assignees, I think. So, I'm going to I'm going to have that fix that. However,
101:08 if I click on this now, you can see that we have the brief and then we also have some keywords,
101:12 which looks really nice. And then we have some really nice formatted stuff on the right,
101:14 like details, format, word count, deadline, and so on and so forth. So, big fan of that. We see
101:19 the ID of the order up ahead, which I guess could be useful if I'm trying to contact my agency. Hey,
101:23 I can't see a thing on my dashboard. Yeah, what's the ID? Then, when we go to dashboard, we can now
101:28 see this has been updated. And it looks like it's using some sort of mathematical formula here to
101:33 divide this so that the top of this is always going to be equivalent to the total number of
101:38 maximum orders in a in a certain period. So that's pretty neat. I like that. What else did we need?
101:43 Uh we didn't have the ability to sign out. So I'm just going to double check. Do I have the ability
101:47 to sign? Oh yes, I do. It's just hiding behind my head again. So at the very bottom lefth hand
101:51 corner, I click log out. Okay. Now I'm back to the client dashboard, which is nice. Uh what I'm going
101:56 to do is I'll go back to sign up. Okay. And then that looks pretty cool. And then I'm just going to
102:00 try go back to the actual landing page. Nice. So it actually did fix this up. Although this landing
102:04 page needs a lot of work, which we're going to fix up in a moment. Uh and then cool. Yeah,
102:09 we have the ability to sign up. We have the ability to sign in. I mean, this is pretty
102:11 solid to me. I don't really think much else needs to occur. I'm going to modify the design on both
102:17 the signin pages, sign up pages, and the landing pages. I'm going to make the landing page really
102:21 sexy uh just to wow you. And then yeah, I think I think that's more or less it. Oh,
102:26 I guess what we should finally do is we should check to see if we if we have middleware. So,
102:30 what happens when I go slash orders? Notice how it immediately jumps back to the login page. How
102:35 about if I go /dashboard? Nice. How about if I go orders new? How about if I go settings? How about
102:41 if I go what else did we have? Notifications. We got notifications. Nice. So, it looks like our off
102:47 middleware is pretty good right now. Um although I'm obviously going to have to double check that
102:50 with that big prompt that I talked about earlier. Now, why don't we modify the design? And once the
102:55 design's ready, we can actually push this and make this public. And then once this is finally pushed
102:58 and made public, we can um round out the the end of our site and it'll be really high-end and
103:02 really clean. So again, for design, I'm going to go to dribble and then I'm going to find a really
103:07 nice high quality uh let's just see if we can find some really nice high quality screenshots.
103:12 I just want like a super sexy hero header, you know? I want it to just be insane. So why don't
103:16 we go landing page? I just want this to be the the best thing ever. This is really neat. Elevate your
103:24 trading experience. Liquid brokers. H I think I'm probably going to want a white mode thing though,
103:30 like a light mode as opposed to a dark mode. Cuz if I go dark mode, it'll just seem kind of weird.
103:37 So, I think what I'll do is this section over here that says AI powered adwords that find lead.
103:43 I think I'm going to roll with this. And then I'm going to try and have some cool animated section
103:47 over there on the right. So, unfortunately, I think this is about as big as it gets. Um,
103:52 sometimes, again, they don't want you to uh like I don't know if you can tell, it's kind of blurry
103:57 here. Sometimes, as I mentioned, they don't want you to uh copy these designs a ton. I'm still
104:01 going to give it my best effort, though. So, I'll go back here. I'll paste this in. Excellent. Um,
104:07 what I want to do next is modify the landing page, the sign-in page, and then the sign up
104:13 page. I'm going to attach some screenshots of the design. In addition, I'm also going to provide
104:18 you a an animation that you could use to run in that right-hand side pane. What I'd like you to
104:24 do is I'd like you to combine our design with the design in the screenshot. I want it really
104:29 clean on the left hand side. I want my main value proposition. I want some hypothetical logos um in
104:36 the center. You could just use some some plain text for that. You don't need images. Um, I want
104:41 a relatively long landing page here with sections for product, sections for pricing, hypothetically,
104:48 uh, and then obviously a button up at the top that says sign in. And then for the video, I want you
104:54 to use this URL. Now, what I'm going to do is I'm going to paste this in. And then I'm going to go
104:59 back here. And what I want is I basically want a cool asset. And then I want to like rotate it with
105:04 AI. And I'll show you what I mean here. Uh, but basically I just want some sort of asset. Let me
105:08 see what can we get from dribble that looks really clean. Okay, so for that I'm going to go over to
105:12 dribble and go 3D shape. Um, I really like one of these shapes, but I think I want this on like
105:20 a white background. Let me see if we could get something that might make more sense. H organic
105:26 3D shapes over here. This is cool. Round egg 3D shapes. That's kind of neat. Feel like this would
105:32 be nice if we could get a white background on it. So, why don't we give this a try? What I'm going
105:37 to do is I'm going to take an image of this. Then I'll go over to Google video. Actually, sorry. Why
105:45 don't we start with Nano Banana? So, I'll go to AI Studio.google.com. You can sign up for this
105:52 um you know, it's the same account that you would use for whatever credits you utilized for
105:57 um Gemini and anti-gravity. Then I'll say, let's see, playground. And I want to generate images.
106:03 I'm going to paste this in. So, I create me a new organic shape that looks like this except
106:10 with a fully white background. It should look very sexy and have a purple blue hue to it. And
106:20 then the aspect ratio, I think, is going to be 34, which is three wide and then four high. And we're
106:25 going to go 2K for the resolution and press enter. Okay, just ran out of token, so I had to go to a
106:31 different account here. But it's important that the aspect ratio is 34 and the resolution is 2K
106:35 because that's approximately the same height of the design that I wanted to copy a moment ago,
106:39 right? Like this one is clearly taller than it is wide. And I think that's going to be important.
106:43 Okay, so we have this organic looking image, which is kind of cool. What I'm going to do is
106:46 I'm going to save this image as. So now this is like our own image. Then I'll head over to VO3,
106:50 which is a state-of-the-art um image to video generation model. And then what I'm going to do
106:56 is I'm just going to do the same thing. So let me just switch the accounts here. And then I'll
107:01 link the API key. Cool. And then what I'm going to do is enable Google Drive access as well.
107:08 And then I'm going to paste in this image, one that I just generated a
107:11 moment ago. We'll go 9 by6. Just copy this image. And then go back here. Paste this
107:18 in which I just downloaded. Okay. And then I'll say uh rotate this slowly. I
107:26 think 6 seconds is probably fine. So that the last frame is like the first frame.
107:34 Perfect. Uh 100% white background. Okay. I'm going to press enter. And now V3.1 is generating me
107:42 uh video. Just playing this. Now we have this cool organic undulating rotating shape which is really
107:47 neat. So I like that a lot. I'm going to download this. And now I have the video. I'm going to grab
107:52 this. And then I'm just going to dump this into public. And then I'll say hero header video.mpp4.
107:57 Okay. And then um I initially said URL, but I guess what I really meant was like inside of my
108:04 folder. public/hero header video.mpp4. Also put a dot here. Uh cool. I'm just going to press enter.
108:15 And then I'm going to give it some time and let it go on its way. Okay. Landing page design is
108:19 looking all right so far. I'm not a big fan of this video now that I'm looking at it. Like I I
108:23 would love it if it just blended in seamlessly, but for whatever reason, the background is not
108:27 white. We could remove the background and then we could remove that border and I think it would
108:30 look a lot sexier. I'm partial. I mean, I might play around with it a bit. Um, we got the logos
108:36 down here. Sign in button top rightand corner. That's nice. I think we just need to align uh
108:41 what's on like the the left hand side and stuff. So, yeah, I'm going to do that in a second. Sorry,
108:45 I just realized I was dictating. And then I'm just going to give it some instructions. Hey,
108:49 this looks solid. Why don't we align all content to the hero header? Because right now some of the
108:56 sections are really tight. So push it out so that everything's at the same width as the hero header.
109:05 Um I'm loving the colors. Something with the graph under the why they prefer Taskbo section looks a
109:12 little bit weird. I think the numbers on the cards of the maximize your traffic with the content
109:19 engine that generates section um are broken or something because they're being cut off. So fix
109:25 those. And then everything else looks really solid. Just update the business name from taskb
109:31 to content hamster as well. Uh and just do that across the entire app. And then while I'm at it,
109:39 I'm going to see if I could find something that looks a little bit better for that section here.
109:43 Okay, I found this video and I really like this. I also think probably because this
109:47 is already optimized, like the file size isn't really big, I'm probably just going to use it.
109:51 This is not a live SAS app. So, Ashkat Ash Moana, great job on said design. Um, we're just going to
109:57 be using this as a a demonstration purpose. Um, it looks like he also allows you to explore or
110:03 tweak this scene by checking it out in his spline community page. I don't even know what that means,
110:07 but I think it's like a way you can share designs and stuff like that. So, that's kind of neat. Oh,
110:11 wow. I can actually revolve it. That's so cool, dude. Wow. So, I guess you could probably run
110:15 this as 3D in your browser. Anyway, we don't want to do that. That's just a little too much. Um,
110:19 but I'm going to instruct the agent to use that image and then make sure the orb doesn't get
110:24 cut off weirdly. Also had a couple of sleek cards placed on top of the video with a glass
110:27 isomorphism effect. So, something to break it up a bit. And then I'm just going to jump back
110:31 over to our app here so we can see um as it's actually being developed in real time. You can
110:36 see we changed the name to content hamster. Kind of silly, but uh whatever. This has now
110:41 done everything perfectly with left-hand side um margin match up which is nice. Why they
110:46 prefer content hamster? This has now been spread out. So the graph is no longer all weird. Again,
110:50 perfectly margin aligned. Something with the numbers is still off. So I'm going to have it fix
110:54 that as well. Let's just do that before I forget. Hey, numbers on cards are still a bit weird.
111:04 Screenshot for reference. Then as I scroll through, is there anything else? plus premium.
111:10 Okay, ready to level up your process. Cool. And then we also have a bunch of buttons down at the
111:16 bottom here that obviously don't really work. Okay, cool. This looks really clean. I'm liking
111:19 this. I'm liking this a lot. Um, I'd say the only thing that's missing is probably like the coloring
111:24 across the board. Um, what I'm going to do now is I'm just going to match all of the colors to this
111:30 because I just love the way that that looks. Uh, I'm just going to take a screenshot here and then
111:35 I'll say colorfinder online and I'm just going to paste in this color. And as we see here, there's
111:45 this hex code. So, I like that a lot. And what I'm going to do is I'm just going to paste this in as
111:48 well. Also, I want you to update the primary color scheme across the entire application so that it is
111:55 that shade of baby aqua blue. Looks really cool. use slightly darker shades of blue as accents,
112:02 etc. And then for the accents, I guess I'll just go back to this. Screenshot it. Paste
112:11 this in here. And then we can use stuff like this as well. Um, and let's go a little lighter here.
112:21 We'll go this dark. Darkest. Cool. And now it's going to go through the entire app and just change
112:26 it to reflect like the background colors of this which I think are going to be really cool. Um,
112:31 obviously I don't want, you know, us not to be able to see the text. So I am just going to be
112:35 around like, you know, if this is that color, it will seem kind of weird. Right now we obviously
112:38 have a cool purple thing going on with all the highlighted text being purple and then these
112:41 things being purple. I do think it would just match really really nicely and seamlessly if we
112:45 had that. So we'll give that a try. All right, this is looking way better. I'm loving how the
112:48 baby blues actually reflect what's going on here. Let's click try out for free. Um, actually I guess
112:53 I already have an account, so I'll just log in. But we are going to test that out in a second.
112:57 Looks like those numbers have been fixed, which is cool. We got that slight zoom in on each card
113:01 as well, which I really like. And then baby blue effect everywhere. That's gorgeous. Um,
113:05 this little content output graph is still purple. So I'm just going to see if we change that. One
113:09 thing I didn't really talk about was mobile optimization, but um, Gemini Mobile optimizes
113:13 everything really, really well just out of the box. Obviously, we do have some minor issues
113:16 with the bounding boxes of this um, like video, the border. Uh, but this is something that would
113:21 probably be better done by actually replacing the core underlying asset because the resizing of the
113:25 border box occurs basically perfectly. Um, but just giving you an example of what it might look
113:30 like on a tablet. As you can see, everything is still basically perfect. I haven't ran into
113:34 major issues so far. Even the numbers and stuff like that are visible. And if we scroll all the
113:37 way down, the biggest problem is just there's this little black overlap. I want you guys to know that
113:41 I haven't even done mobile optimization yet, which is typically just like a line in the prompt. Um,
113:45 really, really wild that it does this good of a job without me even having to tell it. Cool. And
113:49 now we have everything changed. So content output is nice and changed. Uh you know the the the look
113:54 of the little bubbles here goes up. I mean this is basically exactly what we wanted. I also changed
113:58 the name to content wheel obviously. So why don't we now sign up and go Nick Sarif. We'll call
114:04 myself Leftclick Inc. We'll just use a slightly different email this time just so we could retest
114:08 the sign up. Uh let me just make sure this is a simple ass password. That'll always be the same.
114:13 Cool. We're going to click sign up now. Account created successfully. Please check your email to
114:17 confirm your account. Uh, I'm now going to sign into the specific mailbox that gave me that. So,
114:22 let's go here. You can see it's saying to confirm my sign up here. So, I'm just going to go back and
114:26 then I'll now be able to sign in with the specific email that I just put in. We'll click sign in.
114:32 Just delete all this stuff. Cool. And I'm just going to zoom in a bit so we can see. Obviously,
114:35 I have a really big desktop so it won't always look like that. Um, cool. We have total tasks.
114:40 You can see the styles been updated a little blue here because I just wanted it to be blue. Um,
114:44 task completion is still purple. So, I think I may update the graph. I don't really know to be
114:48 honest. It might be okay. My tasks inbox. Cool. All that stuff looks good. So, we'll now test
114:53 the new task. I'll say, "Hey, this is an example. Here's my example brief ABC." And then over here,
115:02 we'll go 13. I'll click save order. Cool. We now have it in our database. It's now a draft. So,
115:08 content is being written. Your writer's currently working on it. You'll see it when it's ready.
115:11 Inbox. Cool. Um, awesome. I mean, this looks pretty solid to me. I don't see any major
115:15 issues. So, we'll go to settings. We can update things. I don't know if this got saved, that
115:20 little leftclick thing. Yeah, it doesn't look like that did. So, now that we basically have like the
115:25 whole app ready to go, we just need to make a few, you know, minor changes before we deploy. Hey,
115:31 uh it doesn't look like the company. Okay. And then after a full endto-end check, this website
115:36 and app is now ready to be pushed um and actually deployed. That deployment is going to occur on
115:41 Netlifi like I talked about earlier. And I'm going to give you guys a simple simple process that you
115:45 guys could use in order to actually push that out. For now, I'm going to go grab some lunch since I'm
115:48 pretty hungry, but I'll BRB. So, the strategy I'm going to use in order to push this site and
115:52 make this web accessible just like we did with our old website is to use Netlefi. And in order to do
115:59 that, we're going to use Netlefi CLI and then give the vast majority of the work to the model. Um,
116:06 so Netlefi CLI is basically just a command line interface. That's what the CLI stands for. That
116:12 lets previously people like you and I, but now mostly agents interact with the Netlefi API,
116:17 which is like their little application programming interface. The way that you uh do various actions
116:23 on Netlfi using HTTP requests autonomously for you. They can actually do most of it. So what I've
116:29 done here is I've actually just said, hey, I want you to build this and then I want you to push it
116:33 on Netlfi. We've gone through the whole build. We've gone through phase one, two, superbase,
116:38 you know, phase three and now what we're doing is we're doing this final production deployment
116:43 and this is uh you know just uh part and parcel more or less the final step of getting this thing
116:49 on the internet. Now, I should say that when you actually push things to production, that's what
116:54 that's called, typically there are some issues because the development environment that you run
116:59 on your local computer is always going to be a little bit different than whatever the heck the
117:02 server is using. And so, sometimes you have to make minor changes to the site. Sometimes
117:06 you have things that work on your device, but then don't work obviously on the production server. So,
117:11 you have to, I don't know, modify like the the way the database works, some of the permissions
117:15 and stuff. And that's just part of dealing with any sort of full stack application.
117:19 wasn't a big deal with our website because our website was obviously not super interactive. It
117:23 was just a bunch of uh links. But this has some back and forth and that's what's important. So,
117:27 as we scroll up here, we can see this has actually gone through the build process, which is basically
117:33 taking our website or what our website should look like and then turning it into like an
117:37 actual instantiated version of the site. That's what that is. Um, and now it's going through the
117:41 installation process for the actual Netlifi CLI, which is a little package. And now it's going to
117:45 communicate with the Netlefi CLI. And all we have to do is we just have to authenticate. So
117:50 assuming we have an account set up and stuff like that. And what we have to do is we have
117:52 to go and actually log in. So what I'm going to do is I'm going to open this up. So I'm going to
118:00 um give it a new terminal tab which is what it's asking for. You can do that by going control shift
118:06 um tilda I think it's called. It's like that little thing in like the top leftand corner.
118:11 It looks kind of like this. Uh you should also be able to do this by going up to the top and then
118:16 going terminal and then going new terminal. And then I'm just going to paste this Netlefi login
118:21 command. And in my case, you know, I've already done this on my machine a bunch of times. So it'll
118:25 say it's already logged in. In your case, uh you know, if you haven't done this login before, it'll
118:29 just pop up a little Netlify panel and then you can do it there. So I'm going to say done. And now
118:33 it's going through the various building procedures and so on and so forth. So, my expectation is I
118:38 mean there's like a 50% chance we oneshot this because we are using a pretty standardized
118:41 framework called next.js. Uh there's a 50% chance that we're going to have to go back and forth.
118:46 It's saying the deploy is live. I'm just going to refresh this and check for myself. Okay. And
118:50 you can see we did push the actual website side of things up. So, that looks good. Just exit out
118:55 of this so we can get like the the full glory of the site. And I'm not seeing any major problems
119:00 here versus the one that was on my machine, which is cool. You know, we got these little buttons.
119:06 premium get started now. Okay. And I mean, we haven't added links to all these yet, which is
119:09 why these aren't actually popping up. Uh like changing my um little cursor when I mouse over,
119:14 but that's okay. And now what I'm going to try is actually the interactive component. Cool. So,
119:18 we have the account created successfully modal. And that's great. I'm now going to head over to
119:23 that specific email address and just check if we have the email confirmation message. Okay, we have
119:27 this right here. So, I can confirm my mail. And now we're starting to see one of the issues. So,
119:32 error parsing package.json JSON file. And it looks like the reason why we're getting that is notice
119:37 the URL up here. The URL is not actually uh the publicly accessible URL. It's this localhost 3000.
119:44 And so the way that you know user signups usually work is basically there'll be some URL here slash
119:50 some code and then the agent will configure your Nex.js or whatever full stack app framework you're
119:56 running to like accept this code and then use that to verify the account. But basically
120:00 what's happened here is the default sends us to localhost 3000. And so I know what the issue is,
120:05 but just for the purposes of like debugging and stuff like that, I'm actually going to just take
120:08 this to my agent and I'll see what the agent says. We have to go back into our Superbase settings
120:12 and then alter it. But I do just want you guys to know like how this works if you guys are actually
120:16 debugging it. So I'll say I received this error, this um call back when setting up my account.
120:27 this isn't the right URL. What should I do? And you'll see here it'll instruct us to go to our
120:34 Superbase and and make some minor changes. And then it's going to tell us to update our Superbase
120:38 dashboard settings. So, go back into my dashboard, which is right over here. And then there's going
120:44 to be an authentication page right over here on the top left. And then it's either going to be
120:49 an email or somewhere else. Like we can actually turn off the um confirmation completely. This is
120:54 the email that Superbase sends them. That's why it looks a specific way. And I don't know, to me,
120:58 it kind of looks a little ugly. So, obviously, if I were running a full production app and I were
121:02 making all those uh little bells and whistles, I'd make this look really pretty. But I think there's
121:07 actually a way to change the URL. Okay, here it is. It's right under URL configuration. It's
121:12 a site URL. And so, what I'm going to do instead is I basically just want to get the the live URL,
121:18 which is this one here. Just going to paste that in. Okay. And I'm going to remove that back slash.
121:24 So now this is going to be the URL that it uh basically redirects us to on Superbase's side
121:29 cuz Superbase handles the the signups and stuff like that. And now when I go back to the app,
121:35 I don't even have to actually make any uh major changes like I don't have to rebuild the app or
121:39 anything. Then I can give it an email. I click sign up here. And now we have another email sent
121:48 to another one of my addresses. There you go. It's right here. When I mouse over this, you guys can't
121:53 really see in the bottom lefthand corner, but I'm no longer going to localhost. And you can
121:57 see if I click on this, takes me to contentorb dashboard.netifi.app/lo. So here I can actually
122:06 um now jump in and log into the app. Cool. So that's one of the first changes I would say if
122:13 you're building something on production versus doing something locally. We just have to change
122:16 the URL that the authentication goes to. So we just did that. Now it's nice and clean.
122:21 And I'm scrolling up and down here, making sure there are no major issues that are egregious. I'm
122:26 not seeing any problems. I guess the company isn't filling in. So, we can change that. Well, I write
122:31 this. Save. Give this a refresh. Yeah, looks like the company in the profile details isn't filling
122:35 in. So, I'm just going to take a screenshot of this and then I'll paste this in. And then
122:39 while I'm like before I actually send this, cuz I prefer just to do a bunch of stuff, not just one,
122:43 let me test the new order. This is a new order. What's up? And then over here, I'm going to go
122:54 one word and then I'll save. Okay. So, yeah, this is actually in my database now, which is pretty
122:58 cool. I can click on this. Looks like the rest of this stuff is is here, which is nice. Anything in
123:04 my inbox? Nope. That's cool. And then my actual orders do populate, which is nice. And we don't
123:11 actually have like the ability to like we don't have any people on our team, but obviously we
123:14 could have added some, which is why we still have those little um little fake Notion-esque
123:18 people there. I wonder where they're getting those images from. That's kind of cool. Okay, so uh we
123:23 have dashboard. Did we I think we checked settings as well. Yep, that looks pretty good. And I think
123:29 every other toggle here probably works. Let me just try searching the tasks. So I'll just go O
123:38 H. Okay, so yeah, clearly it's just searching based off the letters. If I type in new order,
123:43 if I type in old order, then it won't be. Okay, cool. So if we had 20 in here, you know,
123:46 that might actually be useful. And let me just check the sign-in page. Okay, cool. So, we're
123:51 immediately being logged in when we click the signup page. And then, you guys can't see this,
123:54 but in the bottom left corner, I'm just going to click log out and see what happens. Okay,
123:57 so when you click log out, it takes you straight back to the login page, which is the desired
124:00 expected behavior. And then nothing is prefilled. Let's now check all of our routes. So, I would
124:06 always recommend going through every single one. So, that's dashboard. This is settings. This
124:10 is orders. This is orders. um I think and then slash new and then there's also a notifications.
124:17 So notice how none of these are automatically signing in which means some of our off uh is
124:21 fine and you know all of our animations and stuff like that look really clean and uh there there are
124:26 no problems on that end. Okay. And then I'm just going to do a final spot check because although I
124:31 told it to um you know mobile optimize the site, I do want to make sure that it is mobile optimized.
124:36 This looks really clean. You know the only issue here is with this little background not being
124:41 necessarily the same as that. I guess we could just change the background color of this whole
124:44 element. That might actually help. So, yeah, why don't I do that? That's a really cool thing. Um,
124:48 why don't we adjust the background element of our little orb to this? Adjust the background color of
124:58 the element that contains the animated orb to be the same as that background color of the orb. This
125:02 should be our light aqua baby blue. Okay, that looks nice. And then just scrolling through here.
125:08 Any other issues with the mobile optimization? Just make this really nice and small. Be 100%
125:14 sure. Nope. Everything here looks like Oh, you know, there is one. Looks like this learn more is
125:20 not immediately underneath the get started now. So, that's one final thing that I'll do. I'll
125:26 finally say also the learn more button is not um underneath the what was the name of that button?
125:33 Get started now button. So, I'd like you to line them up on mobile. Now I should know because
125:37 this is no longer local on our computer. It's on netlefi the uh debug in an iteration loop takes a
125:44 little bit longer. Naturally when we were just on our computer anytime we'd have an issue we would
125:48 just say hey rebuild it. It would rebuild it and then we'd immediately have access to it. Right?
125:51 But here we actually need to make the changes locally on our computer push them to Netlefi
125:55 have Netlefi do the build and because Netlefi is sort of doing free server space takes longer and
126:00 then we actually have to go online and then um you know take a peek at the website. But anyway,
126:05 I'm uh just going to open this up now. This is the production version. I should be able to see the
126:10 background and everything like that. Nice. And now we have more or less my exact desired behavior,
126:15 which is how that orb just looks like it's floating. And it doesn't matter how big or
126:19 small the website is. It's just like perfectly contained within those bounding boxes. Super
126:24 clean. Um and then I just had a couple of those other changes. Just going to verify that those
126:28 are good. The last thing I'm going to do is I'm just going to go down to my security audit prompt.
126:32 scroll all the way down to the bottom. And there's just a little bit of nuance here. Um, I'm
126:36 not actually going to do this in the same thread that I launched and built the entire website. So,
126:40 I'm going to use Claude Code for this instead of Gemini. And the reason why I'm doing it is cuz I
126:44 don't want any context. I basically want the model to look at this entire codebase as if it's new,
126:48 fresh, and not mine, like somebody else's. And I want it to like run through this whole checklist
126:52 and to end and tell me whether or not it's configured. Okay, so I just copied this all.
126:57 I'm going to head back to anti-gravity. Close these tabs. And I should just be able to do so
127:01 by clicking close all. Let's make this smaller because we're going to have clawed code instead.
127:07 And then what I'm going to do is I'm going to paste this in. Then I'm going to say don't make
127:12 any changes. I just want the audit. Okay. And I'm going to pump this in. And now cloud code is going
127:19 to go pass one discovery map the full architecture and then more or less tell me, you know,
127:24 what's good, what's bad. And I'm doing this for a couple of reasons. Um, obviously I want no context
127:29 as mentioned, but I also think that Claude is a lot more interpretable than Gemini right now. If
127:33 you guys check out the thinking tabs here, and if you compare them with the thinking tabs of,
127:38 you know, Gemini, Gemini uses language that just doesn't really make much sense. Um, you know,
127:42 when you look at it, it's not as interpretable. I'm now taking action to apply the color
127:45 adjustments as previously decided, focusing on the background's visual look. I'm now proceeding
127:48 by updating the styling to use desired hex code. You if you look at it and just compare it to this,
127:53 this is a lot more interpretable. I now have a comprehensive understanding of the codebase. Let
127:56 me compile the architecture summary and then work through every checklist item. They give
127:59 it to me sort of in plain English. And so the interpretability is pretty important when you're
128:03 talking security, right? Um in addition, you know, I just think Claude is a little bit better
128:07 at like security based stuff right now. Okay, so I'm I'm reading through everything here. It
128:12 looks like most of our audits are correct. We do do console. Calls, which is important. Um,
128:18 this is basically a way to minimize the attack surface uh and then minimize or maximize
128:23 operational security. We're not really giving away how our underlying tool works. So that'll fix
128:28 that. Startup validation. Okay, so we need some sort of startup validation here. It looks like
128:36 we can't tell whether or not the RLS is enabled um because we don't actually include the files in
128:40 the codebase, but that's okay. We are actually good on RLS. Uh that's why it's giving us this
128:44 warning message as opposed to a no. We're good on SQL injection, security definer functions, same
128:49 thing as uh previously. So we could have um claude like connect to our superbase instance via API if
128:55 we want. And I'm just going to take all of this default deny routing fails. This is important.
129:02 Remember how I talked about O middleware? This basically just immediately denies all requests
129:05 that don't have some form of authentication. Right now our app doesn't do that. And you know, at the
129:11 end of the day, we while are okay on most things, we're still missing some uh some things there. So,
129:17 I'll say excellent execute all of the changes. Okay. So, I'll say um the SQL stuff was already
129:27 taken care of. RLSTC, but thanks for pointing that out. Execute all of the remaining changes
129:35 and change SQL checklist items to green. And now it's going to go through and then work through the
129:42 fix the systematically form. And just to give you guys some more visibility in the security side of
129:45 things, you know, previously we had a line in our code that said if there's an error, we actually
129:49 add all of the superbase insert error details here. This is actually just like gives a bunch
129:53 of information about the way that our superbase database is configured. And that's just because
129:56 Jeem and I wanted to write it in the way that was, you know, debugable for us if you guys remember.
130:00 Well, this now went through it identified that and it changed that to fill to create order,
130:04 which is just much more general. And um that both gives us the ability to quickly see if there is an
130:08 issue, but then it doesn't expose any of our underlying in infrastructure architecture if
130:14 somebody actually wanted to attack us. As you can see, we have most of the changes that we
130:16 talked about before. We have allow list routing. We have client side user ID filtering. Okay,
130:20 server side validation. We added what's called an off call back route. Um we have environment
130:25 variable validation. And we also had some console leaks that we've since cleaned up. And just
130:30 scrolling through to get to that checklist, you know, the vast majority of these are now
130:34 green. all the issues that we had previously have been taken care of. And so 5.1 which was a dev
130:39 dependency and then 6.2 which was some built-in rate limiting. You know, we don't have control
130:44 over that. And these aren't really large security issues as well, which is why they're in this
130:48 yellow little warning label instead of the X. Um, you know, we're now good. We've basically solved
130:52 for the 8020. The vast majority of lowhanging security fruit do no longer apply to our app.
130:58 And while I probably wouldn't scale this to like a million users without at least having some sort of
131:02 security person look this over, it's pretty dang good. I just did a final walkthrough of the site.
131:06 We have the animation, which was previously hidden because of that middleware update. Um,
131:10 some of our icons are missing as well because of that same thing, as well as the login uh and
131:14 signup routes, as well as every other feature in our network. So, this is an example of like that
131:18 extra step at the end that a lot of people don't want to do because obviously it takes, you know,
131:22 an additional 15 or 20 minutes. It's about how long it took me, but I highly recommend it if
131:25 you do plan on making your app live. and actually launching it to more than just yourself and your
131:30 close friends and family. But congratulations, we have now built an endto-end full stack app
131:35 with login, authentication, signup. We have a database where we store records and queries and
131:40 then also a pretty sexy landing page. You guys now know everything that you need in order to
131:44 basically take this knowledge and then go out and actually just vibe code an app. What I want to do
131:47 next though is I don't just want to vive code any app. I want to take you guys to a higher level of
131:52 understanding of modern software engineering principles cuz I think it's one thing to be
131:55 able to just use natural language to, you know, communicate with agents and have it do something.
131:59 But some of these architectural decisions that the agents are making are actually controllable
132:02 by you. And if you know even 10% more than the average Vibe coder, you can, you know,
132:07 rather than this process takes 2 or 3 hours, you can basically just build like your little starter
132:12 kit with um your preferred stack, your preferred tooling, and then some preferred examples.
132:17 you can get to the point where you could actually just like oneshot uh an app like this. Maybe not
132:20 completely oneshot but like 1.5 shot it. Take uh app creation which previously might have taken
132:25 a very very long time because of all these small little decisions that you and I have
132:28 to make and then get it to a point where it's it's much faster. And not only that, I think
132:32 you'll probably gain a lot more appreciation for software engineering as a whole and then become a
132:36 better developer um whether or not you're working in conjunction with agents. So let's do that next.
132:41 Now, I should know that this isn't going to be a comprehensive software engineer degree
132:46 or anything. In fact, I know there are going to be some software engineers in the comments.
132:50 They're going to look at what I'm talking about and probably laugh. They're going to say, "That's
132:53 not how to actually host. That's not how databases work or whatever the heck." The reality is, you
132:59 don't need to know all of the internals of how all of these different things were put together. These
133:04 are essentially things that were built over the course of the last 50 or 60 years. And nowadays,
133:09 even the most competent developers typically just stand on the shoulders of giants. And so,
133:13 I'm going to give you a very high level overview here. And this high level overview will, like the
133:16 rest of the course, be the 8020 that allow you to dive deep into specific parts if you so want to.
133:22 Um, but you won't necessarily need to hear me yap on for 700 hours about different database
133:26 architectures. Okay, so we're going to start with hosting. To make a long story short, hosting is
133:31 just the technical term for running your web application on a server. works on my machine
133:37 is the scariest thing a developer could say. So, it's important to do this right. You know how a
133:42 few minutes ago when I was developing that app and then pushing it live, there were immediately
133:46 some problems. Well, what a lot of developers will do is they will develop entirely locally and then
133:51 they'll say, "This works fantastic, amazing." And then they'll leave the pushing and the deployment
133:55 and and you know, all the hosting and stuff like that is sort of an afterthought. And then when
133:59 they actually do push it, then there's a bajillion problems and the app doesn't really work. And then
134:03 as you saw there's also a longer feedback loop because now this is live on the internet it's not
134:06 on your machine and that longer feedback loop can make you know that last mile problem where you've
134:10 done 99.9% of the work uh of your app but then that.1% takes like 100 times longer just because
134:15 of the nature of your your prepare preparation or lack thereof. So in order to really get this
134:21 we just need to give a brief highle walkthrough of how communication um on networks tends to work
134:27 or like on apps. Basically on the left hand side here we have a client. And for all intents and
134:32 purposes, let's just say this is um your browser. Okay. Now client is just such a silly name. I
134:38 would say not a lot of people really understand this, but I just replace basically all instances
134:42 of the term client with just your browser for now and everything will make more sense. Now your
134:46 client, okay, it's just your browser. It needs to communicate with a server in order to have
134:52 some sort of back and forth. And so this server, okay, could actually be like your um computer if
135:01 you're developing locally or if you know you're pushing to some, you know, service or whatever,
135:07 it could be something like well maybe Nellifi isn't the right example, but I don't know. Yeah,
135:10 I don't know if you guys ever used Hostinger for instance, not affiliated with them, but um that's
135:14 a good example of one. Or let's just see Hostinger alternatives. Blue Host, if you guys have ever
135:21 developed a WordPress website or Cloudways or Site Ground or Insta. Basically, these are services out
135:28 there that run computers just in the cloud that you can then access in order to like push stuff on
135:34 it. Okay? So, what happens is your client, okay, your browser will communicate with the server,
135:39 which if you're running stuff locally is either just your computer or it's somebody else's
135:43 computer on hosting or site ground or whatever other service. And then it'll send initially some
135:49 very simple and brief requests, okay, for things like um you know site HTML. It'll send uh requests
135:57 for things like uh database data and whatnot. And so your server has the ability to do a lot
136:02 of its own logic and whatnot. And so in general, what clients um are for are they're just for like
136:08 presentation. And then what servers are for is they're more for like the heavy lifting and the
136:12 logic and the validation and stuff like that. That's why server side validation is much more
136:15 important than client side validation. That's why it's a big security risk. The thing is in addition
136:19 to the server, there's like a third piece called your database where we actually store like a
136:24 row or tabular data. And you know, for all intents and purposes, your database is just one big Google
136:29 sheet. There's like an ID column, there's like a date created column, there's like a I don't know
136:34 value column, and then there's uh just a bunch of stuff here. um where basically what your server
136:41 does is it will make a request to this database to receive specific pieces of data that the user
136:47 has requested. So if the user has an ID of 23 foi whatever, okay, and then you know the request is,
136:53 hey, I just want you to grab the value. What it'll do is it'll return 2 3 4 2 3 4 um over and over
136:57 and over and over again. Okay, so that's that's pretty cool. Um the reason why we split these two
137:02 up is just servers are obviously computers. This is obviously just data. Data are not computers,
137:07 although computers can contain data. You could theoretically contain a bunch of information on
137:10 your server, but why would you pay for all that when you could just use like a highly optimized
137:14 service that just stores a bunch of records and then communicates really quickly. So anyway, let's
137:18 say our client is requesting some data. Like if you if you go back to our app, um it's requesting
137:23 that like little dashboard data. Let's see how many orders do we have in the database. What it'll
137:28 do is, you know, we we'll first we'll sign onto our app. We'll initially make that request to the
137:32 server. It'll return a bunch of HTML and um any pre-existing or cache data, okay? And then it'll
137:36 visualize it. And then after, you know, you the user will navigate on the website and you'll say,
137:40 "Hey, you know, I want to, you know, you'll you'll click uh the dashboard button and then
137:44 that'll be like, hey, you know, I want to go grab this data and see how many records I have." So,
137:47 what'll happen is we'll send that request over to the server. The server has a bunch of
137:51 um pre-built logic basically that says, "Hey, when a user requests a specific dashboard data,
137:58 I want you to call the database using this format and then retrieve it." And then we'll say, "Hey,
138:02 you know, we want the dashboard data." It'll do this in a slightly different language,
138:07 typically SQL, although there are no SQL databases as well. And then it'll return, you know, that
138:12 dashboard data. The server will do some additional validation if it needs to, and then it'll just
138:17 return that to the client. And so this is just a loop that goes on over and over and over and over
138:21 and over again. If the client updates something like let's say we create an order, well, it's the
138:24 exact same thing. We'll just send a request to the server. The request will say create order. Server
138:29 will be like, okay, cool. So here's how I create an order. Then it'll take that request and send
138:33 it to the database which will then add a new order to like your orders table. So very very high level
138:38 um overview of how basically these modern web apps work. And I'm going to talk a little bit more
138:42 about like the prevailing frameworks in a second because there are now apps out there kind of like
138:46 this service I'm using right now called Excaladraw which does things both online but also locally.
138:50 And you can really dive deep into that rabbit hole if you want. But um without further ado, what's
138:56 the actual development process look like? Well, for us it's basically we just start local. So when
139:00 we start local, we run both our client and our server on the same computer, right? Our client is
139:04 like our browser and then our server is just like, you know, your your your computer running that
139:08 process. Then we test and verify just like I did a moment ago for my app. And then once we're done,
139:14 we push to what's called a staging server, okay? Which is sort of like an intermediary between
139:19 um having everything on your machine and then have everything accessible to your customers. Once it's
139:23 on a staging server, we then test and verify. And then once we're done testing and verifying,
139:27 then we and only then do we actually push to production, which is like the thing that um
139:30 customers and and users can actually use. And so the process is basically always just like um local
139:37 staging production. And this is not super relevant for our last step, but it'll become more relevant
139:44 when we use things like GitHub repositories and version control because there are changes that
139:49 you can make locally. other people can be working on changes on the staging server and then other
139:53 people can be working on changes even on like the production server. Although ideally you
139:56 don't make live changes because a single live change can like screw up your your whole work
140:00 um like your whole app like you saw earlier. Uh and then you can actually just spread it across
140:04 have multiple people working on multiple things simultaneously. So that in a nutshell is basically
140:08 everything you guys need to know about hosting. Um you do obviously need to pay for hosting for
140:12 most services like you know you're not going to be able to sign up to hosting or or site ground or
140:16 whatever for free. This is basically you renting a computer for the purposes of hosting your
140:21 application on it and then having users interact with it. And obviously every time some user goes
140:25 to a website or whatever and there's a request made to the host, the host consumes a little bit
140:28 of electricity. There's like a little bit of of a cost back there. So they um they arbitrage that
140:33 and then they charge you some big multiple. And there's like a bajillion hosts out there. There's
140:36 like VPS's, virtual private servers. There's like dedicated um computers or dedicated servers you
140:42 could buy. There's like whole computers basically or whole servers that you could buy. Or what they
140:47 do is they take one server and they divide it into like 50 servers and then slowly partition it out.
140:51 There's like so many different ways of doing this that it's not really worth us getting into. But
140:54 suffice to say, this is just like the basic model of um communication. Another thing that's really
140:57 important to understand are databases. Now, for all intents and purposes, like I talked about,
141:01 these are basically just like a Google sheet. If you guys have ever used a Google sheet or
141:04 you ever used Excel or anything like that, the best mental model I found so far is just to
141:08 treat every database that you use like um a Google sheet. So, just like a Google sheet, you'll always
141:13 have like header row, uh, a header row, which is basically just like the titles of every single
141:19 column in your database. So, in this instance, for instance, our table, which I just move my
141:24 big head out of the way, is called sheet one down here. Okay? And sheet one, okay, is just one of
141:31 many possible tables in our database. We can make 100 more tables if we wanted to, but they're all
141:35 going to be divided into like sheet one, sheet two, sheet three, or whatever the heck we title
141:38 them. Now inside of sheet one um we have uh three columns here. The first column has a header name
141:44 or a key of id. The second has a header name or a key of date underscore created and then the third
141:49 has a a header name or a key name of value. Now underneath this sort of initial row which just
141:56 defines the names of all of the various fields. Um we then have the values themselves. And so this is
142:01 a database for instance that contains a one record or one row. If I duplicated this a bunch and then
142:08 I don't know wrote some other IDs here because this is going to be important. You can see now we
142:12 have a database um with one table called sheet one that now consists of four rows. Okay, the thing
142:18 is depending on the type of database that you're using. Okay, you need what's called a primary key.
142:24 And a primary key is just something that's unique, one column that is basically always unique from
142:29 row to row that basically defines that row or that record as like being super unique and not
142:34 existing anywhere else. And so for the purposes of this database, the primary key is going to be the
142:41 ID because the ID is always going to be different between each record. If you have two records with
142:46 the same ID, obviously there's a conflict. If you think about it logically, the reason why we need
142:49 it structured in this way is because if we have instructions in our server and the instructions
142:53 are to pull a specific record from a database and it's like, hey, I want you to grab the record with
142:58 the ID 23FI23F2 and it turns out there's like 10 records like that. You'll return 10 records and
143:05 how are you supposed to visualize 10 records? Like that's going to, you know, it's going to screw up
143:07 whatever your logic is unless you specifically handle for that. And so these databases for
143:12 the most part, most people that vibe code apps suffered using the SQL database with um separate
143:16 primary keys are typically organized in that way where you have one sort of like starred column.
143:21 And so I'm just going to make this one the starred column. It's the yellow one. And then these here
143:24 can be the exact same. Like you could technically have 100 records all created in the same day,
143:27 but since they have different IDs, they're all different records, right? Same thing with the
143:30 value. Okay? So just like in a Google sheet or an Excel file, you can actually like filter things
143:35 out. Um you can do the same thing inside of a database. So if I go back to our little example
143:39 here and then um I add a filter which I can do on sheets really easily just using a little hotkey.
143:44 You can also just go to data and then you could click on create a filter if you wanted to follow
143:49 along this demonstration. What you can do is if you click on this little filter button you
143:53 can see that you can now just filter specific records. Like I could for instance only grab
143:57 um you know this record here 23FI. Okay. And if I did so it would remove all of the additional
144:02 records here and then I'd only be looking at this data. And so every time that a server makes a
144:06 request to a database, that's basically what it's doing under the hood, it's just doing this in like
144:09 a fully automated fashion. Likewise, I can filter based off of fields that are not my primary key.
144:13 So maybe in date created, what I wanted to do is I wanted to grab all records that have 2025-10-3.
144:19 So as you can see here, now I'm grabbing multiple records, okay? But each of these have different
144:23 primary keys. And this is just a way that I could filter stuff. It's just like using a search bar,
144:26 right? You can do the same thing for value, do the same thing for whatever the heck else you want,
144:30 um, you know, in your database. So basically every time that you send a request from you know
144:34 your client your browser by clicking a button you send that request to the server the server
144:38 interprets it. What it's doing is it's sending another request to a database which um you know
144:42 is basically just acting like a big Google Sheets filter. Now the cool thing is there's two major
144:47 types of databases right now. The first is called SQLbased. So SQLbased is divided into a bunch of
144:53 different popular versions. I mean really there's like a thousand but three most popular ones right
144:56 now are my SQL postgrql which is probably the most popular one and then SQLite and then you
145:01 also have what are called NoSQL databases like MongoDB and Cassandra. How I've always worked with
145:06 the differences is SQLbased databases basically fix the column headers and so it's always going
145:13 to be the same column headers for all the data and all of the records that go into a database.
145:18 And so just like here we have those three column headers ID, date created and value. Basically,
145:22 every single record in this database will always have an ID because it's the primary key and can
145:27 optionally have either a date created or a value or it could have both. And so, um, you know, for
145:32 instance, you might get something that looks like this with a date created and then no value. And
145:37 that is what's called a valid record. Likewise, you can get something that looks like this with no
145:42 uh, you know, obviously the IDs are going to be different. No date created, no value. And
145:45 you can also have something that looks like this. Okay? And you know as long as you have a primary
145:51 key which denotes that this is a separate record um every other field is optional but it has to
145:56 stick to this structure. Now no SQL databases are a little bit different in NoSQL I'm just going to
146:02 create a new sheet here. Basically what we have is rather than having just like one header row up
146:07 at the very top I want you to pretend that every single item in your database has its own header
146:13 row. And so the first record here will have ID, date created and values. So let's say the ID is
146:19 this, date created is this, and then the value is this. Okay? Or I don't know, let's just make it a
146:25 little bit easier. Let's just call this uh we have a record here called first name. Probably makes
146:30 more sense. And then this one's Nick. So um you know what we have here is we have one record with
146:35 an ID, a date created, and a first name. Well, for the next record, instead of just like sticking to
146:40 this format, you could have whatever the heck you wanted. So I'm actually just going to paste this
146:44 down here. And then I'll say this record actually has um a last name instead. It has a date created
146:56 column and then it also has a date modified column. Maybe this date modified as 29th. If I
147:03 added another record here, okay, maybe what I have here now is I have a full name. This one's Nick
147:11 Sarif. Then I also have my little date created a little bit over to the right. and maybe there's
147:15 no date modified. And so basically what occurs in a NoSQL database is every single record has its
147:22 own data structure rather than everything being 100% fixed and looking the exact same like we
147:29 had with our previous uh SQL database. You know, every record will have an ID. Then it's optional
147:34 whether they have date created or value. But it's not like they could have another, you know,
147:37 it's not like this row could have another value called uh first name called Nick, right? Unless
147:42 we explicitly define that up here as a value or a header that exists on all. Okay. Whereas
147:48 this would be empty empty empty empty empty empty empty and then this would be nick. Okay. It's not
147:52 like we can just add additional um features or or types of data. In a NoSQL database you have
147:58 total freedom and flexibility. And it's a lot more like like a Google Drive folder where you're just
148:03 storing a bunch of different documents and every single document could look a little bit different.
148:07 Now, obviously for our purposes, we want a simple way to like call a database and then retrieve all
148:12 records that have a first name Nick Sariah or that have an ID of of something. Um, you know, we're
148:16 going to use SQL for the most part. But there are some instances where NoSQL makes more sense. Um,
148:21 and if you want to look more into that, just look for the difference between like relational and a
148:24 non-reational databases. Um, and then maybe you could have your agent tell you. Next,
148:28 I want to chat languages and frameworks for people that might not be super familiar with them. So
148:34 there are three basic languages used these days in modern SAS app um sort of development engineering
148:41 and I'm going to draw them as little bubbles and I'll show you how they all interact. The first
148:45 is probably the oldest which is hypertext markup language. The next I just copy this is a little
148:53 bit newer and it basically took the internet from just a bunch of ugly static web pages to pretty
148:58 dynamic and interesting web pages CSS. And then the third is how we got interactivity in the web,
149:05 which is through JavaScript. Now, I'm not going to give you guys a big historical lesson on each
149:09 of these because to be honest, I mean, I just be googling this stuff anyway. Um, but suffice
149:13 to say, HTML is actually like basically the only thing that you need in order to run a website. CSS
149:21 is sort of the design layer that makes things really pretty. And then JavaScript is just
149:25 what allows you to build interactivity into pages like you clicking a button and then a new element
149:29 appearing or something. And so to show you guys this HTML side, if you head over to info.sern.ch,
149:35 you can actually see the very first website ever made. And that website is called the worldwide
149:40 web. This is literally describing the worldwide web. You know how all websites or many websites
149:47 have www preended? That stands for worldwide web, which is a framework that people put together god
149:52 knows how long ago now. probably at least 40 years ago. And so basically this explains how
149:56 the internet works. Okay. Now obviously you don't need to have gone to this website to know how the
150:01 internet works more uh fundamentally speaking. I think every kid just inherently gets it when
150:05 they are given their first iPad with Coco Melon on it. U no jokes aside uh the worldwide web is
150:11 is a website that's entirely built in HTML. And you can see because the file ending up here is
150:14 HTML. If I open this up you'll see the actual code of the website down here. And it's very simple.
150:19 There's a body, there's a header, there's an H1, which stands for worldwide web, an AT, which is a
150:25 bunch of links, and then P tags and and stuff like that. Now, worth noting that this is a website
150:30 with no CSS, which is sort of the next level up. Now, CSS is how you change the style of the page.
150:36 It's how you make things bigger or smaller or or sexier or whatever. So, if I go style here,
150:43 I can actually change the font size to like 300 pixels and I can make that bigger. This HTML is
150:51 just that core fundamental um kind of structure, the scaffold of the page. This style is now CSS
150:57 and it's where I'm like applying some additional information to change the size. I could change
151:01 the color and I could do so on and so forth. I could I could change things quite a bit. Now,
151:04 there is that one final piece which is JavaScript. And JavaScript nowadays is done mostly through the
151:10 console. Inside of the console, you can actually run um JS. So what I could do is I could go
151:15 document query selector and then I could look for all all H1's elements and then what I could
151:21 do actually remove this from the page um just by clicking or writing document.query selector H1-E
151:28 and this is an example of that interactivity that I was talking about. Basically with JavaScript
151:32 what you can do is you can I'm realizing that my head's in the way here so you can't see that
151:36 most recent function. Um basically what JavaScript allows you to do is allows you to select specific
151:41 elements on the page and do whatever you want with them. You can make them bigger, you can make them
151:44 smaller, you can apply styles, you can create new HTML. I mean, there's like a bajillion different
151:48 things you can do. Okay, so those are the three programming languages. And hopefully we're all
151:51 on the same uh page about how these two or three interact with each other. The thing is, obviously,
151:57 if you design a website or a web app using HTML, CSS, and JavaScript, there's like a million
152:03 different ways you could do so, right? You could write whatever website you want, apply whatever
152:06 styling you want, and then obviously apply whatever interactivity you want, and that's great.
152:10 But the internet thrives off standardization, which is where things are done in a repeatable
152:15 and sort of consistent way. Because of this, the more standardized the internet tends to be,
152:21 the better solutions that people can build on top of pre-existing solutions. And that's really the
152:25 whole idea of programming languages in the first place. So in addition to this idea of you know
152:30 languages as um standardization you also now have this concept of frameworks as standardization. And
152:41 so frameworks are a level of abstraction that are built on top of languages. And what we do
152:46 is we actually just take these three sort of Lego blocks and we just construct them in a specific
152:51 way essentially. Okay. And right now there are a bunch of different frameworks out there. The most
152:57 popular ones I would say are next.js which is the framework that we just used to define and build
153:05 our current app. And you can see that that include a lot of that included a lot of opinionated
153:10 um framework based stuff for like the folder structure and components and hooks. These are all
153:15 things that are basically a handme-down directly from our framework. You also have um vit right
153:21 now is super popular and you'll see a lot of apps created with vit and then on the other side you
153:26 also have view or really like nux.js and there are varying levels of abstraction here like nux.js is
153:32 actually an it's like a second framework built on top of another framework called uh react which is
153:37 kind of funny. Um nux.js is built on top of view. Uh you know there are a lot of like dependencies
153:43 and stuff and if you guys remember earlier I said we stand on the shoulders of giants. really do uh
153:47 because everything nowadays is built off of something somebody else built which was built
153:50 off something somebody else built all the way down to where we were programming computers
153:53 with little ones and zeros on pieces of tape. And so in addition to you know our chosen tool and
153:58 this is the tool I'm going to be using for the most part throughout this course. NextJS being
154:03 essentially the way that we coral these three programming languages together. Nex.js JS is also
154:09 an opinionated framework that um you know helps us organize things like hosting, helps us organize
154:16 things like how to do you know database calls and whatnot in a standardized way. You guys remember
154:22 earlier we talked about middleware authentication middleware uh has a standardized interface for
154:26 authentication middleware is a standardized way to put together routes which are just the names
154:31 of like um website endings. So excalagger.com/ I don't know settings that's a settings route for
154:36 instance and so on and so forth and what's really cool is because a lot of people have used these
154:41 frameworks before you know like NexJS isn't Neo was developed at least half a decade ago if not
154:45 more I built tons of projects with it before we had the luxury of agents to do that for us because
154:50 of all this we had a lot of pre-existing projects out there on the internet that were built with
154:53 this and these were all used in the training sets of these large language models like you know opus
154:58 gemini and so on and so forth which means make a long story short If you use a framework, you
155:03 usually get significantly higher quality results. Now, frameworks obviously have some baggage as
155:07 well. The more opinionated things you put into uh you know a design system or whatnot, obviously the
155:14 more lag that you can have, the bigger the files can be and and so on and so forth. But for the
155:19 most part, these are a good balance of like speed, stability, reliability, and then also
155:23 security. You know, because these frameworks have existed for a while, people have put together some
155:27 pretty simple and easy ways to economize um our security and our ability to build apps. Okay. So,
155:32 am I saying that you have to like go and learn every single thing in HTML? No. CSS? No.
155:36 JavaScript? No. Um, do you have to read through all the NexJS docs? No. Although they are they
155:40 are pretty cool if you wanted to. None of these things will necessarily make you like a better
155:44 vibe coder. But I think it's important to at least be able to like look at the Lego blocks and see
155:48 how they fit together because if you don't, then you're a lot more liable to produce what I think
155:52 a lot of people nowadays are terming as sloop out there on the internet, which are like simple
155:54 vibecoded apps that aren't really well thought out and then interact with the rest of the internet in
155:59 pretty stupid ways. The last thing I want to talk about is version control. And to make a long story
156:05 short, version control just answers the question, how do I store successive updates of files on a
156:13 server as efficiently as humanly possible? Let me give you a brief little example. I'm sure you know
156:18 back in high school or college or whatever, those of us that have gone there in the last few years,
156:23 you've run into situations where, you know, you're tasked with writing an essay. And so,
156:28 you know, you write your essay probably really late in the middle of the night with a bunch
156:31 of Cheetos beside you. At least that's how I used to do it. And then, um, you save it as,
156:35 I don't know, essay docx, let's say. You know, it's like a it's like a Google doc or something
156:39 like that file. And you do it locally in your computer, maybe Microsoft Word, okay? And then,
156:44 um, the next day, you know, you wake up and then you give it to your friend, and your friend gives
156:49 you some feedback or something like that. Okay? So what they do is they they download the file
156:53 and then they give it back to you and then it's called essay with feedback.docex. So what you do
157:00 is you take that file but not wanting to lose the previous two files what you do is when you make
157:05 your updates to it okay you don't save it as essay with feedback you call it essay 2.d dox and then
157:12 the cycle just repeats itself three or four times then you have essay 3.d dox you have essay 4.x doc
157:20 x and so on and so on and so forth until you have essay final superfal important docx. Okay. And
157:29 before you know it, you know, your whole downloads folder is a mess. I'm sure we've all probably had
157:33 situations like this before. Um I know, god forbid, I I used to have situations like this
157:37 all the time. Now, that's for writing things like essays. I want you to imagine instead of essays,
157:43 what you're doing is you're working on an app like we're doing. You'll have app one dot whatever,
157:48 app two dot whatever, app three super important final whatever. Obviously, these things can get
157:53 out of control really quickly. What compounds the issue is this idea of needing to share files
157:57 because this super janky ass method, this could work if it's just you and you understand how you
158:01 name your files and stuff. You could build like a naming convention, right? But what if you want to
158:04 share this with like 20 other people and 20 people all simultaneously need to be able to work on the
158:08 file that is the most updated without causing conflicts and stuff like that and so on and so
158:12 forth. That's really the whole idea behind what initiated version control. And so what we do is
158:17 we basically have again standing on the shoulders of giants um built systems out there that store
158:24 not only the file itself but store the changes between files and then just let you access them
158:30 by you know calling a little URL or something and then pulling the file as well as a list of all the
158:35 changes um that have historically occurred. So that at any point in time, you know, you could
158:40 download, let's say, this original file, but then you could jump over here if you wanted to,
158:43 jump over here if you wanted to, jump over here if you wanted to, jump over here if you wanted to,
158:46 and so on and so forth, all without just needing to like pollute your, you know, file system and
158:50 stuff like that. What's more, at any point you could also branch out and make additional changes
158:54 here, however much you want, called, I don't know, new essay. And then you could share that new essay
159:03 uh with other people. Okay? Or what you could do is you could make the changes here and then you
159:08 could actually take these changes and then merge them with another pre-existing file to get some,
159:13 you know, new better essay hypothetically. Um, you could do that with apps, you could do that with
159:17 essays, you could do that with everything. People use version control to literally do
159:21 everything nowadays, research papers and so on and so forth included. So the major place where
159:26 most version control happens now is on GitHub. And what we do is we've taken this concept of like a
159:32 folder or a workspace and we've standardized it into one called a repository. And so this idea
159:38 of a GitHub repository is very popular. You go into github.com. This is what the website looks
159:43 like. Okay. And you can see on the left hand side I'm signed in here. I have a bunch of different
159:49 um repositories. I didn't even realize, but I have a bunch of people here that are like
159:51 starring my repos and stuff. That's hilarious. Um I have a bunch of different repositories
159:55 here like worklog make money with make gyro app.1c.copy.com copy.com, proposal generator,
160:00 and so on and so forth. And these are all basically different projects that I've built. Now,
160:03 what's cool is if I click on any one of these, okay, you can actually see every change that I
160:08 have made to this over the course of god knows how long. This is basically over the course of I
160:13 don't know 346 different changes. If I click this button, the wildest thing, so I can actually go
160:18 through and I can see literally every change I've ever made to this thing. And at any point in time,
160:23 okay, I can actually open up the details and then the code itself to adjust what's going on. I could
160:30 uh restart my, you know, project from here. I I mean, I could do anything. I could share this with
160:35 other people really easily. Um, and so on and so forth. So, I say this not because I want this to
160:40 be a comprehensive guide to GitHub. Obviously, it isn't. I just like gave you guys a very high
160:43 level overview. Um, but in a nutshell, all this is is just a way to store and and and save files.
160:48 And so whereas with our last couple of projects with our portfolio site and then the um app that
160:53 we just built, I wasn't using GitHub for any of it, from now on, what we're going to do is we're
160:57 actually going to take our big file structure that we're developing locally and we're going
161:01 to constantly push it to GitHub so that we both have like a saved version over there if anything
161:05 locally occurs, but also we have the ability to um share it with others. And then services that
161:10 do deployment nowadays like Netlife, Versel, and and other platforms out there, they can often just
161:15 pull directly from the GitHub. So I don't have to like drag my folder in. I could just say, "Hey,
161:19 here's my GitHub repo." And then it'll just do all the math and stuff for me. And then I don't even
161:23 have to like rebuild it on Netlefi. What I could do is I could just push it to this repo, make a
161:27 couple of changes, and then Netifi will have like a little hook that automatically rebuilds
161:30 the site every time a change occurs. And this is how you get like different pipelines set up with
161:34 like production, staging, local, and so on and so forth. You can also create different branches
161:38 branches. I guess I have one here called chest day workout. That's pretty funny. Must have crushed
161:42 that chest day. Um, and then just have agents manage like everything to do with uh with whatever
161:47 project you have. So, for instance, this is like a little work log that I set up that basically just
161:51 like a list of things that I've done. I use it to track my own my own work. And uh I developed this
161:55 in just a few minutes with uh with claude code I think like two months ago essentially. The
162:01 last thing I'm going to mention here is everybody gets a GitHub profile. And so there are a lot of
162:04 people out there that are have very popular GitHub profiles. This is usually where most open source
162:08 lives. So, you know, if you develop a really cool new idea or new framework or something, you make a
162:13 GitHub repository and then you share it with other people and then other people can also make changes
162:16 and then improve it over time. Um, that's what a bunch of really popular repos tend to do. If
162:21 you guys have checked out like the open claw one and and stuff like that, that's where they were
162:24 getting um most of this this from. And then with agents, what you could do is you could actually
162:27 just have parallel instances of like 10,000 operating in the background, constantly scanning
162:32 the workspace and then making micro adjustments and edits in a very interpretable and accountable
162:36 way. So the future of software development is basically that decentralized GitHub repo pushing
162:40 and pulling and stuff. Okay, cool. I think we've now done enough of like the traditional software
162:44 engineering concepts for you guys to know a lot more about how to build these things efficiently.
162:48 Um, what I want to do now is just talk really briefly about a couple of the different ways you
162:51 could use agents to streamline your work. I know we touched on this briefly with the repo stuff a
162:55 second ago, but I just want to zoom out a bit and then just look at anti-gravity and look at some of
162:59 the the potential and the functionality there in. Okay, so if I just go back to anti-gravity here,
163:03 you know, I still have that old site set up. Um, I should be able to clear this just by going to
163:07 new. Um, one of the simplest and easiest ways to multiply your ability to work on a specific repo,
163:15 which is just what I'm going to call our workspace or file folders from now on, is basically just
163:20 running multiple different separate functions simultaneously. And so, you know, I could say,
163:26 hey, do XYZ, and then I could just wait until this whole thing is finished. And then I could give it
163:31 some more instructions. Hey, thanks. Let's now do ABC. Or what I could do is I could make use of the
163:38 ability to start new conversations. And I could actually run multiple of these um simultaneously.
163:47 So I think we're all familiar with just using the little agent tab on the right hand side. But in
163:52 order to parallelize your work and then work a lot faster, what we can do is we can zoom out of
163:56 a specific workspace and then actually just look at like 3 4 5 10 100 agents working simultaneously
164:01 for us and then just orchestrate their actions. This can sound pretty bonkers if it's the first
164:05 time you've done something like this, but this sort of functionality is actually built into
164:09 anti-gravity and uh it's also built into things like cloud code and and stuff like that as well.
164:13 The way you do so is with this agent manager in the top right hand corner. So if I click the agent
164:17 manager, what we've done now is we've zoomed out of a particular workspace. We actually have all
164:21 of our workspaces here listed on the lefth hand side. And you can actually see every conversation
164:26 you've ever had inside of each workspace as well, which is really handy. So, this one's improving
164:30 dashboard UX. This one's listing directories and stuff like that. Here's a search I just said a
164:34 moment ago, or I'm pretty sure I just said like do ABC or something like that cuz I wanted to like
164:38 have a bunch of these that I could quickly jump through. You can see in this case just ask me,
164:41 hey, what the heck is ABC? What are you crazy? And so on and so forth. This is some other thing that
164:46 I've developed here. This is some other thing that I've developed. And so on and so forth.
164:49 So, I mean, like, you know, this is kind of cool, right? You basically can just go
164:51 top to bottom and then see at a bird's eye view a bunch of different conversations that you've had
164:55 with different agents. And you can do this across workspaces. You can start new conversations across
164:58 workspaces. You can jump into a specific workspace using the editor, right? Um, and so on. The really
165:04 cool thing though is if you go to this inbox in the top lefthand corner, what you can see is you
165:09 basically get a list of all of the messages that AI is sending you. And the reason why this is so
165:14 valuable and so cool is because if you make use of the pending feature, which is basically where you
165:21 don't let AI do something unless you've cleared it, what you can do is you could use this little
165:26 pending filter and then just have a giant list of things that like 20 different agents are working
165:31 on simultaneously and then they're just like serving you um you know the results and asking
165:35 you, hey, do you want me to do X, Y, and Z? Okay, so let me show you a really quick and and simple
165:39 example. So earlier I had this website builder repo, right? If I just open the editor here,
165:44 I had this big Gemini.MD where I was basically showing you guys how to create a website and
165:49 then I pumped through like two or three of them simultaneously. And I hid this from you at the
165:53 time because I didn't want you to obviously get super overwhelmed. But if you open the agent
165:57 manager, okay, you can see that you can now start new conversations in what's called a playground,
166:02 which is an independent workspace, perfect for quick prototypes or following curiosity. Then you
166:06 actually just paste in this multiple times. So you could start a conversation by going in, paste this
166:13 in, start another conversation by going in, paste this in, and start another conversation by going
166:18 in, paste it in. And now in the playground side of things, okay, you now have multiple conversations
166:23 that are occurring where it'll basically just ask you a bunch of information. I'm just going to say,
166:28 um, choose all of this yourself, high-end SAS, for a demo I'm making. You can just paste this in.
166:38 You could paste this in. You could paste this in. And then you could paste this in. And what I have
166:44 now, okay, is I have multiple agents that are all operating simultaneously and independently for me.
166:51 This first one here is called cinematic landing page build. The second one here is called building
166:54 cinematic landing pages. And then you guys can't see these other two, but it's cinematic landing
166:57 and cinematic landing. And basically what they're going to do is presumably they're going to create
167:01 different folders for each of these and then build all of these websites simultaneously in parallel.
167:07 Right now what I have think about it is I've made one command up here and it's split rather
167:13 I've made four different commands up here but basically what I've done is I've split and now
167:16 we have these agents all running simultaneously and inside of this playground I have the ability
167:21 to like get a highle overview what of what um they're all doing just by mousing through each
167:26 okay and you know sometimes you're either going to run into token limits or there's going to be some
167:31 issue so agent terminated due to error here when this sort of thing occurs you can reply and you
167:36 can also just use this agent conversation for it to show you more or less like what it's currently
167:40 working on. So, you know, if I go to inbox here a moment ago, it basically said, "Hey, like what do
167:44 you want me to do?" That that that was a message that the agent sent to me asking me for approval,
167:48 right? I can actually just see all these things at a very high level overview just by constantly
167:52 being on this page. And then essentially all I'm doing is instead of like me being responsible for
167:57 shephering one agent simultaneously, sorry, one agent through a process, I can shepherd multiple
168:01 simultaneously. And this is the difference between somebody that's like building one project and then
168:05 somebody that's orchestrating multiple projects. You do run into some issues with like context
168:09 switching, which is a productivity term that basically applies to when you're trying to do
168:12 multiple things simultaneously or a little bit less efficient at um every one individual one,
168:17 but it's sort of like monitoring like three or four different CCTV uh uh pieces of footage if
168:22 you're like a security guard or something in a mall. You're basically just zooming out. You're
168:25 watching three or four of these things and you're stepping in anytime that a particular
168:29 person needs you. Alternatively, it could be like you're a manager at some big office with a bunch
168:34 of cubicles that you're just walking up and down the halls. When somebody needs you, they're like,
168:37 "Hey, you know, Nick, can you help me with X, Y, and Z?" And so, in this way, you're capable of
168:40 orchestrating significantly more total output or work than you would be able to do yourself. So,
168:45 it's really worth using hotkeys um if you wanted to start building things in this way. And
168:50 uh generally speaking, believe it or not, instead of just building one app, I will usually build two
168:54 or three apps simultaneously now with something like the agent manager and an inbox. and then
168:58 I'll just like have them all run in parallel. Um, the reason why is because then that way I
169:02 could build multiple versions and then I can just pick the version I like the best. Once I
169:05 pick the version I like the best, I drop the other ones and then I just proceed with that one. Um,
169:08 but yeah, hot keys are pretty important. So you can find those just by mousing over each of these
169:12 buttons. So inbox is command I for instance, uh, if you scroll down to playground here,
169:17 you can create a new instance just by holding controlN. And so a lot of the time I'm just
169:21 jumping between new conversations and then my inbox over and over and over and over again.
169:25 Um, you can also jump back to that editor like I talked about earlier just by going command E. This
169:29 will jump you into the particular folder where the conversation and kind of work is happening.
169:32 So this one's called glowing cosmos for instance. At any point in time if you're operating inside
169:36 of this playground, you also have the ability to um move this into a specific folder. And so
169:40 this is occurring right now in like a temporary folder that uh Gemini and anti-gravity just puts
169:45 together anytime you do this sort of thing. But you can also just click this button and
169:48 then you can select a destination folder for all the files in your project. So I could, you know,
169:53 use the playground to sketch out three or four different ones and then when I find one that I
169:58 really like, I could then use the um create a new folder thing to like actually go in add a folder
170:02 and then just work in like a dedicated workspace. They also have a feature called follow along with
170:06 agent in the top rightand corner. So if you follow along with agent um basically it'll
170:10 pull you back in to what the agent is doing at every step and then allow you to see the various
170:14 um you know pieces of work that that agent it's worth keeping this page pretty clean. So, I'm just
170:19 going to proceed with whatever the heck it asked me for. And then over here, now I basically have
170:23 these two main threads that I'm running. You can see the same thing's occurring back here and then
170:29 also back here. And although kind of per unit, it'll still take the same amount of time to get a
170:34 website out because, you know, this is operating at the speed of um whatever Gemini 3.1 Pro is,
170:39 if you think about it, I'm technically doing four times the amount of work um simultaneously across
170:44 all four. I don't usually recommend having more than two or three of these operating. I
170:49 just wanted to show you guys how cool it could be if you have four. I actually have five now
170:52 cuz I'm proceeding with some um agency operation thing I did a while back. Uh just because I find
170:57 like your attention gets pulled away a little too much. But um yeah, you can see here in the
171:00 top rightand corner because I'm following this anytime it'll make a substantial major update. I
171:03 can actually see the code that it's working with and so on and so forth. I usually don't actually
171:07 click that though. I just go to my inbox and then I seem you know do you need anything from me? if
171:11 there's any specific feature or whatever that they want, then I can I can jump right in. So,
171:15 let me run this for a couple more minutes, get a bunch of websites, and I'll just show you
171:17 what they all look like. Okay. And our landing pages are now starting to um be finished. So,
171:22 we could actually access the Vit server. This one's using a different framework called Vit that
171:26 I covered earlier just by pasting this in. You can see we now have one of the websites. Now, I
171:31 should note that this looks pretty similar to the 1se secondond copy website I had set up because
171:35 uh I think I just asked it to build something that was like very very similar visually speaking. So,
171:38 we had that little heartbeat. we have this little thing, but you know, I'm like trying to build
171:41 it with a particular template, right? So, I'm just going to instantiate a bunch of versions
171:45 of this template, and if I like them, then I'll go with that. This second one here is done. Um,
171:48 because I didn't specifically say, "Hey, I want you to run the server and then open it." You know,
171:51 this one's asking me to do this terminal command, npm rundev. Um, so I'm just going to have it do
171:56 it by saying run it and then it'll open it for me and then I can take a peek. Here it
171:59 is. Let's copy this over. Paste this in. Cool. And now we have another one called Aether Core,
172:04 which is very clean. I really like this one. Damn, that's really, really sexy. You know, there are
172:09 some issues here with some of the fonts and stuff, but hopefully you guys see like I was capable of
172:13 generating four of these simultaneously. This one here is still under development. As you can see,
172:17 there's a hero section and it's scrolled down, but it is running live on a server and it does have
172:20 that cool little bar up top. And this one here had probably my perfect instantiation or my favorite
172:25 of like this slow scrolling card like that to me looks really sweet. Um, it's just rerunning it
172:29 because it's making some additional changes, but yeah, pretty cool, huh? So, you can actually build
172:33 multiple apps simultaneously. And in this case, you know, I gave it some pretty static resources.
172:37 And I was like, "Hey, I want you to use like this kind of noise layer in the background and
172:39 stuff like that." You could also just have all of them be different. And the way you do that
172:42 is you just provide like a prompt that has some inherent randomization. Basically says, "Hey,
172:47 I want you to randomly select like, I don't know, a background from this online background service."
172:51 And then it'll use different backgrounds. Hey, I want you to automatically select a different type
172:54 of style using this thing. You know, instead of high-end SAS, I just want you to come up with a
172:58 different one every single time. And then it'll come up with like a 100. So yeah, in this way
173:01 I've I've uh successfully built something like 15 websites simultaneously at the same time. I
173:06 found like the top two or three that I like. I've proceeded with those. I filtered out the ones that
173:10 I didn't and then I've had like a really really high quality product. And I've done all that stuff
173:13 in like 10 maybe 15 minutes or so. Um obviously be careful with token usage here because it's always
173:20 going to be a trade-off between the time it takes to build something and the total cost on your end.
173:24 This is just a pretty straightforward money for time trade, but running multiple agents in this
173:28 way um simultaneously can be pretty cool. Okay, now that you guys know more or less
173:31 everything you need to know about both modern software development, um, hosting, databases,
173:35 frameworks, and all that stuff, plus how to use agents to pour fuel onto the fire, let's build
173:40 product number three, which is a lead generation SAS app that scrapes, enriches, and even queue up
173:45 um, the sending of fully automated emails. This is very similar to a structure that I use in
173:48 production myself in my own business, Leftclick. We work with multi-billion dollar portfolio
173:52 companies and essentially connect to the outbound systems on a team to help them send emails,
173:56 scrape uh contact details, and then personalize outreach at scale without needing like a million
174:01 bajillion hires in order to do all that for us. So this time, instead of just diving right into
174:07 the app development via prompt, I wanted to take a few moments to sketch out what an actual app might
174:11 look like. And there are variety of different names for this sort of thing. Um, in my case,
174:15 I'm just going to call it planning. You could call it some form of like UX or site design
174:19 or navigation design or whatnot. In short, um I know for sure this app is going to need a landing
174:25 page. So here I just said landing page sexy on it. We're going to want some navbar, some main
174:31 value proposition, a social proof section, some how it works section, some case studies, a CTA,
174:37 and then a footer. This is pretty standard, right? It's basically the exact same thing that we did
174:41 with Content Orb. After that, we're going to want some sort of login and/or signup page. And so this
174:46 is the O form in Superbase where you enter your email, enter your password, and then it signs you
174:50 up. Now, what I imagine will probably happen after is once you're signed in, um, we'll need some form
174:57 of configuration page cuz I want this app to be able to be usable by people like you, people that,
175:02 um, you know, I don't want to have to necessarily build for. Instead, I want there to be a space for
175:05 your instantly API key, your anthropic API key, your OpenAI API key. Uh, I want you to be able to
175:11 configure the prompts that are being used by the AIS to do personalization as well as have defaults
175:15 and stuff like that. And basically, I just want that to be like your onboarding. It's like, hey,
175:18 do you want to get started with the scraping? Just enter your API keys here. And there are a
175:22 couple of other API keys that I'm going to need, actually. But, um, in addition to that, I also
175:26 want like brief little one-click guides to show people how to do all of those things. And then
175:30 finally, I want the actual scraping page itself, which is just going to be a form where you put in
175:34 some basic parameters. And the way this is going to work, for those of you guys that don't know,
175:37 there's a scraping service out there called Appify. And we're basically just going to wrap
175:39 around Appify. If we can't find enough leads, then we're going to scrape Google Maps. And then we're
175:45 basically going to combine both of these into some sort of like enrichment personalization flow. Um,
175:50 and assuming that, you know, we've enriched and personalized, which, you know, may not necessarily
175:54 mean something to you guys if you guys aren't in the marketing space, but I'll run you guys through
175:57 it all um throughout this demo, then you'll just get all the leads that you just scraped in a
176:01 simple CSV with some additional column that has AI based personalization. So, we're going to need the
176:07 first name and email at minimum. And then I think the last thing to talk about is that orders page
176:10 or just going to be like a like a history page where you could see all the orders that you've uh
176:14 scraped and sent before. And then maybe I'll also do plus specific order pages for each that have
176:20 like I don't know a bunch of descriptions on them. Okay. So, you know, I think uh probably a real UX
176:25 designer would crucify me uh in terms of the ways that I've laid all this stuff out, but you know,
176:29 seems to work pretty reasonable for me. Um, what I do next is I basically just take a screenshot
176:33 of this and then I always have this on hand cuz you know I want to like know what my app's
176:38 going to look like. Then I go into anti-gravity and then what I do is I um say something like,
176:41 "Hey, I'm making an app that helps people scrape leads. Turn this into a brief description of an
176:45 app that includes all the important components and I actually just screenshot and I send it to
176:48 them." This is back when I had it like vertical. I've since made it horizontal. Then scrolling down
176:53 a little bit, you can see we've now changed it into the description. Okay. And then over
176:56 here we have the updated description with just a bunch of, you know, plain text language here. So,
177:01 we're probably going to need more. I mean, like, it's not that big of a deal. Then I made a couple
177:05 of changes and I said, "Hey, here's some scrapers that I want you to wrap around." Okay. And now my
177:09 claw code instance has generated this prompt. So, that's good for now. What I want to do next
177:13 is open a new folder cuz I've copied this and I want to call this lead scraping SAS. I'm going
177:18 to create and I'm going to open. Now, in our anti-gravity instance, we have a plain folder
177:22 here, lead scraping SAS. And so what I want to do next is two things. First, I'm going to need to
177:29 feed in that prompt. And second, I want to feed in um a description, sorry, an example that we
177:35 could use to basically inspire Gemini. Now, I went on dribble and I found something that looks like
177:39 this. This looks pretty reasonable to me. Um keep in mind like the design and stuff like that is
177:43 pretty sleek, but obviously they have a lot more components here. Data transfer. I mean, I don't
177:47 really know why I would ever need a data transfer component, but you know, there's like a bunch of
177:50 buttons here and stuff. And I think we could make this work. Um, you know, our graph may not look as
177:55 nice, although I think we could actually make it look as nice if we really wanted to. But for now,
177:59 I'm just going to copy this image. I'm going to go back over here. I'm gonna start by pasting that
178:02 in. Okay. So, we're going to start just by pasting in um this image. It looks like we're copying
178:09 this, but it's not actually making it all the way to our dashboard. It's kind of annoying. So,
178:11 I think I'm going to have to take a screenshot of the actual app itself. I think sometimes
178:14 Dribble does like anti-creenshot protection or something. Keep in mind that we're not stealing
178:19 this or anything. We're just going to use this as like inspiration. That's all. go back here, paste
178:22 that in. Then I'm going to say um I'm going to head over to Google, say cold email lead scraping,
178:29 and I'm just going to find some links here. Basically, I just want like a brief description
178:32 of what cold email lead scraping is. So, let me see if maybe instantly has some information on
178:35 their site. Um, this is like a full endto-end cold email sending platform. Uh, probably not what I
178:44 want. I just want like some lead scraping. This looks pretty good. I like this. So,
178:49 I'm just going to copy this. I'm going to head back here. I'm going to paste this in. I'll say
178:53 this is an example of the sort of thing that we're about to build. I'm going to paste this in just so
179:00 it has context and so it can write my landing page for me. And then next up, obviously, we need that
179:05 um prompt that we just copied over. I'd like to build an application. I want it designed
179:09 according to the screenshot that I sent over. The specifications and the stack is um in the middle.
179:15 And then I've also given you a description of another website that does something similar that
179:19 I'd like you to emulate for the copywriting and content and so on and so forth. Okay,
179:25 we're going to stick that in. And uh this is most likely going to end up using like a next.js stack,
179:30 although I did not this time necessarily want to be opinionated cuz I wanted to see what the
179:34 app was going to do. Uh when it ends up creating files, it'll do so over here. Keep in mind that
179:38 we are in planning mode as per usual. So that's what's going on down here. And it looks like we're
179:42 using Oh, actually we're using Vit, which is good because that'll give us a the ability to maybe
179:47 use a different framework here. To be honest, I don't really care about the specific framework,
179:50 right? We talked about how there were multiple uh in the previous section. So, whatever works
179:54 is going to work. Um, you know, as long as it's fast and performant. Okay. So, at this point, I'm
179:59 just going to sit back and let it do its thing. Awesome. So, I just got a notification saying that
180:02 it's done for Leadzo, which is the name that uh I decided I would give our cute little app. And now,
180:08 what I'm going to do is I'm going to say run it. The reason why I'm going to do that is
180:11 because in order to access this application, we're obviously going to need like some server
180:15 running at the back end. Our browser is going to end up being the client and then that's how we're
180:19 going to communicate with that. So, our server is going to be on our computer for now since it's
180:22 all local. Let's see how it goes. So, we got the Vit server set up. This is the landing page. Uh,
180:27 super clean. I like it. Okay, so we have like some weird spacing here. That's fine. This is
180:33 really nice. I like this AI personalization prompt. Very clean. Very clean. Nice. 100
180:38 free credits. Okay. So, what happens if I click get started? I go over here, which is nice. Um,
180:44 I'm just going to ask it. Oh, it looks like it's actually recording a browser session of me testing
180:49 this. This is wild. It's Nick Nikki Wiki. Then, Nikki Nikki Nikki. Let's sign up. Okay, we're now
180:57 inside. We have some workspace settings on the lefth hand side here. API integrations. On the
181:02 right, we have some prompt engineering. So, define the rules leader should follow and generating the
181:05 personalization column for each lead. Cool. Does this actually fill in? Okay, we just have some
181:10 placeholders for now. What happens if um Cool. So, it went it actually went it found the uh specific
181:15 API keys and stuff. That's fine. Scrape leads. So, we need a job name, LinkedIn Sales Navigator URL,
181:21 max leads, then default icebreaker. I think what we want is basically are going to want to be able
181:27 to just say uh I don't know like HVAC companies in the United States and then we want it to actually
181:35 go and find that for us. We're not going to need a LinkedIn sales navigator URL because the appy the
181:39 specific service that we're using doesn't actually um use that. So, it's going to be okay. Then here
181:43 we have some fake order history which looks really clean. We can, you know, open it up in
181:46 a new window or whatever. Awesome. Awesome. Cool. So, let me just check the bottom. You guys can't
181:51 see this, but there's a little button that says log out. So, click this log out button. Nothing's
181:54 going to happen since obviously we don't have the off set up. Yeah. I mean, like in a nutshell,
181:57 this is more or less what I what I wanted. Um, anything else that we need? So, new scrape job
182:01 orders configuration. I think that's basically it. Now, now what we have to do is we basically have
182:06 to test this. Uh, cool. So, what I'm going to do next is I'm just going to run through a couple of
182:11 these services that we're using just so we're on the same page. Otherwise, I think it'll be
182:14 kind of intimidating for you guys to see what I'm doing. But in reality, most apps nowadays are just
182:19 like wrappers, as in they just wrap functionality around some other app. Of course, you could build
182:23 your functionality yourself if you really wanted to, and I can help you with that. But in my case,
182:27 you know, for the purpose of this demonstration, I'm just going to do what I normally do,
182:30 which is I use a three a thirdparty service called this leadsfinder on a uh which basically allows
182:34 you to put in some parameters and then get some leads. So, it generates targeted B2B contact list
182:38 using advanced filters. Now, this isn't the best lead scraping service out there. I should note
182:42 that like it's actually quite poor in terms of quality now because uh the leads are cached and
182:46 they haven't been around for quite a while. So, I use this as an example in Make Your School,
182:51 my community all the time. But, let's say I'm scraping some dental clinics in Canada. I want
182:54 to scrape a thousand. What I do is I basically just put in a bunch of job titles here. Owner,
182:57 practice owner, principal dentist, lead dentist, so on and so forth, and then locations to include,
183:03 which in my case is Canada, locations to exclude, what sorts of emails I want to get. So, validated,
183:08 not validated, unknown. So, I I actually just want validated emails, what sort of company website if
183:13 I have them. Um, we can use to narrow down the search. The size of the uh resulting company,
183:19 so 1 to 10, 11 to 20, 21 to 50. the industries that I'm looking in. So, health, wellness,
183:24 and fitness, hospital, and healthcare. And then which ones not to look for some keywords, dental,
183:28 dentist, and then I'm also excluding some down here. Then we have revenue, and we also have some
183:32 funding. So, let me just make this smaller because I just want to show you guys how this actually
183:36 works in practice. I just click save and start. And basically, this thing goes on this service,
183:40 Appify, and then goes and it scrapes it for like some small little piddly fee. So,
183:44 it's cooking up some data magic. Uh, let's just wait until we see the very first result, which
183:49 should be about 100 leads or so. And as we see the first rung here has found a bunch of different
183:53 leads from specific companies, company websites, LinkedIns, their full names, their job titles, and
183:58 so on and so forth. This is pretty cool, right? I mean, this is just like a service that I'm using,
184:01 and it returns a bunch of leads. And so, for the purpose of this demo, I'm going to assume
184:04 we're only using like simple services like this. We're not actually rebuilding the wheel. Although,
184:08 I should note that you totally could rebuild the wheel if you wanted to. It's just uh, you know,
184:12 it's not super easy, right? Like, this is really the moat nowadays. It's not the app interface
184:16 that you build. Sorry, that's the wrong one. Uh, where are we? right over here. Okay, so basically
184:22 in order to run this, right, logically what we're going to need is we're going to need an API token
184:26 and then what'll happen behind the scenes is this Appify API token will plug into this search. Okay,
184:32 then it'll use some data with an input like this via API and then it'll find us a bunch of
184:39 of stuff. And then on the back end, we're going to do is we're going to enrich emails using a service
184:44 like this. Basically, not all of the emails that come from this service are going to have
184:48 um like all of the information laid out. So, we can actually use another service called an email
184:52 finder to enrich that. And then over here, um we're going to pass in either our open AI key or
184:57 anthropic API key, whatever one works, honestly, and then use that to generate personalized
185:02 snippets of text that basically are going to allow us to personalize the emails that we send. So,
185:08 hopefully we're all now on the same page. This is a pretty niche service, but you know,
185:11 the best SASes do tend to be pretty niche and um you know, that's more or less what we're putting
185:15 together. We also have an instantly API key for one-click campaigns, which are basically where
185:20 we'll just upload the leads automatically. I don't actually know if I'm going to do this
185:23 cuz the instantly API had a bunch of issues last time I tried, so I might not. And then over here,
185:27 we have the actual prompt engineering. You know, I want to generate like a highly personalized var
185:32 uh uh email, right? I want to say like, "Hey Pete, been following you for a long time. I love what
185:35 you're doing at XYZ company." because those emails that I send when they're highly personalized
185:39 like that tend to land a lot better. So here's where you can actually define the prompt that
185:43 we're going to use inside of the app in order to generate these ice breakers. So you're an expert
185:47 sales SDR. Your job is to create a highly relevant one or two sentence icebreaker so on and so forth.
185:50 This is this is everything here and the idea is you'll get to change this over time and then you
185:54 know save and then see your new orders and stuff like that. Okay, so hopefully now we're all on
185:59 the same page and I've created this demo. This is basically like the vision of the app. What
186:02 I'm going to do now is I'm going to go through and just make a bunch of changes. Um, I'm also
186:07 going to feed in like the API documentations or the services that I want to scrape and use. And
186:10 then my agent should do a pretty good job to start. This is great. The Appify scraper that
186:17 I'm using to generate leads doesn't require a LinkedIn sales navigator URL. I'll give you the
186:22 Appify API below as well as everything that you need in order to make this request, but
186:27 you'll have to modify the new Scrape job form to reflect that. What we'll do is we'll pass in a job
186:33 name and then we'll have AI convert that job name into a list of filters that work with the specific
186:40 um Appify scraper that we're using. We also need a way to be able to click into the orders under
186:46 order history and then open them in sort of a sidebar. Also, right now nothing happens when
186:50 I click those three little dots or the download button. Obviously, we're going to need to download
186:54 these CSVs. Under the configuration section, let's start with the Appify API token up at the top.
187:01 Then let's do the Anthropic and OpenAI API tokens underneath. And then let's remove the instantly
187:06 API token completely and have the any mail finder down below. The idea is going to be our Appify
187:11 actor is going to return most of the information that we need rather than treat OpenAI's API key
187:19 as a fallback. Let's just treat it as another option they could go through and then let's
187:22 just prioritize anthropic. For instance, if both the anthropic and open AI API keys are filled out,
187:28 the model should automatically choose anthropic. If anthropic is empty and open AAI is uh present,
187:33 then we should automatically choose open AAI. And we'll just proceed in that manner. And then
187:37 for prompt engineering, I'm actually going to give you a big long prompt that you could use to
187:41 significantly improve the quality of the output. I want you to incorporate this. Once we're done with
187:46 the front end, we obviously need to work out the back end and have all these functions available.
187:51 So, what I'm going to do is I'm going to create av and then I'm just going to paste in all my
187:54 API keys for you so that you have them. You can use this as demos to basically test the
187:58 backend functionality and we could use these and store them um in a static database for now
188:03 just in like JSON files or or whatever. When we eventually push to our database and use superbase
188:09 um then we can make these more dynamic. I think you have everything that you need. If you have any
188:14 uh questions or misunderstandings or whatever, just give me a shout. Cool.
188:17 So now I'm just going to go through and then give it everything that I promised. So the appy API is
188:23 going to be here. It's going to go right into the app API docs. Now what we want is we want
188:30 to run the actor synchronously with the input and return the output. I believe return the data set
188:40 items rather. So I'm just going to see if I could copy this whole page. Can I copy this whole page?
188:45 Sometimes Appify has the ability to copy the whole page for AI. Yeah, it does. So, copy for LLM.
188:50 Paste that in. See how long that is? That's super long. Yeah, it's pretty long. And then I also want
188:57 to paste in the specific stuff about the actor. So, this is the specifics about the actor. Input
189:05 schema for actor is here. And then, um, I also promised that I'd feed it in a big long prompt.
189:14 So, I'm going to go over to Maker School wrapped, which is massive document that I put together that
189:19 basically guides everybody through how to write like super high quality cold emails. And then I
189:24 have a little prompt here that actually you guys could use as personalization. So, what I'm going
189:29 to do is just going to type personalization and start down at the bottom. There we go. And this
189:37 is going to be the prompt which I'm going to feed in right here. Here's a personalization prompt.
189:46 For the personalizations, use Claude Sonnet 4.6 or uh uh GPT 5.3. Check out both of their docs.
190:01 Okay. And then I think that has everything that I told it that I would give it. I mean,
190:04 this is pretty long, right? Just make sure. Okay. So,
190:06 I'm going to create av and then um paste in all my API keys for use. That makes sense.
190:12 So I'm going to go over here and then just go env. And then I'm now going to go find a bunch of API
190:17 keys on all the services that I promised it and then just paste them all in. So this is going to
190:21 be my enthropic API key right over here. Then go apply API key. So I head over to appy, go to my
190:29 console. There's always a way for us to grab our API key from whatever service we're using. So I'll
190:37 go up here to API and integrations. We'll create a new personal API token and I'll call this for
190:42 SAS app. Should I limit token permissions? Should I set the expiration date? H yeah,
190:49 I'll set an expiration date just in case I forget to delete it. Okay, this one's expiring tomorrow.
190:54 That's all good. I'm going to copy this now. Paste that in. Uh I need my open AI AP. Actually, do I
190:59 need my open APK? No, I don't because I'm going to use the anthropic one. Ah, I suppose uh the other
191:04 services that I need, I can find them by looking at my Vit app right here. Any MailFinder API key,
191:15 paste that in. So, we'll go to any mailfinder, log in. I'm going to go up to the API and I'm
191:20 just going to copy this token right now. Go back to anti-gravity. Feed that in. And we should now
191:24 have everything. So, I'm going to press enter. And I think this is now going to be able to develop
191:28 the rest of our app, at least for now. Uh, this is going to be like kind of what we see above the
191:34 fold. Let me just be smart about this. Don't just paste the prompt in verbatim to the user
191:38 editable section. Obviously, it's pretty long. All right, we've made a couple of changes here. Now,
191:43 we have find me VP sales and practice owners at dental clinics in Canada. I want companies with 11
191:47 to 50 employees. That's kind of cool. If we go to orders here, can we actually click on these? Yes,
191:51 we can. As you can see, we now get a little sidebar. Um, the sidebar is kind of small,
191:55 so I'm going to adjust that in a second, but it is still pretty neat. I mean, I can click
191:58 the download verified CSV button here. So, it's pretty nice. I like this. I really like the fact
192:02 that we have this little job. It also pumps up so quickly. It just makes it seem really snappy. And
192:08 here is the prompt engineering. So, the prompt is just pasted entirely in now, which is nice. Yeah,
192:14 it's basically perfect. We do have um what looks to be no training examples, but that's okay. These
192:20 prompt variables are going to be injected as the first name to lead, last name of the lead,
192:22 headline, industry, organization name, location, even their email address. That's going to be cool.
192:26 And then we also have our uh our tokens in. So now it's just time to actually give this a try.
192:29 So I've just added the API keys right over here as mentioned. And now we're basically good to go. I'm
192:35 going to wait for this thing to relaunch the dev server and then we're actually going to test out
192:39 the flow. I should note that, you know, because we are testing out what is essentially going to
192:44 be the core function of our app, just like with a full stack app, like the probability it'll work
192:48 on the first try is pretty low. I found it kind of interesting because a lot of people like they
192:52 judge AI by its ability or inability to do things in one go. uh human beings rarely do things in one
192:57 go as well. The difference between humans and AI models is silicon thinks at something like
193:01 10,000 times the speed. So you could just try it 10,000 times faster. So you know whether or
193:06 not this works in one shot is okay. We're just going to go back and forth until it it works
193:10 reliably. Um and then from there we're going to pump this up to netify just like I had before.
193:14 And then app number two, full stack app number two, but total uh web app number three is going
193:21 to be completely cool. I've just done this. Now it's storing what's called local storage since
193:24 of course we're always doing our our first jobs uh or our first check statically. So let me exit
193:29 out of my cloud API keys. Thank you very much. Go right over here. Just relogged in and then
193:34 I'm just going to go scrape leads. So I'm going to say and I imagine there are going to be some
193:37 issues here. Find me VP sales at dental clinics in Canada. I want companies with 10 employees. Okay.
193:47 And why don't we do I don't know 200 leads. And then we'll go laconic or lassic. I don't actually
193:54 know how to say that. Um and then we'll go error executing leads workflow. Check console. I'll head
194:00 back to console and then I see that we now already have some issues not found. So what I'm going to
194:06 do is I'm just going to scroll through this then feed back to our agent. All right. After some
194:13 back and forth, it's now telling us it's good to go. I'm not entirely sure if this is true,
194:17 but we are going to give it a try together. Uh, I think it'll probably be over here. And then I
194:22 go slash scrape. Find me some practice owners at dental clinics in Canada. One to 20 employees.
194:30 Cool. I'll press 100 max leads. We'll run the workflow. We see here it's now doing what it's
194:35 saying is a search extraction. And it looks like it hasn't finished it successfully successfully
194:41 because we're immediately getting a return saying it's it's completed successfully,
194:45 but it isn't. Let me just paste this back. I ran this on localhost 888/scrape returned this
194:52 and then I'm just going to paste it in. I'm also going to uh paste in my um input as well just so
194:59 that I could, you know, monitor this and also maybe have a little bit more meaningful of a
195:03 back and forth. Um but anyway, let's see what it has to say. just as a form of parallelization.
195:09 While this is debugging whatever the appy issue is that's leading to um inconsistent output,
195:14 I'm actually just going to have it adjust the copy on the landing page as well. So,
195:18 let me see here. Hey, this is fantastic. I'd like you to change the copy on the landing page that
195:24 it's a little bit more geared towards outbound cold emails specifically. Um, also there are some
195:31 minor graphical issues like the start for free buttons arrow is on the same is on a different
195:36 level than the text. I'm also seeing that there are four cards under built for performance,
195:42 but the fourth spills out onto the second row. Let's do six cards instead. The main value
195:48 props here are the breadth of contacts, the high quality database, the high quality of enrichment,
195:55 um the simplicity of the tool, the affordability of the leads relative to most other people. For
196:04 the AI personalization section, um under AI personalization prompt, remove the export to
196:11 oneclick instantly campaigns and then change the language so it's not start for free.
196:17 You just start. I'm also noticing that there's no pricing section. Update it so that there is a
196:21 pricing section. And make sure that everything in the navbar is like perfectly centered. Right now,
196:26 it's a little bit off, or at least it seems to be off. Add a pricing section that is on average 0.05
196:35 per credit. Every credit returns one verified email. And then offer some higher and lower plans
196:43 um that scale with price. Obviously, when you purchase more, you should get more of
196:46 a discount. Cool. So, I'm going to pump that in. And then I'll say only modify the landing page.
196:52 There are other agents currently working on other sections of the website. Do not modify anything
196:56 that is not the landing page. Also, don't you don't need to rebuild. Okay. So, I'm going to
197:00 have that operating at the same time as our other tool, which is fixing the appy scraper. And then
197:06 I can monitor this just by going back to command E and checking out the agent um kind of conversation
197:12 here. If I go to under inbox, you can see my two open conversations. There's this one here,
197:16 and it looks like we're still building or fixing whatever the specific Appify problem was. Looks
197:21 like it has to do with like hash IDs or whatnot. Okay, so this is a good summary of where it's at
197:25 right now. And then the landing page copy builder is now doing some things. Cool. So,
197:31 it's analyzing the landing page. And now it's going to go through and actually write it.
197:36 Looks like this search worked now on the uh curl command that it created and it just did
197:42 this to validate without me actually having to go through and then do it all myself on the website.
197:46 It's also reporting the specific issues. So there was some location, some swallowed exceptions and
197:51 so on and so forth. That's cool. And it also ran the live test and it's asking me to do it again on
197:56 um you know 888. So that's a different server. Then I'll go what are we doing? Scrape. return
198:03 me owners of HVAC businesses in Texas. Okay, we're still getting the zero completed. So, let's go and
198:11 debug Y. This is my input. Just go into the new landing page update. We've now changed this to six
198:17 rows, which is cool. This looks kind of silly. So, I'm just going to go back here and say is
198:23 currently on three lines. The on though the N looks odd. Everything else here does look pretty
198:32 solid though. I like that we now have a growth and pricing plan with the same style. 49.99 and then
198:40 249. Super cool. And I'll just say let's dress up that final CTA card down at the bottom. Cool.
198:51 We'll go back to our appy scraper, see how this is going. Just shut over a request here. And it
198:55 looks like we are actually doing something which is nice. Um, normally this would have immediately
199:01 errored out, but it's either hanging or it is doing what I asked it to do. I think this is hung,
199:06 which is why nothing is occurring. If I refresh this, I think the server probably
199:10 went down halfway through. The good news is we are populating the database, although either
199:15 some design issues have occurred or something is broken. But as you can see here, we have the
199:19 status, the date, and then the verified emails as well. I'm seeing no problems in the configuration
199:24 side as well. So, it really is just the scrape leads hangup. What I think I'm probably going to
199:28 do given that this has taken me like 10 minutes or so just behind the scenes is I'm probably going to
199:32 go and just give it a bulletoint list of what it needs to do. Like basically if you think about it
199:37 um it needs to interpret my request. it needs to convert that into an input friendly JSON object
199:49 using um you know like a location table UTC. Then it needs to send the request to um some
199:58 big long URL which is going to look something like this just with a different appy token.
200:03 And then it needs to return to user alongside CSV etc. I also think I might just simplify
200:13 the number of steps so that all we're doing is the appy search extraction then any mail finder
200:17 enrichment for now. Um so I'm going to do that next. Just heading back over here. Just going to
200:22 paste all this in. I'll say let's adjust the logic to the following. Okay. So I ended up running out
200:28 of tokens halfway through this build. Let me just show you guys what that looks like and then how
200:31 you can solve it. So, basically, if you use Gemini 3.1 Pro, that obviously being the most in demand
200:36 model right now, given the fact that it's, you know, new, really good at UX and stuff like that,
200:40 eventually you will probably run into some rate limits. This case, this rate limit occurred after
200:44 about an hour of this working independently on its own to solve some problem with some rate limit.
200:49 I just went and I walked away and then I came back and then I saw that um sorry, with the uh
200:53 with the app scraper. And so essentially how you proceed from here, at least my recommendation is I
200:58 would use a different model using the agent chat UX. So I went down to claude opus 4.6. And then
201:05 I said first generate a comprehensive prompt that includes everything that we've talked about so far
201:09 so I can paste it into another version of CC. CC being cla. I'm now going to copy this. Okay. Then
201:16 what I'm going to do is I'm going to open this up in claude code. And not only am I going to
201:21 open this up in cloud code, I'm also going to do something called fast mode because claude has an
201:25 additional piece of functionality that uh Gemini does not currently possess. That is the ability
201:29 to go very very quickly. I'm then going to double check my extra usage. Looks like I'm 600 bucks in.
201:36 So I'm just going to go extra- usage. Keep in mind you guys aren't going to be spending $600
201:40 and stuff on cloud code usage. Why don't I just change this to 700? Um I just use a I use this for
201:45 like so many different things, right? juggling five or 10 projects simultaneously. So for me,
201:50 700 bucks in additional usage might be I don't know an additional 20 or 30 bucks per project.
201:56 Then I'm going to set that monthly spend limit. Going to give that a little refresh here. Now
202:01 it's up to 86% use. So I have 14%. Okay. And then I'm just going to exit out of this and then go
202:06 to a new one. I'm just going to paste all this in now. I'll say proceed. And now there will be this
202:14 little lightning icon down here which denotes that it's in fast mode. And then I get to make use of
202:18 um you know claude code or claude opus 4.6 thinking I should say on fast mode while I wait
202:23 for my Gemini usage limits to come back. Now you don't have to do this. If you don't want to you
202:28 know juggle multiple models like I'm doing right now. If you're happy to trade a little bit of time
202:32 for speed then by all means absolutely go ahead and just use like the claw opus 4.6 built into um
202:38 the Gemini or agent chat inside of anti-gravity. In my case, I want this to work as quickly as
202:43 possible since on kind of a time crunch here. I'm going skating with my girlfriend. So, we're going
202:48 to see how much of this we could do in 15 minutes just using the fast mode. And I'm happy to make
202:52 that time money trade um as necessary. What you'll see about Claude is it's just significantly I want
202:59 to say more verbose with its notifications and the information and it's also a lot easier to
203:04 follow along. That's one of the downsides of the Gemini series of models, just like a little less
203:08 interpretable. Um, the thinking tabs and stuff like that here are basically just in natural
203:13 language and I can follow along with them almost as if it's me doing the thinking. Uh, which is
203:17 one thing I appreciate. Obviously, you do have to weigh each of these minor pros and cons against
203:22 uh, you know, the model's ability to do things like do front-end UX is really pretty and and so
203:27 on and so forth. Cool. So, this looks pretty solid to me. We now have the server. It's going to test
203:32 the API endpoint directly and it looks like we have some internal server error. It's now just
203:36 going to go through and then update model ids and make minor terminations um as to what the error is
203:41 until we're we're good to go. And it's telling me that it is currently running an appy actor
203:46 run. So I'm going to take a peek at this right here. Looks like we ended up finding five leads,
203:51 which I think was initially what we asked for. Going to head over scrape here and I'll say HVAC
203:55 owners in Texas. Let's do 100 leads. We'll run the workflow. Looks like we've now generated the
204:00 filters right down below. So, it's now scraping leads with this poll. And um this is just for I
204:05 guess our own our own purposes essentially. You know, if we ever want to modify what the target
204:09 audience is or our job name, we can do so just by maybe being a little bit more descriptive or
204:14 maybe being a little less descriptive. Okay, we've now completed the job. We have the CSV
204:18 over here and I can actually open it and you can see all these leads are now scraped. So,
204:22 we were basically like 99% of the way there right before I ran out of tokens. Just needed uh another
204:26 model to get it over the line. This looks great. Now let's re add the personalization workflow.
204:34 Use claude sonnet 4.6 as well. Okay. Now I'm going to do the exact same thing. HVAC owners in Texas.
204:42 We're going to test the lead scraping. We can also test the AI personalization as well. I'm doing 100
204:46 leads. So this should occur reasonably quickly. Should be another five or 6 seconds. Okay,
204:51 looks like we're done with that. Now we're doing AI personalization. So Claude in this
204:54 case is generating personalized ice breakers for all of the leads that are in our database.
204:58 Something I'm noticing here is the AI personalization is taking more than five
205:02 or 10 seconds. I imagine this is probably because we're passing 100 rows sequentially or serially.
205:06 If you think about it realistically, you don't need to do that sequentially or serially. You
205:09 could do that parallel in a parallel and send 100 requests simultaneously, whatever the the rate
205:14 limits are. So, I'm going to ask it to do that. I'll say batch the requests. Make do whatever
205:19 you have to do to make it faster. Okay. I'm then going to rerun this. We'll go I don't know HVAC
205:25 owners in Canada instead of Texas. Let's just make sure that lead generation uh filter thing
205:31 still works. So, this is now Canada. We still have a bunch of size filters down here as well,
205:34 which is cool. Because I'm only doing 20, this should occur significantly faster. We're now
205:39 moving on to the AI personalization step. And then at the end, we're now at completion and
205:43 export. That looks great. We're going to download the CSV. Just going to open this up again. Make
205:47 sure we have that personalization column. Where is that personalization column? Here we go.
205:53 Hey, Jean Michelle. Revolutionizing luxury best in 77 is no small thing. Bane Ultra's legacy speaks
205:59 for itself. Wanted to run something by you. So, I'm not really liking how this is looking. It's
206:02 just a little too much right now. So, I'm going to want to make this significantly more casual
206:05 and cleaner. I'll head back to configuration. Okay, these are looking a little better. Still
206:10 probably not the best personalizations we could be doing, but I think just for the purposes of
206:13 demonstration, I'll leave it there. Hey Kate, love what you're building at Posh, also in engineering
206:17 services. Wanted to run something by you. I can see that work reasonably well as an email
206:20 icebreaker. So, let's just exit out of this. We'll close this older one. And uh from here on out,
206:25 all we really need to do, if you think about it, is we need to fix this UX problem. Um we need to
206:31 add authentication with Superbase. And then we need to take this puppy live. So I'm just going to
206:35 do a big voice dump here and get it to the point where the quality is significantly improved. I'm
206:39 going to do that as taking a screenshot of this section. And then coming back to Claude, we'll
206:45 paste this in. Then I'll say, "Hey, the current app looks great. There's just a few issues.
206:52 The order history page looks really squashed and not at all like the rest of the pages. I want it
206:57 in that nice clean style um similar to the scrape page and the configuration page. We also need to
207:06 put this live and uh get this on superbase. So I'm going to set up a superbase instance and I'd
207:12 like you to assist me in the connection of that. We need all of the fields of relevance including
207:20 um database fields for the configuration, the prompt engineering, API integrations, basically
207:25 whatever you've done locally just applied to um you know a database instead. Last but not least,
207:32 when you click on an order in order history, it opens up this nice side modal, but it's
207:37 not very tall at all. I want it stretched out to contain such that I don't have to scroll through
207:44 um the div containing all of the information. If that's unclear, just let me know and I'll clarify.
207:51 I'm going to dump this in and then I'm also going to just because I'm using a new instance of cloud
207:56 code here. Just going to go back and then I'm going to copy all of this. And I'm doing that
208:03 because I want to give it context, but I also don't want it to like go ahead and redo stuff on
208:06 the app ify scrape and so on and so forth. While that's occurring, I'll head over to Superbase.
208:11 And then we'll click start your project. I already do have a couple of apps set up. I think what I'm
208:15 probably going to do is just delete one of these. H probably delete the proposal generator app and
208:22 then set up a new one just because I think you're only allowed two on a free plan. And um I want to
208:26 show you guys how easy it is to set all the stuff up. So just going to delete that. And then I'll
208:30 go new. I'm going to call this one um let's go Nick J Wellsorg. We're going to call this leadso
208:38 DB. I'm just going to do a strong password automatically here. Copy that. And then I'll
208:43 enable the data API. Click create new project. I'm just going to give it all the information
208:49 that uh it needs in order to set up this database just like I did last time. Okay. So, first thing
208:54 is head back to anti-gravity. I'm just going to paste this in. That's my DB password. Then
209:01 I'll head over to this left hand side here where it says project settings. I'll go project name
209:11 and then we'll also go project ID. I think there's one more. We just need the API key so we could do a
209:20 lot of that work for us. So we'll go secret key. And then we'll also go superbase public key. We'll copy that as well. And this should have
209:35 everything that we need. I think what it's going to do now is probably just set up O for
209:39 us. So head over to authentication where it says email. And this time I don't actually want it to
209:44 confirm the signup. So I'm just going to go back to emails and then where I click on sign on signin
209:50 providers. I'll just turn off confirm email. That way I can make an account without having to do
209:54 that back and forth. Great. set up superbase and off. I'll give a bunch of information here. So,
210:02 I think this is probably everything that it needs and then we're just going to head over to
210:06 um SQL editor where it's going to give us a bunch of SQL for us to paste in. Now,
210:10 my Gemini usage limit resets just in a few minutes here. Um just because I have all of
210:14 the context inside of Cloud Code and it's going through and doing this work, I'm probably just
210:18 going to continue in this Cloud Code thread at least until I'm done this migration.
210:22 um then I can start up another agent chat uh using you know anti-gravity's built-in
210:26 functionality and then have a conversation with it. Uh in general you don't really want to jump
210:30 around between one model and the next unless you can either fully export the conversation history
210:34 or you could do some sort of midway summary like I just did a moment ago um from the anti-gravity
210:38 to claude or sorry from the agent chat to Claude code direction. If I were to go the other way,
210:44 I'd do the exact opposite. I asked Claude to give me a detailed project description of everything
210:48 that is currently occurring and all of its current context. So I could immediately just segue that
210:52 into um the the conversation with Gemini 3.1 Pro high. Okay, it's given us a plan and I've already
210:58 enabled this plan and let it go. So we have the superbase URL, the anon key, service ro key and
211:03 and so on and so forth as well as a bunch of other information here. It's going to start
211:08 with the environment variables, give me an SQL migration file, do some client updating, add a
211:13 bunch of protected routes using authentication middleware, finish the login and signup pages,
211:17 have a log out function as well, set up the config page, do the orders page, do the scrape page, um,
211:23 set up the API layer, and then connect that to Netlifi functions before finally building and
211:28 verifying. There's going to be some back and forth there for sure. Um, but just like we did this with
211:32 Gemini 3.1 Pro High, we'll do the same thing here. So, I have the migration right over here.
211:36 I'm just going to copy all of this in. And then we're just going to remove these little comments.
211:47 And then what I'm going to do is just click run. This will go through and then set up
211:51 our database. You can now see this in database because we have a scrape jobs table with all of
211:56 these fields. The user configs table with all of these fields as well. Any mailfinder key,
212:00 system prompt, instantly key, and so on and so forth. And these are all going to be um sort of
212:04 fed into this authenticated user. So this is what the authenticated user will sort of have access to
212:09 when they go from one route to the next. At the same time, it's going through and then updating
212:13 everything that it's set up to do locally using um JSON and JSL files to work through, you know, API
212:19 requests to the Superbase PostgresQL server to the Superbase Postgrql database. And this is actually
212:25 a really good use case of using two different models. The first is to build and the second is
212:30 to basically spot check what the first model did without full context. The reason why is because
212:34 when you don't have the full context, your uh opinions aren't really like polluted by the fact
212:38 that you're the one that spent all this time and energy working on it. Just like you always have
212:42 like empirical or peer reviewers in papers and and studies and research and stuff like that. So
212:47 too do I recommend doing this with models as well. Having an unbiased third party review our code is
212:52 what is ultimately going to make our code and our app significantly higher quality. Funny how models
212:57 are kind of like people in that way. We could theoretically go back and forth and back and forth
213:01 with Claude Opus 4.6 designing something, Gemini 3.1 Pro High designing something else. Um, but I
213:07 think just one of these passes is good enough. And in a way, that's what we're already doing with our
213:11 security audit if you think about it. Okay, it's asking me to run the migration. I already did. So,
213:14 I'm saying done. Let's test it. It's now going to launch this live. And imagine there'll probably be
213:19 some back and forth just like there was before. Why don't we click get started? I'll say nick
213:23 sarif nick atniki.com and then we'll go I don't know nikki nikki. Click sign up. Okay, we are
213:32 now being automatically taken to that config page just like I wanted to. So here is where we'd set
213:36 up our keys and then we have that prompt which is automatically set up. That's kind of cool. Okay,
213:41 I think what we need to do is we actually need to modify this prompt to make sure it it's actually
213:45 like being reflected in the end result. Um and then obviously we need a way to stick our tokens
213:49 in there. So, what I'm going to do for now is I'm just going to go grab the ENV file here. I already
213:55 have my token. So, I'm going to copy this. I'll go this API. Okay. Paste that in. Annie Mailfinder,
214:01 we'll paste that in. Enthropic. We will paste that in. Okay. Now, I want to save changes.
214:08 Just reflect that this actually works. So, it says saved. If I refresh this, I'm seeing that
214:13 the state is the same, which is good. If I make a spelling mistake here and save, I'm seeing that
214:18 the changes are reflecting here as well, which is good. I go to orders, there's nothing. Okay.
214:23 If I go to scrape leads now and I say, find me a bunch of HVAC companies in Canada, owners of
214:29 HVAC companies in Canada, and I go 20 leads, and I run this workflow, is this going to work? So,
214:35 it's gone through and it's generated the filters. Let's just see what it's saying here. It's now
214:39 scraping the leads. Now, we're doing some AI personalization. And I'm just playing around the
214:43 UX here. This is nice. This is nice. and smooth. I like this a lot. I also like these cute little
214:48 animations and whatnot that it's decided to put in. Okay, job completed successfully. I also like
214:52 how on the lefth hand side it's renewed. I don't like how this little um scroll wheel animation on
214:57 completion and export continues. So, I'm just going to head back, turn off the scroll wheel
215:01 animation on completed when the job is scraped. When the job scrape is complete, completion.
215:13 Okay, that'll be good. But for now, let's actually download the CSV. We got our leads up here. Just
215:19 going to take a peek at them. Same thing I did before. Okay, icebreaker is looking great. Love
215:22 what Proparts doing in modular construction. Also work in the space. Love the tutor teach model.
215:25 Connecting educator students is no small fee. That's reasonable. So this clearly inherited our
215:29 good um result. Then finally, if I go to orders, we can see this is now populating our database
215:35 successfully. What happens if I click? Awesome. We have all of the data. Looks really clean. We
215:38 have the parsed filters. We have the profile scrape. You can actually download the verified
215:41 CSV here as well. That's clean. Very nice. Okay, the last thing I'd say is this three. These three
215:47 dots don't do anything. Also, the three dots to the right hand side of an order in order history
215:56 do nothing right now. Okay, that's clean. And then if I go down here to log out. Okay. Well,
216:05 let's just quadruple check everything else is good. Looks like it. We're back here.
216:13 I think it was nikki.com, right? Yeah. Okay, cool. Awesome. And I'm just going
216:17 to head back out and then test the rest of my routes. So, if you guys remember,
216:20 there was scrape. Okay, that doesn't work. There was config and there was also orders. Okay,
216:25 so all of the off middleware here is working correctly. Um,
216:28 how's our landing page? It's looking pretty clean. We don't have payment functionality yet,
216:32 which I'll cover in a second. This looks pretty clean. If I click start, we go back. Nice.
216:39 Also, dress up the footer a little bit more. It's
216:41 quite small right now. That's on the landing page specifically.
216:47 Okay, this is cool. I like that little like light effect that we got in the background. Real clean.
216:51 Real clean. Um, product goes to product. Pricing goes to pricing. Resources. Oh,
216:56 there is no resources link. So, we don't really need that. Uh, I suppose we could probably make
216:59 a cute little logo. So, why don't we head over to asstudio.google.com and just do that while we
217:05 can. I'm just going to see if I could link an API key. Okay, I need a different account for that.
217:10 And over here, let's see if we can link a key. And heading over here, let's see if we can link
217:13 a key. Cool. Generate me a simple square logo, minimalistic, uh, straightforward,
217:20 but immediately interpretable and high-end for a lead scraping SAS called Lezo. And then over here,
217:26 the aspect ratio is going to be 1 one. And we're going to see if we can generate a 2K um, result. I
217:32 should also probably find some inspiration logos. This looks pretty good just because it's simple,
217:38 straightforward, and obviously it's sort of unique. If this gives me a bad result,
217:42 then I'll say something along the lines of that. No, sorry. Flat icon style. Look at the below for
217:49 inspiration. Mimic this. Okay. And then going back to our landing page at the very bottom,
217:53 you can see we have significantly more context including the logo, bunch of information down
217:57 here, and so on and so forth. I've also been told that we should be good. Um, I just sign in here
218:07 on this little orders panel. This looks like it's opening up something, but it's not showing up. So,
218:12 I'll just have to clarify a little bit more what's going on. When I click the three dots,
218:19 it looks like the menu is being hidden within the div. Then, if I go back to AS Studio,
218:27 we see we have this. This isn't bad, to be honest. Great. Remove the text. Let's just keep the shape.
218:32 Okay. And I don't know if you guys could see this, but at the very top right hand corner, we
218:35 now have our little custom logo put in. Um I mean like I think this could probably be a little bit
218:40 bigger. So why don't we make the background color a little lighter gray? Looks good. Why don't we
218:44 make the background color a little lighter gray? Okay. And then if I go to get started, you can
218:49 see that we now have that little new Leadzo logo. And the colors here match the uh sign up button.
218:54 So I mean, is this going to win any awards for its design? Yes, of course. It's it's gorgeous.
218:59 No. Uh, jokes aside, you know, maybe I had a real logo designer come in here or maybe I iterated a
219:03 little bit more on the logo, we'd have something that looks a little bit better. But the rest of
219:06 it looks real clean. I mean, if I don't know, this was an Nvidia logo or something. I probably think
219:10 this is like an Nvidia style interface. It's wonderful. Um, so looks great. Let's launch
219:15 this thing. Now, because we've done a fair amount of work on Netlefi already, we had to use Netlefi
219:20 to like do the backend functions or whatever. That was the design um pattern that the agent decided
219:26 on. This is already on Netlefi. All we really have to do is just change the URL and then create the
219:31 site itself. Just jumping into Netlefi here. There is now a leadso project created a few seconds ago.
219:37 Um that is manually deploying. I don't want it to manually deploy. I just want to show you guys how
219:40 you can link it with GitHub. So I'm just going to pause this and say set up GitHub as well and
219:44 then link the two. And so this now apparently is online. If we go here we have leadzo.netifi.app.
219:52 So this is actually on like a real URL. So we could see up top. Um, I think this might have
219:57 made the uh logo a little bit brighter than I was initially anticipating, which is cool. But
220:00 remember that I want this to be um, you know, on GitHub as well. So, that's what we're going to
220:04 do next. First, it's going to initialize the Git repo. It may ask you to sign in if it's
220:07 the very first time you've done this before. I've done this many times before. So, my um,
220:11 anti-gravity instance is basically already linked to my specific GitHub account. It's now going to
220:15 do what's called git ignore, which is take a bunch of these files that probably shouldn't be pushed,
220:19 like all of my API keys, then ensure that those don't actually go live. Now it's creating the
220:24 actual thing and then linking it to Netlify. It'll handle whatever errors it has in its own syntax
220:29 mostly autonomously. Just checking for mobile optimization as well by making my browser window a
220:34 little smaller and then dragging it all the way to the left. This looks pretty clean to me. I don't
220:37 see any major issues. Nothing so far. Nice. Cool. All of these are arranged the way they should
220:45 be. Pricing. Excellent. Okay. Get started today. Beautiful. Now, how about the actual login page?
220:52 Yep, that looks good. Then how about Nikki? Nikki is the password. Okay, so the actual app page not
220:59 super mobile optimized. Everything else is. So what I'm think I'm going to do, which is my final
221:03 command essentially, is excellent. The landing page and a sign-in pages look great, but the um
221:11 dashboard stuff after you sign in is not optimized for mobile. Make sure that it works on mobile
221:17 displays as well. And while all that stuff's going on, I'm also going to do our security audit.
221:21 What's cool is I could do a lot of these things in parallel side by side. So whereas previously
221:25 I had Cloud Code do the security audit, I'm not just going to paste this big security prompt into
221:28 Gemini 3.1 Pro High for a couple of reasons. One, I've already used like $800 of my Cloud Code limit
221:34 at this point and I don't want to spend anymore. Um, another is that the Gemini model uh rate limit
221:38 runs out at a specific time and then like it's usually back within an hour or so. I think they
221:42 do it like every 2 hours or 3 hours or something. So yeah, I just uh Oh, and the third is I just
221:47 want to test how it is compared to the Cloud Code experience. So, we're going to allow this whole
221:51 conversation here and then it's just going to run through top to bottom and do that security
221:54 audit. Um, what's cool is now we're pushed to GitHub, right? Because we're pushed to GitHub,
221:59 we can actually do a lot more of the um kind of like uh version control based security things that
222:04 we couldn't do that last time because it was more of like a because we had just dragged and dropped
222:07 the folder directly into NFI. So, it looks like it's doing pretty well mapping out the front end
222:12 and backend LFI functions entry points, checking ignore for secret management. I'm just going to
222:16 let this go on its own and then uh along with the designed components and stuff like that, we can
222:21 get to that um when it's all done. Heading back to the app, which is now online, I'm actually just
222:27 going to do one final mobile optimization check. So, that looks really nice and solid. I'm now
222:32 going to sign in. We'll go nickniki.com. And then I think the password was like Nikki Nikki. Um this
222:40 new scrape job here is looking really clean. As you can see, we actually have that functionality.
222:44 Let me just move my head. We actually have that functionality now where all of it is contained
222:48 within like a mobile browser um view which is really cool. And then we also have that little
222:54 navbar. So I'm going to head to orders. Orders you know it's going to be a little tougher by nature
222:58 I think but uh included this little horizontal scroll wheel. And so I'm still technically going
223:03 to call that mobile optimized. I guess we could just like redo the whole structure and have job
223:07 ID here, target request here, profile scraped here, but it'd be a little bit annoying to do
223:11 that. And I kind of like having a table. Tabular data is um notoriously different to turn into like
223:17 mobile optimized form when you're working with tables and HTML. So I think I'll just leave that
223:21 there. This page looks really clean. I really have no issues. Um I'm I'm honestly quite pleased with
223:26 the performance of Gemini and Claude Code together on this app. So 10 out of 10 would do again. Um,
223:32 we do have one more feature I guess which is that feature that I talked about earlier where um,
223:37 you know, if it doesn't scrape the leads through Appify, uh, sorry, the Appify codec crafter actor,
223:43 then I wanted to pass that off to Google Maps. Uh, I think for the purposes of demonstration,
223:48 like we're pretty close to just wrapping up the app. And the purpose of this was not to do like
223:51 some super crazy endto-end uh, like 500 different platform scraping flow. The purpose is to show you
223:57 guys how to wrap around an API and how simple that is. So, I think I'll probably just leave that as
224:00 that actor for now. But uh rest assured you could very quickly and easily weave in uh you know logic
224:05 like hey if this thing returns zero leads then I want you to use this other approach. Um yeah that
224:11 looks pretty good to me. I guess we could also add that post any mailfinder step. H I might just do
224:17 that instead once we're done the security audit. Um generally speaking though you do want to do
224:22 the security audits at the very end. So might be skipping a step here. Not that big of a deal. Just
224:26 wanted to make sure we're all on the same page. On the security side, if I just open up this agent
224:29 window, you can see that it has actually found some major issues. Found major off bypass in the
224:33 API routes. It also found a hallucinated enthropic package dependency. So, it's preparing some final
224:38 checks. That is a big deal, right? Um, you know, it's done more or less exactly what I've asked it
224:44 to do. Go through with a fine tooththed comb and see whether or not we can access routes without
224:49 actually having any sort of credentials. I can open up the task right over here. And, uh, this is
224:53 where we're at. The first phase was where it was just identifying and running through the codebase.
224:58 And the second is now where it's running through every single step here sort of like a tabular way.
225:03 It's now finishing up the report generation. We're going to take a look. So this looks like
225:08 it's quite critical. We have authentication bypass and paid API routes, some hallucinated malicious
225:13 package dependencies, missing with check clauses and so on and so forth. So, what we can do is we
225:18 can actually go through this whole thing and not have this hallucinated anthropic package,
225:23 but instead use the atanthropic-ai- SDK. So, I think what I'm going to do is we're probably just
225:31 going to push it. Okay, great. Do the security fixes, make sure the app still works, of course.
225:39 And now we're going to run through this big list of detailed findings and fix it. Of note, this is
225:43 significantly less secure than u the other app. just off the get-go. And it's probably because
225:48 we have some additional functionality where we're basically like piping through API requests
225:52 and whatnot, right? We're also using a slightly different framework. We're using Vit instead of
225:56 Nex.js, which I think solves a few of these. Um, in total, I think the score is like something like
226:01 70% or so, whereas the previous app, I think, was a little bit higher. But yeah, you know,
226:05 some of these are quite quite severe. The fact that you could bypass um the authenticated user.
226:10 So if they're not authenticated, it skips the check entirely and proceeds to use the fallback
226:14 process API keys to execute the scrape. Any visitor can hit this endpoint via curl or postman
226:19 without authenticating and your server will gladly run expensive API ampy jobs, open a analysis or
226:23 anthropic calls all build to my personal account. This is the same sort of issue that um I think
226:28 there was with OpenClaw at the time where um you know you could just like bypass one of
226:32 the routes entirely, go on like their dashboard and then if they had some little server bypass
226:38 uh setting or flag not like explicitly opted out of then you could actually just use their own
226:42 keys. And so in this way a lot of people had their keys used not only leaked but also used and run
226:47 up something like 25,000 people. It's yeah quite a big deal. Looks like we're now installing some
226:51 input validation libraries and stuff like that and it's fixing the bypass. I'll get back to you
226:55 guys when all this stuff is done. Excellent. Looks solid. We now have everything that we
226:59 need. I'm just going to take a quick peek at the final version of the app. Make sure everything
227:03 here works the same way that it did initially. Opening up another list here. And this looks
227:07 solid. Excellent. So hopefully you guys now see how you guys could use Gemini in conjunction with
227:13 cloud code and anti-gravity to build an app not only that has full stack database authentication,
227:18 everything else, but that also wraps around like a pre-existing API. As mentioned, a lot of fantastic
227:23 um SAS apps nowadays will either incorporate a wrapped API as like their main functionality or
227:28 they'll like include this as one of the five or 10 or 15 different things. Realistically,
227:32 like the software is no longer the moat. It's not really that like, you know, you're going to build
227:36 something super incredible that solves a problem that nobody else has ever solved before and then
227:41 you're going to package it in a beautiful UX that nobody has ever put together before and then, you
227:45 know, put it on the internet and then that is what is going to distinguish you out from from somebody
227:49 else. And so in this way, you know, there are a lot of short-term opportunities you could take
227:52 advantage of through app creation just by wrapping pre-existing APIs that already do most of the
227:57 heavy lifting for you. And hopefully this Appify example um was was a a good show of what that
228:02 might look like. And by the way, just so we're on the same page here, this is just one tiny little
228:06 actor of like thousands of different scrapers that you could use. Just scrolling through Appify here,
228:11 you guys see there's stuff like uh Trip Advisor review scraper, DraftKings Scraper, there's
250:28 all these elements now are starting to match color-wise. We even have that little down CTA
250:35 with that light blue. So, this is a much better approach, I would say. Some other adjustments
250:38 I went through and then in uh a lot more detail basically deconstructed everything that I wanted
250:43 changed. So I wanted to make the nav bar a little bit square. I wanted to fill out the rest of the
250:47 dashboard underneath the hero header, make the social proof section infinitely revolving and so
250:51 on and so forth. And the idea here is we just want to get the app as close as uh possible
250:55 to basically perfect aesthetically speaking before I do all the rest of the work. Okay,
250:59 we got the website right over here looking really clean. Notice how we've gone through and then
251:03 actually adjusted the dashboard down here. That's really, really sexy. Um, I'm not liking the slight
251:08 difference in Oh, actually, no. That's basically perfect. Why don't we just, um, I think I'll
251:13 probably square out all the buttons everywhere. But anyway, this stuff's looking real clean. We
251:17 have the pricing down below, ready to blow up your channel. I'm just going to go to dashboard. Let's
251:22 just see how the actual functionality of the app is. This looks pretty good. Um, I don't really
251:27 like the light blue in the back, so I'll adjust that as well. But everything else is looking good,
251:30 right? Like the margins are basically all the same. Um, we also have emphasize contrast. So
251:35 now the generation prompts are autopop populating. And yeah, I mean, I'd say this is pretty great. I
251:40 don't like the background blue on the um inside of the app page, like the dashboard to generate
251:47 the settings. That component looks weird to me. I'd like some collection of soft gradients on the
251:54 background of the hero header in the landing page. And then I'd like you to turn all pill
252:02 shapes right now into those rounded squares instead. I think that just looks a lot better.
252:08 For instance, the signup button in the navbar, the real-time generation from your prompts widget,
252:15 and the dashboard in the hero header um image. I want all of those little pill shapes converted.
252:24 Aside from that, change define to thumbly. I want you to make sure that those two buttons,
252:30 filter by CTR and plus new thumbnail, are just on one line. Right now, they're both on two. Adjust
252:35 the verbage if necessary. And then everything else looks really clean. Yeah, that's about
252:44 it. All right, this is looking a lot cleaner. We have everything that we need on the landing page.
252:49 Um, I like the fact that the cards no longer look that ugly, atrocious blue. At this point,
252:54 all we really have to do is provide all of our API keys and tokens. So,
252:58 as mentioned, I basically want to reproduce the functionality of AI studio.google.com,
253:03 except I want to be able to provide a thumbnail and then a bunch of my own faces and then just
253:06 have it replace the image in the uh thumbnail, or rather replace the person's face in the thumbnail
253:11 with my own. This is a pretty common thing to do on YouTube nowadays. Basically what you do is you
253:15 find like outlier really high quality thumbnails and then you just replace them and make some minor
253:19 adjustments. Um I'll show you guys what I mean. If you head over to this app here, one of 10, and
253:24 then you go down to, I don't know, videographer or something, and you know, just look for something
253:31 like this by this fella here, Kristoff Oliver. I mean, like, is this the best thumbnail? Actually,
253:36 no. Let's use this one. This one's probably nicer. So, you see how there's like, you know,
253:40 some fella here in the middle and then there's the text around it and then there's some little image.
253:43 So, I mean, like, you know, I think you'd probably design something better than this, but still. I'm
253:46 just going to save this image. Head over to AI Studio. I wanted to just switch my account to
253:51 one that actually has credits. What I'm going to do is I'm going to stick this puppy inside. Then,
253:56 I'll say replace the man in the thumbnail with the man in the profile picture provided. Then, I'm
254:05 going to look for a picture of myself. I like this one. This one's pretty funky. So, I'm going to
254:10 say replace the man in the thumbnail that includes how to build a portfolio with a man in the profile
254:17 picture holding a trophy. Okay. So, what I want basically want to do, what I'm instructed to do is
254:24 to take this and then just swap it out for this or something close to that. So, I press enter. You'll
254:29 see that it's not going to do the most amazing job right off the bat, but it's going to do an
254:33 okay job. And basically the whole idea is we're just going to run this multiple times until we get
254:37 like three or four options. And then we're just going to present them to the user and then they
254:40 can just select one that they really like. And scrolling down here, you can see that we've since
254:43 replaced that man just with me holding my trophy. So it didn't get like exactly what I wanted to do.
254:48 Obviously I don't actually want to be holding the trophy, but you can see that I'm in this fell's
254:52 room. And for the most part, it looks like me. I mean, there's some minor little changes in terms
254:55 of the skin texture and stuff. Um I think my skin texture is worse and it's like done some done some
254:59 touch-ups, but you know, it's got my hair. It's got me holding the trophy. didn't add any extra
255:04 AI fingers. And yeah, that's more or less what we're doing, right? So the question is, how do
255:08 we actually do this in our app, not inside of this as studio.google.com thing and it's pretty easy.
255:13 There's just like a bunch of API routes for image generation. We just basically need to reproduce
255:17 the same flow that I just did here over there. And then we need to um connect API keys and tokens and
255:22 stuff like that. So I have an API key over here. Uh I'm just going to I don't know. I guess I need
255:27 to find a way to copy this API key. So why don't I go to get API key here. We'll create a new one.
255:31 And I'm just going to call this um thumbly. Going to click create. We're now going to have the key
255:38 generated right over here. Okay. And I'm just doing this in a new one because I want to be able
255:43 to turn it off. I'll then go back to anti-gravity. And then, okay, it's just done some changes for
255:49 me. I don't know exactly what. Then I'm going to open up av file and then I'm going to say Gemini.
255:55 I think this is Gemini, right? What is this one technically called? uh maybe like nano banana API
256:03 key and I'm going to paste that in. Um there are a couple of other things that we need if you think
256:07 about it. So this is not enough. We obviously have to go through the whole superbase spiel and then
256:12 get a bunch of images. Sorry, I get a a database from there. So I'm going to set up a database on
256:17 Superbase just like I've done before. Head over to superbase.com or rather I think it's database.new
256:23 is even faster, right? Yeah, there we go. I'm going to do it inside of proposal generator.app
256:28 maybe gyro. Okay, never mind. I need to go and delete one of these old ones, so bear with me
256:31 one second. This is in the leado database, right? So, I'm just going to delete this project. Leadzo
256:36 DB. Cool. Thank you. Delete. Um, and then I'll go to database new. Once that's done,
256:44 now it's going to say, hey, let's make one. I'm going to call this one um Thumbly DB. Again,
256:50 I'm going to generate a password. Copy that password over. Enable. Oh, cool. They also now
256:55 have automatic RLS, which is cool. So, I'm going to create a new project there. And what I want is
256:59 I basically want to um paste in my database password. Let's say superbase DB password.
257:08 Paste that in. Um I don't know, superbase project URL. Paste that in. Previously, I
257:14 did this just directly inside of the um you know, agent chat, but this time I'm actually going to
257:17 copy and paste it over to the CNV. So, Superbase publishable API key. I'm going to paste that in.
257:26 I think there are a couple other ones. You know, I just want to give it my API key as well. So,
257:31 we'll go superbase project ID. Paste that in. You can see it's the same thing as in my URL. So,
257:38 basease project name I'm just coming up with all excuse me, I'm just coming up with all this stuff
257:45 um myself. Like I'm coming up with these names myself. Um these aren't really important. The
257:49 model can understand the context themselves. Okay. So, I I have more or less all of that,
257:54 which is cool and pretty clean. Um, and then yeah, now it's just provisioning my database and API
257:59 input. It's actually creating them for me. So once all that stuff's good to go. I'm just going to
258:04 paste that in. Any other additional functionality we need? I don't think so. So I'm going to say is
258:09 I've added a bunch of uh credentials for nano banana and then superbase um into the env file.
258:17 You now have everything that you need in order to actually build out the functionality of the
258:20 app aka the API calls. I'll go call or find the um specific endpoint to reference. But basically,
258:26 we're going to be replicating the functionality of um Google's AI Studio just inside of my app.
258:33 Let's see. ENV. Cool. And then, you know, there should be the ability
258:43 to grab the code. Okay, cool. And there is. So, I can grab this code. And then
258:48 we're just going to go rest here. And then what I want is I basically just
258:54 want to copy all of this stuff. And then I'm just going to paste this in.
259:05 Here is some REST code straight from their dashboard. And then I'm just going to paste
259:10 this in, which should be everything that they need in order to actually like generate the
259:13 the thing. Keep in mind we're going to be supplying two inputs. The provided
259:20 thumbnail image and our prompt uh I guess three inputs. The provided thumbnail image
259:29 um images of the person's face and then a prompt check there. Let me see. Are there any docs or something like that I could use to give
259:43 me more data? Okay, check their docs if you need more on how to do this. First,
259:51 test all of this via curl to make sure it works. And then once it works, you can put it
259:58 on the app. And then finally, I'm going to just provide some base um data here. So, you know,
260:04 earlier I had that portfolio builder image. So, I'm actually just going to supply these images.
260:08 Um, so this is going to be one image. I think we can just open this in a new tab. Okay. No,
260:14 I guess we can't. So, let me just save the image. This is going to be the supplied. Okay,
260:23 this one over here. Then I'm going to move into anti-gravity. Just upload this to the agent. I've
260:30 provided you three things. supplied the image to insert a face into um face the image to get the
260:46 face from and then prompt and the prompt is going to be here. Let's just save this too. Uh this is
260:56 pretty big actually. I don't know if we'll be able to feed all this stuff in. Let's say face
261:05 And uh it should be able to pull all of this data up from just the names.
261:11 Okay. In case like unless we get blocked, we should be good. Just going to double check this
261:17 because we we have supplied like a lot of image files here. I mean this was like 4 megabytes.
261:21 This here was like I don't know megabytes. So in total it's going to be like five or six megs
261:25 which is actually pretty chunky. Maybe they like automatically resize the images or something so
261:29 it's not taking up a massive amount of tokens. But um you know I always do kind of worry like oh am I
261:33 going to run out of usage and stuff. Okay. So I'm gonna allow this conversation. It can do more or
261:37 less whatever the heck it wants. And then um just double checking thumbly. Yeah. I mean like this
261:46 honestly looks really clean. I'm liking this quite a bit. Nice. And then we have like this infinitely
261:50 revolving social proof section here which you know you stick your own social proof in. And then all
261:55 of the um buttons and stuff like that are square now which is cool. And everything is just a little
262:00 bit more squared off. I don't actually like this shadow. There's a slight shadow in the background
262:03 here, which hurts, but not the end of the world. We have the ability to change this. This is nice.
262:08 Cool, cool, cool. Awesome. I mean, like, you know, I think this is basically like the the MVP of
262:13 um a high quality app with the landing page. So, wonderful. I'm just going to wait and then um let
262:18 you guys know when we're done this next step. Looks like it's already making API calls, which
262:22 is cool. Just using everything that I provided it below. Generative language. Google APIs appears
262:27 to be the endpoint. That's pretty nice. And so it's gone through and actually verified
262:30 that this works and it's created um another step inside of implementation plan. So now it's going
262:35 through and then integrating this directly into the app. So it's not just going to be doing it
262:39 via its own curl requests, but I'll be able to do it via uploads files and stuff like that. Okay. So
262:44 just signing in here. We've now integrated the um database functionality. Going to go over to
262:49 generate and see if we can do this. So you know I can obviously add images and we just did. So
262:54 now we have this cool little blur effect which is really nice. Let me see. Keep the style identical
262:59 to the inspiration image. Make the main subject highly cinematic with dramatic neon backlighting.
263:03 Contrast. So no, I'm going to say but replace with the user. Oh sh uh crap. I need to actually
263:09 provide images, right? So let's upload some faces. Let's do face. This is now me. Okay. And then here
263:17 inside of the default prompt instructions, I'll say replace the thumbnail image with the supplied
263:25 user cinematic. and I don't know dramatic lighting on the face. Replace the face of the person in the
263:36 provided thumbnail image with the face of the supplied user. Cinematic and dramatic lighting
263:42 on the face. Let's save the config. I'm just going to refresh this. Has that been saved? Okay,
263:46 it is. This has been saved as well. Okay, that's great. You know, might as well test one additional
263:51 piece of functionality here, which is if I could just paste the URL in. So let's go back here,
263:57 paste that in. Okay, cool. So we've actually we've actually now got this in the URL, too,
264:01 which is clean. I'm going to click generate variance. And this is really like the test
264:05 of the functionality. So I'm going to give it a few seconds. Then I'll double back with
264:09 um you know, changes if it didn't work, and then maybe some next steps if it did. Okay,
264:13 we've actually generated one of the options here, and it looks interesting. Um for whatever reason,
264:19 look, it's like the background's kind of white. I don't know. And we've only done one, so we want to
264:23 do three, right? Obviously, we're going to want three. I see there's some click functionality,
264:27 which is kind of cool, but um yeah, we're going to have to do more. So, the first thing I mean, the
264:32 dramatic lighting looks freaking badass. Like, you know, it's not exactly my nose, to be honest. It's
264:37 a little bit different for me, but still really cool. Hey, we've um generated only one, not three.
264:43 So, just double check and make sure that there was no issue in the background that prevented us
264:47 from doing um all three simultaneously because we want to populate that with three thumbnail images,
264:52 not just one. Also, when the images came out, they had this sort of like white sheen or overlay. They
264:59 looked kind of transparent. I just want you to remove that. Um, so that I just can see the actual
265:04 image immediately. Uh, and yeah, I think that's about it. What's interesting is while it did that,
265:10 it consumed three credits. Okay, so the credit consumption functionality is there. However,
265:15 when I saved this, it saved it twice. So, that's another thing we'll have to change. This time
265:19 we're going to do the same thing just with the supplied version instead. And then I should just
265:24 be able to click generate variance and we should be able to do three, right? Since we're generating
265:28 three times. So credits available um on the left hand side, which you guys can't see. Say 197 right
265:34 now. Okay, now we have three provided variants. These all look awesome. I'm loving this. Loving
265:39 the the really badass lighting on the face. That's neat. Um so now what I'm going to do is I'm just
265:43 going to select one of the variants that I want to keep. So why don't I select this one? That one
265:45 looks probably the most realistically me anyway. And then I'll click keep selected thumbnail. It
265:50 says thumbnails saved to your gallery, which is awesome. Okay. And then we go back to overview.
265:54 And then we can see this new one here. Beautiful. Okay. So, I guess what else we need? Like the
265:58 first thing comes to mind is we just need a way to like delete these, right? Provide a way to delete
266:03 um the thumbnails under recent generations. Basically, I want to be able to delete ones
266:07 in my gallery so that I don't have to see them in the database anymore. Um aside from that though,
266:11 everything looks like it worked really clean. Oh, um, instead of like the alert that comes up, um,
266:16 just make like a nice modal, a nice toast message, um, that then allows you to, um, I don't know,
266:23 open it in a new tab or download the image or, uh, go back and generate a new one. Also, just little
266:28 things. I mean, these intelligences are so dang good. Notice how in this one here, I don't have
266:32 the O behind my neck, but in this one, I I do. Like, it's, you know, it knows the placement of
266:37 the O and where it should be and stuff like that. But yeah, um now that we're done with all this,
266:41 what we're also going to do is we're going to uh like after we get the little X functionality,
266:46 we're going to hook this up to Superbase and then it's just going to give me that migration script
266:50 so that I could use this in like real production scenarios. Then on from there, it's connecting
266:55 it to Stripe so that the payments work and then yeah, everything's just going to be 100% live,
266:58 which I'm really excited for. Speaking of Stripe, I forgot, but I do need to provide the keys there
267:02 as well. So, let me head over to Stripe, sign into that sandbox. It's right over here. And then
267:07 I'll give both the publishable key and then secret key. So stripe publishable key, stripe secret key.
267:18 Then I'm just going to save this and say, hey, I've also added the Stripe publishable key and
267:22 Stripe secret key. I want you to connect the payment feature as well. You may have to adjust
267:29 the SQL migration script. So um do this first. Okay. And the really cool thing is I can just
267:36 queue up messages. So even if I change my mind or do a bunch of things, I can have this message
267:40 sent. I can then read that message and then just um incorporate it in the flow. I don't actually
267:44 have to wait until it it all finishes. So that's pretty clean, huh? Pretty stoked about that.
267:48 While we're waiting, why don't we test this on another thumbnail? So I'm going to head back over
267:52 to generate and then I'm going to paste this in. Going to set that. I'll say replace the face in
267:57 the provided thumbnail which is the face applied to use cinematic and dramatic landing the face.
268:00 Also replace 100 to 1,000. Let's see if maybe we could get um a slight little variant of the actual
268:08 number in the background as well. Generally speaking, my experience with these AI models,
268:12 you only really want to suggest one major change at a time. So maybe what I could also do is add
268:16 like a little tips feature or something like that so that people know um how to prompt these things
268:20 and get the best results. Nothing like clean work. This one here looks real good. I like it. We have
268:26 the 1000 in the background. Also dramatic lighting on the face. That's cool. And this one has
268:30 dramatic lighting on the face with my actual skin texture. Thank you, Rosa. Um, honestly, I think
268:35 all all three of these are really badass. So, I'm going to keep this one. And as you can see, I'm
268:39 going to have a toast message instead. So, I can download this image. I can open in a new tab. Uh,
268:44 that one doesn't seem to work, so I'm going to have to modify that. And then I can also click
268:47 generate another. It'll take me back to this page. So, really, really clean functionality. I mean,
268:50 this is basically exactly what I wanted. Just wish it could be packaged in a slightly better UX,
268:54 but we'll we'll solve that later. It's now going through and just doing a bunch of Stripe stuff.
268:57 So, creating API routes, resolving TypeScript errors, and so on and so forth. I'll let it go
269:01 and just do that thing. um as it wills and then we'll double check how all that works with SQL
269:06 and we're done with that. Okay. Now I'm going to use the uh big thing inside of Superbase schema
269:12 migration script the file that it created for me. Then just hold command and press enter. I
269:18 realize I used to think that you couldn't have comments in here but uh you can. It's just the
269:21 comments that the previous model did for me were I think like with two hashtags instead of
269:26 um two dashes. As long as there are two dashes, you can basically pump this whole thing in and
269:30 there are no problems. And it's always good once you're done with that just to go back
269:33 to database and then you can see how everything interacts. So see the model here is set up ID,
269:37 user ID, original image base 64, prompt, generated URL, selected URL, and created at as well as ID,
269:42 email, credits, Stripe, customer ID, subscription ID, default prompt, face images B 64, and then
269:48 created at. This is where we're basically going to store their status. Okay? And then over here is
269:54 where we're going to store the number of credits that they have. So if they have a subscription ID,
269:57 then they will have been signed up. Um, obviously if they have credits, any credits,
270:01 then we'll populate that. That's where we're going to get this from. Um, and then if they're at zero
270:05 credits, then when they attempt to make a thing, it'll check their credit balance. And, you know,
270:09 because they don't have any credits, that won't be able to uh work. The primary key of thumbnails is
270:13 ID. Primary key of users is ID. These two things are sort of mapped together. And then, yeah,
270:18 everything else here looks pretty solid to me. So, just heading back to anti-gravity. Right now,
270:21 what it's doing is just finishing up that little migration from uh mock routes, which are when
270:27 you store all of the database files and like, you know, your your local computer to ultimately like
270:32 live supabbase instances. And it's just doing a build right now to verify that everything works
270:37 uh the way that we told it to do it. And as you can see, I've just signed into this supposed new
270:42 account here and uh we are now at zero credits available. So, it's pulling it directly from the
270:47 database. Meaning if we want to run the full flow, we now have to go through create a new account
270:52 and then run basically the entire signup flow. So I'm just going to go back to anti-gravity,
270:58 verify that everything is good. Awesome. Live database has now replaced our prototype API
271:03 structure. I've now done it all. So we should be able to test this. Just going to head back first
271:09 to Superbase and then I'm going to turn off the feature of authentication that forces us to um
271:14 confirm our email. So you can do that in signin. I just do that because it's a little bit faster. And
271:18 I realized after that first build, I was spending just as much time, you know, signing up as I was
271:23 doing everything else. Now I'm going to click sign up. And this is sort of the desired user
271:26 flow. So we'll go nick@niki.com. Continue with email. Let's see what happens. Just says signing
271:31 in. There's no password. So this is a problem. Um, notice how before we always had an email address
271:35 and a password. Now we just have this like email. So I think this is probably a blind spot where it
271:40 didn't really realize, oh, okay, we're connected to Superbase. Now we have O. So we're going to
271:43 need an actual like login page. Hey, the login right now only requests an email, but I need to
271:49 authenticate with Superbase. I'm pretty sure we'd need an email and a password. No, I just tried
271:53 to create one and it didn't really work. There were some errors. Okay, so now going to see if
272:00 maybe I'm already logged in or something. We go to payment. Yeah, no, we can't. So,
272:05 I mean like the middleware routes are working as we could tell with dashboard and stuff like that.
272:08 Everything redirects us to login. It's just the actual login doesn't seem to be um set up yet. So,
272:13 we'll double click that. We'll double check that. Um, it looks like we also added some additional
272:18 landing page stuff here, which is super cool. So, this added a whole new section based off what we
272:22 added. AI power generation, AB testing, clean modern aesthetics, and so on and so forth. We
272:27 also have some FAQs here based off how it works. So, that's really cool. And then we have the ready
272:32 to blow up your channel. Um, Gemini will do this from now and uh every now and then. I don't really
272:38 sometimes it's sort of annoying when it acts without necessarily asking you, but in this case
272:42 it was what I wanted because really really early on in the prompt I said, "Hey, I want you to make
272:46 this longer." And then it said something like, "Oh, I don't have enough context to make this
272:49 longer." So I guess it just like generated its own context based off of our conversation history. One
272:53 thing I really like about this app is just how fast it is. I mean, each of these routes are what
272:58 are called preloaded or pre-filled. And so this is me like really quickly going from one page to
273:02 the other. And just notice how this whole page is just like automatically done. Um, I also really
273:06 like these brief little animations where you, you know, start at the top and work your way down,
273:10 loading each element slowly in succession. You just get the, uh, visual appearance of very fast,
273:15 very performant website. Okay, we have some new superbase schema. So, I'm just going to
273:19 jump over here and then what this is going to do is go through and then add the rest of our users,
273:25 tables, and stuff like that. So, back to SQL editor, paste this in, run. Okay, the updated SQL
273:31 script seems to have worked. So, I think we just added one or two additional records here and then
273:36 allowed it to add like the email and the password. Heading back to Thumbly, if I go click sign up,
273:42 we're running into Superbase URL is required. So, they do have some runtime error. Now, I'm
273:47 just going to paste all of this in. Okay, this new signup page seems to work. We'll go nickniki.com.
273:54 Then, Nickniki. Um, I'm going to click sign in. Invalid login credentials. The reason why it's
273:59 telling me this is because we obviously don't have an account. So, I'm going to go back to sign up
274:03 instead. I like that it keeps the email address and the password. I don't have to redo it. Okay,
274:07 we now have the secure checkout with the starter plan with 100 thumbly credits. So, now what I
274:11 can do Okay, because we're we clicked the starter plan. So, I can go Oh, actually, did we click the
274:17 starter plan? Hold on one sec. I don't necessarily just want to buy the starter plan. I might want to
274:22 buy pro. Let me try agency, actually. Okay, we'll go nickniki.com. And do we have the account? Oh,
274:30 you see because we exited out of the um payment flow, it immediately jumped us into dashboard, but
274:40 it selected the starter plan automatically. So, I need to change that. Right now, it's automatically
274:45 selecting the starter plan. You should allow the user to select which plan they want on the payment
274:50 page. It should also take into account which button they click on the landing page because
274:55 there are three different payment options there as well. Just going to enter this in and then
275:00 I'm going to proceed to check out just to see what happens. When I click proceed to checkout,
275:05 nothing occurs. And I think the reason why is there might be some problem here. Additionally,
275:11 when I click proceed to payment, nothing occurs. Do we need to open up a Stripe checkout window or
275:16 is the payment occurring locally on the platform? Keep in mind, I'm using a Stripe sandbox, so we
275:21 should be able to test the payment and have all of the events and stuff like that run true. Hey,
275:25 more pointedly, um, since I am now signed in, I should be able to go to the dashboard even though
275:29 I haven't done the payment. If I go to overview and then click generate new and then actually go
275:35 down to settings, can I upload my face? So, we go supplied face. Okay. And I'm just going to refresh
275:41 this. Am I still here? Okay. So, I'm not actually keeping the reference faces in. And this could be
275:46 because my account is not like set up yet because the payment hasn't gone through. I'm not entirely
275:50 sure. Let me just make sure everything else works here. So, face that goes through. All right.
275:54 If I click generate variance, what's going to happen? Please provide an inspiration image and
275:58 a prompt. So I have the inspiration image here. The prompt is right over here. So we also have an
276:04 erroneous error message where it says please provide an inspiration image and a prompt. Hey,
276:08 I provided an inspiration thumbnail and a generation prompt. And I clicked generate
276:12 variance, but I'm getting an error called please provide an inspiration image and a prompt. I think
276:16 this is occurring because I don't have a reference face. However, that error is not representative of
276:22 the real problem. If this are if this is the case, I've also noticed that when I click upload face on
276:27 reference face, then I click save configuration, nothing happens. And then if I refresh,
276:33 my reference face is gone. So make sure that the save configuration button works. If it's
276:38 not working because of some frontend error, fix that. If it has to do with superbase,
276:45 let me know if there's anything I need to do on my end. And I'm just going to continue going through
276:48 this and seeing if there are any other errors that I could spot. Obviously, I'm going to sign
276:52 out again because I'm on a local dev server. This is all occurring in real time. So, any updates I
276:56 make to this is going to be reflected. Um, but we do need to make sure that if credits available are
277:01 zero that we immediately jump back, right? So, some other design decision. If a user has zero
277:05 credits upon signin, we need to redirect them to a payment page where they could select um, you know,
277:10 how many credits to purchase and stuff like that. That should occur every time a user is at zero.
277:15 Now, if you're noticing, I'm not actually just like doing waiting, checking the feature,
277:21 and then proceeding to the next one. I'm now at the point where I'm just dumping in a bunch
277:24 of changes. And the reason why is because most of these changes are relatively minor. Uh, you know,
277:28 it's probably just some slight little database misconfiguration or whatever. And so, I can
277:31 actually proceed in this way. Um, have it working on a change while I'm like modifying the rest
277:36 of it. On the landing page under everything you need to win the click, I don't like the shadows
277:43 in general. I'd actually like you just to remove shadows across the entire UX of the website. It
277:47 they just seem a little bit off um given the fact that most of the website does not have shadows and
277:52 does not use them. Under the frequently asked questions where it says how does thumbly insert
277:56 my face? Can I use any images inspiration etc. The title text is good. So how does Thumbly insert my
278:04 face? Is written in like this nice black text, but the subtext that says when you upload your
278:09 reference photos in the dashboard settings, our models learn your facial features. That's a little
278:14 too dark. Can you lighten that just by 10% or so? In this way, I'm sort of arbiting the time between
278:19 the changes that are occurring here and then um you know my testing. So, signing in, going back
278:24 to the dashboard. Let's go to top up. Okay, cool. And now we have the ability to select these three
278:28 different plans, which is cool. Okay, so why don't we pretend I'm doing pro. And then every time I
278:32 click redirecting to Stripe, looks like there's this problem which pops up. So, I'm actually going
278:35 to copy this over then say every time I try making a payment by clicking the proceed to checkout
278:41 page, this error occurs. But I mean like you know we could also parallelize this and do a bunch of
278:45 them simultaneously. No real need. Um but yeah I mean like you know we're getting closer for sure.
278:50 One other change it just made is when I click on starter you see it goes payment question mark plan
278:55 equals starter. So I'm actually on starter but if I go pro it actually opens up this page to pro.
279:00 So these links do something now which is kind of cool, right? I can actually click get started and
279:04 then go to a specific payment page. I'm unsure if this is because I'm logged in or logged out
279:09 though. I'm going to click sign out. Then I'll go back here and then see what happens. Okay,
279:13 so login question mark plan equals pro. That means it's actually going to keep and conserve
279:18 this query parameter as I browse through the rest of the website, which is pretty neat. Okay,
279:21 now the redirection script has changed. It's pretty clean. The way that this always works is
279:25 you can just put in whatever um numbers you want so long as your card details are 4242 repeating.
279:30 So I'm just going to click pay. Please do not save this card because it doesn't work or exist. And
279:37 it looks like after the payment, we're being sent back to the main page. So, I'm just going to say,
279:41 "Hey, it looks like the Stripe Checkout payment um went through, but then it redirected me to the
279:47 slash payment route." Uh, if I go to dashboard, it continuously pushes me back to that route despite
279:54 the fact that I've already made the payment. So, we just need to find a way to validate that the
279:59 user's actually done the payment. That seems to be the main block right now. Okay, it's telling
280:02 me that it's finished this, which is cool with new secure endpoints and session IDs and stuff like
280:06 that. Okay, I'm just going to try a new account here and see if maybe there's a problem with
280:10 that. Maybe it just has to do with the fact that I had an old account and it's redirecting me based
280:15 off some old flag. Then I'll click processing there. That payment looks good. No, it must be
280:20 a more broad issue. So, check out Stripe here. It looks like we are receiving the payments. So,
280:26 that's going through. Um, for whatever reason, we're not actually capable of connecting that back
280:30 to a person. This is my fake card, nick@niki.com. I've made tons of payments. Uh, I'm just going to
280:36 relay this information over to my agent. If agents have a hard time dealing with stuff like this,
280:41 it's best just to give them as much context as humanly possible so they don't get stuck on one
280:45 loop over and over and over again. Okay, looks like I've finally made it into the dashboard. So,
280:49 we finally solved that persistent error um to do with payments. As I'm sure you guys can imagine,
280:53 you know, adding payments is like adding another whole u problem that you have to solve,
280:57 which is why I wanted to push it off as long as possible. But, uh, now that we have I'm seeing
281:01 that the credit monitoring is good, settings look good. But I'm going to try uploading
281:05 faces. See if we could um diagnose any issues there. The saving configuration button looks
281:11 like it works if I refresh this now. Okay. No. So, it's telling Oh, okay. Cool, cool,
281:17 cool. I got worried there for a second, but I guess we had a bit of a lag. Um, that's okay.
281:21 Okay. Going to take a peek at an example. Why don't we just go to thumbnail generated? Oh,
281:29 no. That's uh that's me from before. Let's do this one here. And then um it doesn't look like we're
281:36 saving the prompt variants. That's one change. I'm also noticing this is significantly laggier than
281:41 it was before. Uh make the main subject highly cinematic. Replace the face with the face of
281:52 the supplied face of the reference image. Use dramatic cinematic lighting on the face. Okay,
282:01 let me try saving this configuration. Just seeing if maybe it's an error or if maybe I didn't fully
282:06 understand what this is doing. If I refresh this now, do we have that default prompt down below or
282:13 does that need to be dealt with as well? And why is it so laggy? It may just be my computer. I am
282:18 editing a bunch of videos. So, okay, that doesn't look like that filled in, which is unfortunate.
282:23 Um, why don't we do supplied here? Generate new variants. Okay. Make sure the generation prompt
282:31 auto prefills with the default prompt in settings. Right now it isn't. It should pull directly from
282:38 the default prompt instructions. It's also a little laggy. The app takes significantly
282:44 longer to load now than it used to. Diagnose whether this is because of some persistent error
282:50 behind the scenes or some issue with prefilling or something else. Okay, taking a peek at this.
282:56 It did give me a very sexy beard. Let's be real. Nick definitely can't grow that level of facial
283:01 hair. But now like the internet will be able to tell the difference. Cue that one up. Thank you
283:06 very much. After the save, it's going to pop up this little thumbnail saved. Um let's download the
283:16 download the image and just see how that looks. See if there are any problems there at all. Nope.
283:20 That looks like definitely fake Universe Nick, which is what we wanted. I'll go back to generate
283:25 another. Now I can do more. Okay. And it looks like this is taking some time to load. I mean,
283:31 it's saying zero. Okay. Now it's saying 97. I think I know the problem. I think in order to
283:34 fix whatever payment BS that it had to do, it's now fetching data from the database on every page
283:40 load, which is adding a fair amount of latency and then causing the app to lag a lot more. So, it's
283:45 obviously not what we want, but it's what's going on. That's why every time I load settings, it
283:49 takes a second before this comes in. Ideally, what you want to happen in a full stack app like this,
283:54 at least a modern full stack app, is when you sign in, you want it to automatically cache and then
283:58 like like pull all the data and then cache it. Um, and then that way everything is pre-filled,
284:03 all the images are prefilled, the credit amounts prefilled, so on and so forth. And then instead,
284:06 what you want is you basically only ever want that to change if you materially change the database.
284:11 So when you change a database, then it says, hey, you know, you should probably grab the new
284:15 data as well, just uh just to be 100% sure. And in Nex, they manage this through a variety of means,
284:20 but a big one is like mutating the database um or or setting like mutations or or whatever as
284:25 opposed to always fetching totally new data. So, I think that's what's going on. I'm just going
284:29 to instruct the agent, see if we could fix that, and then assuming that there's no other changes,
284:33 I'm just going to push this puppy live. Okay, looks like it's loading significantly faster now,
284:37 which is nice. We can jump around from settings to generate to overview, and we don't have that
284:41 like really persistent lag like we had before. Um, we also have the ability to, you know,
284:45 delete if we wanted to. I think what I'm going to do is I'm just going to open this in, well,
284:50 not an incognito window. I guess I'll just open it in a new tab. And then what I want to do,
284:54 whoa, I don't know what the hell just happened here. No, thank you. Let's not do that. Thank
284:58 you. Thank you. Um, I think what I'm going to do is I'm just going to try the mobile features now
285:03 on the dashboard because mobile optimization is pretty big, right? Just want to make sure this is
285:08 going to work. And it looks like it is. We have um we have a little nav bar down at the bottom now,
285:13 which is kind of cool. And we can jump back and forth between these three. So, that's nice. I am
285:18 a fan. Thank you. And now, let's just exit out of the dashboard, go back to the landing page,
285:23 and just see what we're looking at. So, looks like that mobile optimization prompt worked in
285:27 so far that, you know, the um little section here is mobile optimized. And then all this stuff's
285:34 mobile optimized. I'm just going to pretend sign in now. Okay. Okay. And then yeah, we immediately
285:39 jump to dashboard where we have functionality. Let me just try deleting this. Yeah, I want to
285:43 delete it. And then if I just refresh this puppy, is it gone? No, it's not gone. So that's the final
285:50 change we need to make. And then uh yeah, I'm pushing this puppy live. In addition, I've also
285:55 set this up. So it's now at thumbly-g.netfi.app. I just said, "Hey, put this puppy on GitHub and
286:00 Netlefi. Let's do this thing." And uh yeah, this is actually working really, really good. So,
286:05 I'm just going to go over to sign up here and I'm going to go nicholas@gmail.com. Would be a hell of
286:10 a name if I could pull that up, though. And then we'll go proceed to checkout and I'm just going to
286:15 enter some info. Apparently, my card holder name is 234234. Take that, Nicholas. This has jumped
286:21 us directly over to dashboard and now I have the ability to do everything. So, I'm going to upload
286:26 some face. Uh, what was it again? Was it supplied? Yes, it was. Keep the identical to the inspiration
286:32 image. Replace the face. to face the reference image. Use dramatic cinematic lighting on the
286:35 face. Cool. I'm just going to save this. Says that it saves successfully. Oh, hold on a second.
286:41 That's not my face. That's my face. Good god, Nick. You know, you've been developing an app for
286:47 a long time when you start making trivial errors like that, huh? Okay, now I'm going to generate
286:53 three variants. Um, we're going to see how long this takes. So, counting down. 1 2 3 4 22.
287:01 Okay, so right at 22, we had an unexpected error occurred. So I imagine this probably actually went
287:06 all the way through. There was just some problem with updating the DB. Uh this occurs as mentioned
287:11 when you go from local to some sort of like cloud setup or or you know actually like hosting
287:16 it live. So I'm going to go through and just give this an unexpected error occurred. Do a little bit
287:21 more final debugging and see what we need to do to make this puppy. I would imagine the issue is
287:26 probably related to the fact that um when we were running this locally, we didn't have a timeout,
287:31 but services that like manage the calls for you, like uh Netlefi, for instance,
287:39 typically have timeouts of like 15 seconds or so, maybe 20 seconds. So, I think we probably just
287:43 ran into that. Okay, just ran out of usage again after developing this for a good hour or so. So,
287:47 I've moved over to Claude Code. Uh I'm still going to try pushing and generating the variants here.
287:52 We're going to see how that goes. 22 Mississippi, 23 Mississippi, 24 Mississippi, 25 Mississippi, 26
287:59 Mississippi. Okay, so right at 26 seconds is when we got the result. Um, I imagine that's probably
288:04 why this one's kind of weird. I think that's the first one that's like actually objectively failed.
288:09 Uh, but yeah, no, I like this one. So, why don't we just keep selected thumbnail? Awesome. Looks
288:13 clean as per usual. And uh, yeah, I mean like we'll just click generate another and we can just
288:17 keep on going as many times as need be. But that's it. We just launched our app and it works. And
288:25 there's one final thing we need to do, which is that god darn security audit. Almost forgot. So,
288:29 let's do that. Okay, pasting this directly into cloud code. As we can see here, now reading all
288:34 the client pages and doing the config. And let's see how we do. And it's just building to verify
288:39 that everything compiles now. And then I'm going to do a final check just make sure that, you know,
288:44 the app functionality works the way I want it to. You'll quickly realize that the vast majority of
288:48 time that you spend on this is not actually the building. It is just the giving of vibes plus the
288:56 verifying it works to the way your vibes require it working. So I made a bunch of these changes. Um
289:03 okay, there's some rate limiting off middleware. Okay, so I'm just going to say implement the
289:10 middleware with check stripe web hook secret etc. So I'll probably have to go and grab some stripe
289:20 stuff, but I'm just going to go and verify that this actually works now. Awesome. We still have
289:23 the ability to do everything that we had before, which is nice. Okay, I'm taking a look at this
289:29 is so interesting. Like if you really zoom into one of these things, you see every little pixel
289:33 that this constructed. It's wild. Um anyway, I mean like that dead inside completely. But yeah,
289:40 uh we're now going to run a with check migration on the database. So that's going to be cool. And
289:45 then we'll also add some web hook secrets. So I'm going to head over there and then just verify that
289:49 um I got all this. Okay. Well, that one took a little bit longer than I wanted it to because
289:53 we did have a bunch of back and forth with the payments on Stripe, but suffice to say,
289:57 still good to go. Uh this is a good example now of everything. It's not only, you know, kind of CRUD
290:02 create, read, update, delete, like a traditional app. Doesn't just do stuff that you ask it to. We
290:07 also, um, are wrapping around a pretty popular and powerful API, the Nano Banana API. And then
290:13 we're applying some prompts and then some sort of creative applications here to generate really cool
290:18 outputs. Uh, and then we're wrapping it all in a really nice UX and connecting it to payments. So,
290:22 at this point, like you guys basically have everything that you need in order to just build
290:25 whatever full stack app you want. Uh, I think what I'm going to do next is just do one final app
290:29 combining everything that we talked about. Maybe make the UX a little bit more complicated. So,
290:33 instead of just having three or four, you know, two or three things on the left hand side, we have
290:37 like what might uh be considered more of like, you know, like a really successful enterprise app. And
290:42 then I'm just going to run through the motions that I've already showed you guys multiple times
290:45 at this point before talking a little bit about the economics of vibe coding and then wrapping up.
290:50 Man, I am so excited for this app because as somebody that produces a tremendous amount of
290:54 content nowadays, having an app that can basically allow you to focus on one uh place, let's say
290:59 YouTube or maybe your blog or something and then have that same content, the same concepts and
291:05 ideas immediately distributed to a bunch of other platforms is fantastic. My issue with the way that
291:10 most people do this is they just do it in a really poor way. And so, you know, the end uh output
291:15 quality of, let's say, a blog post converted to like Xthread snippets or whatever ends up being
291:20 so bad that, you know, the AI slop um overruns it and then the quality is really poor. So, my idea
291:25 today is I want to make an app that's so dang good that, you know, you don't get that. And it's still
291:30 written in your tone of voice. It's written really succinctly. It's written really intelligently.
291:34 And I was trying to come up with like a good name for this app just before, you know, like
291:38 clearly if you guys have paid attention so far, the names so far have been afterthoughts, right?
291:42 But um this time I think I already got one. It's going to be called splinter. And the idea is okay,
291:48 you're going to put in one piece of content which why don't we just call this like pillar content.
291:55 This is going to be like the pillar upon which everything else rests. And maybe it'll just be I
291:59 don't know like a blog post or something or maybe like a video URL, right? And then what I want is
292:04 I want this to be able to create content for a platform like X. I wanted to be able to create
292:09 content for a platform like LinkedIn. I wanted to create content for Instagram. I wanted to create,
292:16 I don't know, scripts, maybe like long form scripts. And then I also want short form scripts,
292:23 right? So we could do stuff. And then like eventually, and I'm not going to get to this now,
292:27 I don't think, cuz it's kind of a big ask, but um we should also be able to create like video like
292:32 full stack end video. Um that would be my that would be my end goal. So, this is basically what
292:38 I want the app to do. I want you to be able to provide one piece of content and then immediately
292:42 just like, you know, creates high-quality content that's specific to each platform. And obviously,
292:47 we're going to need to do this through some sort of dashboard. In addition, okay, I don't
292:51 just want this to be basic where we had like our little dashboard on the left hand side with like,
292:55 you know, three things and then we have some other like central section um over here. I want this to
293:00 be more interactive and I want this to have some sort of like really detailed onboarding as well.
293:05 Um, this is naturally going to involve like a fair amount if you think about it. Not only are we
293:10 going to have to do everything we did in the last app, which was to uh summarize a landing page,
293:15 Stripe payment integrations, um, OD DB, some sort of API wrapping, and then like a good way to,
293:21 you know, present that to the user. We're going to have to go further because it's now not just
293:24 one like API that we're wrapping around, but it's realistically going to be multiple. And
293:28 then we're also going to use our own custom logic sort of um on-site logic to well not on-site sorry
293:34 but like our own proprietary stuff to do things like manage the tone of voice the prompts and so
293:39 on and so forth. And perhaps one of the coolest parts of this is I think the last app used AI as
293:43 just like an like an afterthought to help generate you know a list of filters in this AI is going to
293:48 be like the main deal and uh hopefully we all know like AI is the big thing right now. So,
293:53 it allows us to sell both uh AI and our value props, but also AI through the apps. And my my
293:58 goal when building apps is I just want to build stuff that like I actually would use
294:01 uh if I wouldn't actually use it as somebody in a space. Odds are I probably don't understand the
294:06 problem enough to even be building this app in the first place. But yeah, you know, if I could
294:09 save myself a bunch of time with this, that's going to be a solid win. And then if I could
294:12 save other people time of that and stuff like this as well, then that'd be even better. Okay,
294:16 so the very first thing I'm going to do is I keep turning back to this 16 or 17-year-old kid. No,
294:21 he's 16 years old. His name's Leon. And what he's been doing recently is he's been building like
294:24 really cracked high-quality landing page designs for Gemini. And so he comes up with these very
294:29 very in-depth prompts. And then he ends up with like a literal interactive app that you can like
294:33 move your your fingers around. Unfortunately, you didn't take a video of this, but this is like,
294:37 you know, an app that there's like little strings that are basically here being um processed every
294:42 second through I don't know if it's like web web GUI or something like that, but it's some sort of
294:46 3D library. And um he shares his prompts online. He's really cool. I used him in my last video.
294:50 I wish I had half that uh brain at 16 years old. And so what I'm doing just to start us off is I'm
294:55 going to copy this prompt that he's put together. Okay? And then I'm just going to ask Gemini to
294:59 make me a landing page. And I just want it to make me a landing page first before I do the rest
295:03 of the app because I just don't trust that it'll be able to do both the very in-depth programming
295:07 required to build some sort of cool 3D generative thing and then also do the app. So basically what
295:12 I'm going to do is I'm going to have it like generate the the landing page and then we'll
295:14 build the rest of the app out afterwards. Um, so you know, kind of non-traditional, but basically
295:19 what I've done here is I've just pasted all this stuff in. Okay, I'm going to press enter. And I'm
295:23 not going to read this whole prompt to you, but this is basically, you know, act as an elite,
295:27 award-winning creative developer and digital generative artist. Your task to write a single
295:30 self-contained executable file that renders an ultradetailed pixel perfect and breathtaking hero
295:34 section for a next generation tech company. Critical constraints, do all this fun stuff.
295:38 Here's the theme and the content. You know, provide some information about what I want and
295:42 stuff. And stylistically once we have this set up um you know I'll make some minor modifications to
295:47 it so it's not a one to one clone or rip of this uh and then we can actually move on with the app.
295:52 Now while I'm doing that just to save on time I'm going to voice dump everything that I think this
295:57 app is going to include. Um and then I'm going to send it over to claude code so that I can have two
296:01 of these instances operating simultaneously. One that's probably a little bit better at
296:05 architecture design than the other that you know is better at the front-end design that I'm asking
296:09 for. So, uh, I'm not going to repeat it all over to you guys, but a I want to design an application
296:15 that takes a single piece of pillar content and then immediately rewrites it, regenerates it,
296:20 and recreates it, and then syndicates it across a variety of platforms. Okay? And I just gave that
296:24 over to Claude Code, and I asked it for a spec, which is basically a highlevel description or
296:29 overview of what this app would look like. And I just want to run you guys through this here while
296:33 Gemini is designing the actual generative part. So this includes tech stack um app architecture
296:39 some info on the database schema some info about the landing page and marketing site.
296:42 So after we're done with this, we'll use this to modify it. Pricing and Stripe integration,
296:46 authentication and signup flow, onboarding flow, the actual content syndication engine,
296:51 uh info about the dashboard, the content library, AI configuration and voice model, scheduling and
296:56 calendar, analytics and reporting, settings and account management, API and webbook architecture,
296:59 and then also some direct platform publishing and then AI video generation stuff in the future,
297:04 which basically we're just going to like add stubs or little nuggets that we could use to build that
297:08 out later if necessary. I've then given it some information on the text stack and then asked it to
297:13 come up with some other things. So for instance, we're going to use Next.js15. We'll use Tailwind
297:17 CSS plus the Shad CN/ UI component library. We'll have Superbase Realtime for live updates. We'll
297:23 we'll do a bunch of other stuff as well. ZOD validation. This is important for security cuz
297:27 I asked it to make sure that it was as secure as possible on the first shot. What I'm going to do
297:30 is I'm just going to modify a couple of the pages here. I'm probably not going to use a calendar.
297:34 Okay. Analytics look good. Um platform connections for now. I'm just going to leave those out.
297:38 Um, AI voice prompt configuration is good. So, I like this. This is like your tone of voice.
297:44 Just make sure that gets that in right. And then settings, account, billing, and team. All that
297:47 stuff looks good. Here's like the data objects. I don't want to spend too much time on that,
297:51 so I'm not going to worry about it. Um, that looks solid. On the right hand side, it looks like
297:55 this generative component has now been done. So, that's pretty sexy. Now, it's going to go design
298:00 the rest of the website. While we're looking here on the lefth hand side from cloud codes,
298:04 uh we have a bunch of different feature sections. The landing page pricing and stripe integration
298:08 is going to start at 19 a month or 190 a year. So it's going to be 10 months basically giving two
298:12 free months to people. Of note, just before we do this, the input method is really clean. Um I asked
298:16 it to be able to either paste raw content. So just copy and paste a blog post, article, a transcript,
298:21 or a series of notes, or paste a URL. And the whole idea is, you know, if we paste a URL,
298:27 um it's going to go through and then scrape the whole website for us. So we didn't even have to
298:30 touch any of that. Um, additionally, I want to be able to do things like paste a YouTube video,
298:33 although I think right now I'm probably going to leave that out just uh as the demo. And then
298:37 once I have those core functions and features in, then I'm going to do more. But you should
298:41 also be able to upload things like MP3s, waves, M4As, OGs. Um, all these things should be auto
298:46 transcribed. And the idea is it's just going to be like your one-stop shop portal for like, hey,
298:50 I just produced a piece of content. I'm going to plug this in and then I'm going to have copy and
298:53 pasteable ready content to distribute to all these different platforms with minor adjustments. And
298:57 obviously, I'll also be able to like change the prompt anytime I want. Um, so very valuable for
299:01 me. Hopefully it'll be as valuable uh for other people as well. Okay, very satisfied with the
299:06 first iteration of this landing page. As you see here, there are some issues with this WebGL stuff,
299:10 but these are real particles that are being rendered um in real time. Um I don't like how this
299:15 neurallex stuff is all over the place. Obviously, that's that's okay. I've since told it to slow
299:19 things down a little bit, but yeah, I mean like the text on the left hand side of the page looks
299:22 really really clean. Obviously, we have like nice little mouseover buttons and and stuff like that.
299:26 Um, I'm going to change all of this signap stuff to uh Splinter, but for now, I mean,
299:30 Gemini uh 3.1 and you know, prompts from Mr. Leon Lynn over here are absolutely crushing it. So,
299:36 pretty stoked and looking forward where and looking forward to where the next uh step
299:40 goes. After the next round of edits, we've also added some additional sections. Common questions,
299:44 ready to syndicate, and then finally down here, um, a full- length footer. So, that's looking
299:48 pretty sexy. The lines here are still moving around a fair amount. So, I'm just going to modify
299:51 them a little bit more. But, we've now implemented some sort of like mouse um interactivity. Do you
299:56 see how this thing is kind of like moving away from my mouse as I move around the screen? So,
300:00 I can technically control this. It's just it's not super uh what's the term? Trivial
300:04 or obvious to me as a user of the app how this works. I've also had it change these lines. So,
300:09 that's going to slow down pretty significantly. And then we can see what the final product looks
300:12 like. While I was waiting, I also had it go do a little bit of research on other platforms. So,
300:17 Repurpose.io lately, Constant Studio, Buffer, and so on and so forth. And then why Splinter
300:22 will solve it. So most are distribution only or creation only. Splinter will do both. Basically,
300:27 it'll allow you to both create content and then distribute it quickly. Um voice and tone being
300:32 an afterthought here. We're going to fix that via um some pretty strong prompt engineering. I
300:36 think most people that are designing these sorts of repurposing apps are more software engineers
300:39 than they are prompt engineers. I would consider myself much more prompt engineer than a software
300:43 engineer. So that should allow us to get like very high quality tone. Okay, these particles
300:47 are looking a lot better. They now move according to my mouse, which is cool. And then these little
300:52 um things are no longer facing the opposite direction. I'd say they're probably a little
300:56 too many of them. So, I think I'm going to remove the entanglement ratio here just so we have three.
301:00 And then I'll probably also just adjust the color of the particles a bit. So, you know, it's I don't
301:05 know, like kind of lightish yellow, maybe goldish, something like that. Also see if maybe I can make
301:10 the particles just a little bit bigger. Right now, I feel like they're kind of compressed,
301:13 which I'm not a fan of. still is kind of neat just seeing this little streaming animation. Pretty
301:17 interesting seeing the logic and kind of the math that uh ended up aggregating all these things
301:23 together. I mean, I'm just moving my mouse around and there's clearly a deep relationship here,
301:27 but I can't exactly figure it out. I think that's because they're modeling this in 3D instead of 2D.
301:32 Becomes a lot simpler when you see them in black like this. There's definitely some 3D going on
301:37 here as we could see. And honestly, I think I like the black. Um I like the 3D translation. So, I'm
301:42 just going to keep it at that. All right, awesome. So, now that we're done with this, um, now I'm
301:46 just going to modify the content on this page. And I'm just going to do it by giving Gemini the rest
301:50 of the instructions and saying go for it. Um, you know, we're going to want to clean out some of the
301:54 contacts and stuff. Uh, but I'll show you guys what that looks like. So, I'm going to say to
301:58 adjust the copy on the page to match the purpose of the app, which you can find in this side of
302:01 this spec. I'm not actually going to like manually do any of this. And then it'll go through and then
302:06 just adjust the rest of it. And yeah, I didn't actually realize, but this is this is definitely
302:10 like a portal that we are moving through in 3D space. So, it's actually more complex than I
302:15 thought it was. Looks clean to me. We now have everything here set up. All of the syndication
302:21 text is in now. Um, it's still saying synapse, which is kind of annoying. I don't think it got to
302:25 that. Cool. Good to go. So, let's build the rest of the app now. Um, for us, it's going to be as
302:29 simple as just sending all of this information over to Gemini and saying, "Excellent work.
302:35 I'd now like you to build the rest of the app as detailed in splinter_spec.md. But there's one
302:43 change. I'm going to say along the way document each update in an updates.md file so that we have
302:50 a history of tracked changes in case something occurs or I need to feed this into another version
302:59 of the model of Gemini. And the reason I'm doing this is because this is a pretty crazy long app,
303:06 right? There's a fair amount that's going on here. Um, I anticipate I'm probably going to run out of
303:09 tokens at some point because I ran out of tokens about an hour and a half into the development of
303:13 most apps so far. What I want is I basically just want like a list of everything that it has done
303:18 up until the time that it did not do the thing. Um, and I'm just going to store it in a file that
303:22 I can then give to either another version of Gemini later on or clawed Opus 4.6 or whatever
303:27 the freaking model I want. And in this way, this is almost like a GitHub um repo before I get all
303:32 the pushing logic and stuff in. But it gets to take advantage of AI summarization features. So
303:36 I'm not going to have to load the codebase every single time. I want to like analyze and you know
303:39 see what the problem is. This section cracked me up a ton because I don't know if you guys have
303:44 uh seen the draw the rest of the owl meme, but basically it's like how to draw an owl. Draw some
303:51 circles. Draw the rest of the freaking owl. Um I feel like we've just done this so far and it's
303:57 doing that. So, thank goodness for AI, huh? This initial implementation plan is going to be heavily
304:02 modified since we're no longer just building a one kind of uh file uh website. Instead,
304:08 we're going to be distributing some of the stuff across big file structure. Here you can see that
304:12 it's also set at the updates.m MD, which is quite nice. So, we're going to see technical decisions,
304:16 feature implementations, and significant changes applied to the Splinter project. And my hope is by
304:20 doing it this way and then later on feeding this to um you know claude I can have both of these
304:25 models both claude code uh sorry claude opus 4.6 and then gemini 3.1 pro high basically like debate
304:31 about which features are better which things to keep and then which things to remove. Agent
304:35 teams in cloud code does a variation of this right now where basically they have like a shared chat
304:40 file and then they chat back and forth. Um, this updates to me is just a slightly more streamlined
304:44 version of doing that without me having to waste $400 in tokens cuz boy does that agent
304:48 teams feature consume a lot of them. All right, so it's built the MVP implementation plan. Just
304:53 taking a quick peek through this. This is going to need everything here, which is fine. Hopefully,
304:58 we are very used to getting all those API keys now. And yeah, we're going to initialize Nex.js
305:03 directly inside of this root directory. So, it's going to do all of these steps here. Oh,
305:07 hold on. I see that it's not actually taking that into account. I'll say initialize in the same um
305:15 folder as root hero.html will be our landing page. Just want to make sure that's super clear. And in
305:22 this way I get to pause the outputs. I'm not going to waste a bunch of usage on you know building it
305:27 out and so on and so forth. That's where taking a peek especially initially at what um Gemini is
305:33 doing can be pretty valuable. I always liken this to sort of like a trajectory sort of thing. Let's
305:39 say over here is um I don't know South America, okay, on the left hand side and then over here
305:45 is the westmost coast of Africa and hypothetically you are a boat trying to make it from one side to
305:51 the other. And so this is you, right? And then your goal is you want to go over here. Well,
305:55 logically speaking as you are leaving the port on the eastmost side of South America. Okay. Um there
306:01 are a lot of different directions you could go. You go this way, you go that way, you go this way.
306:06 only a very small subset of these directions will actually get you to your goal. Obviously, you're
306:10 going to need to go like here, right? And even then, I'm a little bit off. And so, initially,
306:15 I guess what I'm trying to say is the direction that you pick even in like the first kilometer
306:20 as a boat heading to to to sail is really really important for determining the final placement of
306:25 the app. Um, even if I was like one tiny little degree off, that could be the difference between
306:30 me making it directly on target and then I don't know like a one degree difference or something
306:34 could be the difference between me making it to city that's like 100 km away. And so I usually
306:41 like to be around here to steer the model and then once it's sort of like in this territory
306:46 or whatever, you know, if it's like on track well enough that I think it's like going to be okay,
306:50 then I don't really worry too much about that. Now on the right hand side here you see that the error
306:54 um the agent actually ran into an error. This is another reason why I like being around. This can
306:59 occur for a number of reasons. This could occur for token issues. It could occur because I don't
307:03 know like the API is just out. It could occur for rate limiting reasons or just because sometimes
307:08 um some of these packages don't actually interact nicely with Gemini and then it kind of struggles
307:11 with the terminal. But yeah, I'm just going to be around for the first couple minutes for
307:14 a build that this is this comprehensive because I don't want it to like make a wrong assumption
307:18 and then build something completely different to what I want and then later on I'm just going to
307:22 have to go back and and redo it all anyway. Okay, you got the app right over here. So, it's looking
307:26 pretty sexy. If I click get started, we now can sign in or sign up. So, I'm just going to pretend
307:32 that I've done all of that. Now, we have the onboarding. So, initialize workspace. Cool. So,
307:40 this is like all the platforms that I'd want to connect to. It's good. This is really interesting.
307:45 Formality index, humor coefficient. I like that, but I think we're going to have to add some to it.
307:50 So, I'm just going to go back to the model and then I'll say change voice profile to a default
307:58 um to an advanced advanced setting advanced let's say button where I can modify the prompt directly.
308:09 That looks pretty cool. Dry run simulation. Hey, what's going on? Execute run. This is
308:17 going to be like when it actually does its thing. Cool. Also add a um an additional
308:26 step right after the dry run that shows the output. I'll wire you up to Claude Opus 4.6.
308:41 So we can test this next. Okay, we're now going to enter the dashboard. Okay, so this looks like
308:46 a pretty simple dashboard still. I do like the style we have. We're going to build out,
308:51 you know, a generative interface. It says over here. I'm probably going to want to
308:54 move this stuff a little bit over to the left. I'm not seeing anything under generative engine,
308:58 voice profiles, platforms, or settings. So I guess right now we have the onboarding all the
309:02 way up to the dashboard. So that's pretty cool. Still, if I click log out, I go back here. Then
309:06 if I go back here then uh Okay, cool. So yeah, I think I'm understanding where we're at with this.
309:11 Uh it's looking pretty clean and I'm glad that I managed to do all that stuff with just a little
309:15 bit of prompting. We still have that cool little 3D thing, too, which is really nice. Okay, so next
309:20 up, I'm going to feed in these instructions and then I think what I'm going to do is I'm going
309:24 to have it continue the initialization. Um this is going to be tough. I mean,
309:30 I really like this. I really, really like this, right? But this is going to be pretty tough. Uh,
309:36 I guess we could probably autogenerate a prompt that includes some settings with this
309:42 for the sliders. We'll use this in a prompt to fill variables like formality and humor.
309:56 And then this dry run simulation. We'll execute the input. We should get a new
310:01 one here. Systems nominals. Cool. Awesome. Okay, cool.
310:05 Let's also start building out the dashboard. I'd like you to replicate the attached image
310:15 in terms of content. Now, I'm going to go to dribble over here. I'm going to go dashboard
310:24 and let's see what we can do here. I want something that's just like much higherend,
310:28 cleaner. I do like the squareer look. Um, to me that just implies like a high-end brand. So, I'm
310:33 going to look for something that does have that square look. Let's try filtering by new instead of
310:38 um popular. That way, maybe we can get things that other people haven't built before. Okay,
310:44 this looks pretty clean. I like this. Let's see if we could feed this in. Oh,
310:49 sorry. We need to copy this. We can't just do that. Okay.
310:52 uh in terms of content and style except I want you to stick to our pre-established
311:02 um square no border radius. That's the little um smooth corners. I don't really like that.
311:11 I also want you to add significantly more functionality as per the initial doc initial
311:19 splinter spec.md. And this is looking pretty clean. There's an advanced settings feature
311:26 here now where we can actually change things which is quite nice. I'll pretend I'm executing a run
311:32 running style transfer. Okay, great. Awesome. So, this looks kind of silly. Not a fan of the design
311:39 for sure, but um you know, it's cool that it has a lot of the stuff laid out. Interesting. Yeah,
311:45 this is like highly opinionated stuff clearly. Um all right, so I think what we're probably going to
311:49 want to do is on the left hand side, we're still going to want to have like a like a database,
311:57 sorry, database dashboard panel. Um we're not going to want to mention the model. I do like
312:02 the system log. That part's cool. All right, cool. Let me just give this some stream of consciousness
312:06 feedback. Hey, this looks cool, but it's quite opinionated. I don't like the dark borders. I'd
312:11 like a higherend sort of Lux design internally that still sticks to um very similar to the design
312:18 on the landing page. I'd like you to remove all mentions of the specific models that we're using.
312:23 I want some sort of lefth hand side pane that I could use to select different views. I really,
312:28 really like the system log. I like the credit usage, the generation, source items,
312:34 active platforms. These are fine. replace recent archives with a graph. That graph should go really
312:39 in-depth on the number of generations and which platforms we've connected and stuff like that.
312:43 We also need the rest of the app. So, I need a way to see specific and individual generations. I also
312:50 need a way to create a new syndication. Right now, when I create when I click create new syndication,
312:54 it takes me back to the wizard. But I want this to take me to a page where I can insert content
313:00 either using URL or MP3 file upload or video upload or paste in a bunch of text and then it'll
313:09 do the syndication for me. Remember, we're just dry running all this stuff for now. Uh I'm going
313:13 to include some API credentials for anthropic in a second. So you could hook up the cloud opus 4.6
313:19 six integration and change the rest of the language on the actual app side to reflect
313:24 like normal app usage. For instance, I don't like the term disconnect. I don't like the matrix. Um
313:30 I don't like, you know, some of the other language that you're using here. It seems a
313:34 little too tryhardy. Okay, after about 40 minutes of development, we did run out of tokens. But
313:38 never fear, that's one of the reasons why we're using two models and not just one. So what I've
313:43 done is I've exported our conversation history and then that updates file. And now I'm just
313:47 uh doing next steps which in my case involves feeding in the enthropic API key. So I'm going to
313:51 go and find the anthropic API key here. I'm going to call this uh for splinter. Then I'm going to
313:59 copy it over right there. Okay. And then what I'm going to do is I'll say let's wire up Claude Opus
314:08 4.6. Test a bunch of prompts. Give me a few uh a few dry run examples. And then I'll pick the ones
314:17 I like the most. Let's say test 10 prompts. Give me a few dryr run examples of befores,
314:24 afters, and I'll pick the ones I like most and we can integrate them. In general,
314:28 the design quality of Opus 4.6 will be a little bit lower. So, just keep that in mind. However,
314:33 um there are some other trade-offs. You know, it's a little bit faster and then addition to
314:36 being faster, I think architecturally, it tends to make like a better functioning application. So,
314:40 that's why I frontloaded the design with Gemini. And then after the design and stuff like that was
314:45 all wired up, I did all like the little scripting or I'm doing all of the little scripting and
314:48 backend passes with um you know cloud opus 4.6. This database is now set up. So I can head over
314:56 to let's do two things. Under authentication I just want to go to sign in signin providers and
315:02 then I'll remove that little confirm email step and then under project settings I'm going to go
315:06 to API keys just so that this has all of the keys that it needs in order to you know do whatever it
315:11 wants. So I already gave it the publishable key. We'll go um superbase secret API key and then I'll
315:18 paste that in as well. And the idea is now it has everything that it needs in order to manage the
315:22 Superbase instance for me. I don't really need to be involved in this process at all. And I'm doing
315:26 this while Claude is basically just running a quick little test on the prompts. I'm just
315:30 going to pick the best prompt for now and then I'll worry about like optimizing the hell out of
315:33 it later. Okay. And whereas anti-gravity was using its own built-in browser, uh Claude Code typically
315:38 uses Chrome DevTools. So that's what it's doing right now. jumping on taking a screenshot and then
315:42 it's seeing an internal server error. So whatever it did either didn't compile or there was just
315:46 some problem on the back end. Um so that's what it's fixing up now. As you can see the syndication
315:51 page here for create is much lower quality. Um and as mentioned you know cloud is just nowhere
315:56 near as good as Gemini at least as of the time of this recording and designing those really high-end
316:00 uh looks unless it's like per perfectly basically trying to duplicate functionality which is
316:05 unfortunate. Um, it is going to make some minor changes here because it it can't actually click
316:09 this generate button. So, it's cool that it can kind of run that testing loop on its own,
316:13 but all of this is just in contrast with Gemini's high quality design. And it looks like it created
316:18 a LinkedIn post and then also an X and Twitter post. Just taking a peek here. It took us 3 years
316:23 to hit 1 mill AR with our SAS product. Here's what actually moved the needle and what didn't. So,
316:26 this is a um phrase that I explicitly said that I didn't want in the prompt. So, obviously,
316:31 I'm going to have to do some adjustment there. We sell to dental practices only dental practices.
316:35 The temptation to go horizontal was constant, but saying narrow am meant we could out build and
316:38 outmarket anyone in the space. We charge more than felt comfortable from day one. Honestly, the price
316:41 anxiety never fully goes away, but underpricing would have killed us. Okay, just while we have
316:45 this, I'm going to go back to the actual page. Make sure that nothing else was changed here.
316:50 Cool. So, the design here is quite nice, right? Hopefully, we can we can see that. The question
316:54 is where do we go from here? Get started. Sign up. What's the wizard looking like? Okay. Okay. And
317:04 then we're going to have our prompt here. Try run simulation. Sure. Oh, is this now actually using
317:11 real cloud code? No, it's not. Okay, cool. Uh, sorry. Um, Opus 4.6. We'll sign off. Enter the
317:17 dashboard. So, the dashboard here is looking a lot simpler. Um, you know, we we're missing a fair few
317:24 of those cool design features that we had before. And then we also have little rounded corners which
317:30 I don't like. So, I'm just going to dump a bunch of instruction into Claude and see if it can solve
317:34 this. Hey, I want the design of the dashboard to reflect the design of the landing page. Right now,
317:42 there's a very big discord between the two. Notably, the corners are rounded in the dashboard
317:47 and not rounded everywhere else. There's also color discords. We're using this soft purple,
317:52 which uh is correlated with which is typically associated rather with LLMs. I don't want pill
317:57 style things anywhere here. And in general, I want you to use the same fonts in the landing page for
318:03 the new syndication or create page. I like how we've laid this out so far with the URL, file,
318:08 or paste text, but rather than have three buttons that the user has to click, I just want them to be
318:13 able to do it um do all of these simultaneously. So, just have one field inside of that field
318:18 allow users to either paste text, import a URL, or upload the file. It'll eliminate some complexity,
318:24 keep things really streamlined and simple. also allow them to select which platforms they'd like
318:28 to syndicate content to at the bottom. Right now, the generating for button, generating for section
318:33 rather, doesn't allow us to um make any of those changes. Finally, make sure that the app looks
318:38 similar to the landing page. As mentioned, it's very important that we get this one right. Oh,
318:41 this is much better. Okay, as we see here, we now have that perfect design unification. I
318:45 like the new syndication button up top. Um content library, votes, profiles, analytics, config, and
318:50 API access don't fully work yet, but this looks a lot cleaner. So, we paste a URL. or drop a file or
318:56 type our content here. If I go into my finder, if I go into my finder and drop it, does that work?
319:02 Oh my goodness, it does. That's really clean. Likewise, if I paste a URL, so I don't know.
319:08 Let's do this one here. Okay, for my big claw code course earlier and paste that in. Does that work?
319:14 URL detected. Really clean. Okay, we also have blog x, Twitter. Okay. Okay, this is much much
319:19 nicer. Thank goodness. Um, obviously this is going to be difficult to see the differences
319:24 between these lines. So, looks fantastic. Let's add mild differences between the lines on the
319:31 generation throughput graph. I also want to build out pages for content library, voice profiles,
319:37 analytics, setup, and API access. So, work all of those out. Add uh whatever relevant features make
319:43 sense. And if there are any additional features that you think would make sense on the lefth hand
319:47 side panel, please add them. I'm uh attempting to increase the at least perceived sophistication of
319:53 the app right now. Okay, I actually just stepped away to grab myself some breakfast and came back
319:57 and it looks like Claude is still monkeying away at this. It's been probably 30 or so minutes.
320:03 I've had very little actual hands-on involvement and uh yeah, you know, like the agentic workflow
320:09 time horizon of this specific model tends to be quite large. Um, I'll say Gemini actually has
320:14 a slightly longer one, but when you prompt it right, where essentially you say, "Hey,
320:17 here's a big road map of things. Here are a bunch of changes that we've already made. Here's the
320:22 uh whole spec of the thing that we ultimately want to build." And then you just let it run loose. It
320:27 can operate quite independently for quite a long time. Um, and so this has gone through I
320:31 think three or four context windows at this point considering it's about 200,000 or so tokens. You
320:35 know, I've spent a few million tokens um using the cloud or anthropic API. That's multiplied by fast
320:41 mode here. This sort of approach isn't the best for everybody because of costs, but in my case,
320:45 I'm happy to trade off that cost for um time as previously and will continue to do. Checking
320:51 back in on the app, it's looking significantly more fleshed out. We have a content library up
320:55 in here with the actual posts themselves. We can go grab these posts and do something we wanted
320:59 to. There are voice profiles now. Um there is a brand voice, casual, blog. You can adjust that
321:06 using this little section down below. You can also add writing samples for best results which will
321:11 improve the probability that an AI model actually outputs what it is that you want. Generation
321:15 volume right over here along with tokens used, average numbers per session, platform breakdown,
321:19 everything that I basically like talked about in the spec. Finally, automation rules. So,
321:24 um this is like a workflow thing where you can automatically syndicate new content. Basically,
321:27 every time you add new content, it'll automatically go through a big flow. We have
321:31 like enabled and and disabled and stuff like that. Right now, these are all just stored on the local
321:35 database. um it's left to be seen essentially whether or not I could scale that up. We have
321:40 profile platforms. This is where I can connect and disconnect and so on and so forth. And ideally
321:45 this would open up a little like connection panel. And then uh you know we have notifications
321:49 supposedly throughout email with the ability to export all data. And this is really the section
321:54 that I'm I'm the most excited about because uh you know if you make your apps like agent compatible
322:00 via API um I think that's going to be a massive market later on. So, what I've done is I've added
322:04 an API access section with like supposed production keys and stuff. This isn't fully
322:08 fleshed out, uh, as I'm sure you can imagine, but still pretty reasonable. Um, what I'd like to do
322:12 next is basically want to verify that all this functionality works and and actually like does
322:17 what it is that they imply that it does. And so for this, I'm probably going to use a distributed
322:23 um cloud code either agent team or I'm just going to ask it to run through one by one by one. The
322:27 idea would be, you know, spin up a se separate instance to test the API key while you're spinning
322:31 up a separate instance to test the notifications while you're spinning up a separate instance to
322:35 test the automation rules. We'll see how all that stuff goes. Hey, this looks fantastic.
322:38 I don't think there's anything else here that I really want on the app. Um, maybe on the dashboard
322:43 there is a little bit of white space at the bottom because the system log is just just a little too
322:48 long compared to the connected destinations. I think we could probably fix that by adding
322:52 one additional row of connected destinations. That'll um match everything up quite nicely.
322:56 Everything else looks really great. My next desire is to test this end to end every specific feature.
323:02 Just going through a really simple setup here for LinkedIn O because I want to verify that
323:07 this actually works. So, uh, we're going to add a couple products to the app. So, share on LinkedIn,
323:12 we have to do this. So, request access. We also need, um, sign in with LinkedIn using open ID
323:18 connect. So, I'm going to request access to that as well. And the good news is, you know, you don't
323:21 actually have to know how to do this yourself. This is just stuff that uh in this case Claude,
323:25 but Gemini as well can just walk you through. Then under OOTH 2.0 settings, we need to add this
323:30 redirect URL. So I'm going to go up to O. Just going to grab the authorized redirect URLs. And
323:36 then I'm going to paste this in. And then I'm also going to copy both the secret um into this ENV
323:43 file. And then I'm going to uh okay, added restart dev server etc. And then when this is done,
323:51 I need to go to setup platforms. Connect LinkedIn. Okay, cool. So, I'm now going to check out what's
323:58 going on over here. We'll mock. We go to setup platforms and then connect LinkedIn. This is going
324:06 to open up a little LinkedIn dialogue. I'm then going to sign in using my own credentials. Okay,
324:11 now I have a phone number that I have to verify. So, I did just get this. I'll type that in.
324:22 Now I'm going to sign in as myself. Cool. And it looks like LinkedIn status is now connected. I'm
324:28 going to head back over here and say connected just fine. So we should be fine with this. Um
324:35 find some way to store all of that info so we don't need to reconnect next time. All right.
324:43 So, we just did this um you know with with LinkedIn. So, I should be able to go to new
324:49 syndication now and then I don't know. Let me just like find an actual post that I made before. Maybe
324:53 my my blog. It's a good source for this stuff. What's a fast one right over here? Actually, let's
325:00 test this functionality. We'll click generate. I don't know if it's actually feeding in this. So,
325:07 that'll be the tough thing, the thing to double check. We are on a generating tab. It's a fair
325:12 amount of content. So, you know, I'm not expecting it to finish basically immediately. Oh, also we're
325:16 syndicating to LinkedIn supposedly. We should have like a final check before we actually publish it.
325:22 Okay. Okay, cool. So, it's double checked to basically see whether or not we're connected.
325:26 And so, X doesn't have publish, but LinkedIn does. Most business small business owners are terrible
325:30 at hiring. Honestly, it's not because they're bad at business because nobody teaches you how to do
325:33 it properly. Biggest mistake, hiring based on gut feeling instead of actual data. You meet someone,
325:36 they seem sharp. Cool, cool, cool. All right. Uh, we still have some issues here. So like I don't
325:41 know hashtags. Nobody uses hashtags anymore, buddy. Remove that. Explicitly add it to the
325:48 prompt. Uh we should never generate any sort of hashtags. Also, I'd recommend against emojis in
325:53 general. And then let me see what are we doing that is sort of unfortunate. Most small business
325:59 owners are terrible at hiring. And honestly, it's not because they're bad, but it's the biggest
326:01 mistake. Okay, so we have to avoid um LLM isms. Like essentially the main LLM writing pattern
326:10 that pushes it into uncanny valley territory is when you jump between extremely short sentence
326:16 lengths and then long sentence lengths and then do that over and over and over again. That's not
326:20 how most human beings will write unless they're trying to be direct response copyriters. And for
326:25 the most part we are we are not. So find a way to adjust the prompt. Cool. And then everything else
326:29 looks pretty good. So I should be able to actually like push this. Um, thing is I don't really want
326:34 to because then I'm going to have to publish this on my own LinkedIn, right? Ah, I guess we're going
326:38 to have to test it. All right, why don't we go to another page here and then just verify whether or
326:45 not this is being published to LinkedIn around personal profile. If it is my personal profile,
326:49 I'm just going to delete it basically immediately because I don't want all my all my fans to see
326:54 that. How do I do this again? Good god, man. Okay, here we go. And we should be able to right click,
327:01 press delete post, right? Okay, cool. Okay, just ran into one issue right before I did this. So,
327:06 I'm just going to Oops, that's not what I wanted to paste. Um, I wanted to paste this. There
327:11 you go. So, we ran into a problem just as I was about to do this. I I don't know if it like out
327:17 um just ran out and sort of timed out or something, but okay. There we go. There we
327:20 go. That's better. Okay. And now we should be able to go to dashboard. I would hope anyway. Okay. It
327:27 is going to force me to do this signin flow. We do have some more platforms here as you could
327:32 see. Fix the onboarding wizard as well. It should now um function off of live data. Right now it's
327:36 just doing the basic pass with templated stuff. Okay. Setup. All right. All right. Here we go.
327:43 Content library. Go back to new syndication here. Go drive blog. Why don't we get something maybe a
327:48 little bit shorter like this. Paste that in. Click generate. We'll exit out of X Twitter so that we
327:54 only have the syndication option for my LinkedIn. Then we will go to my LinkedIn and then see if we
327:59 could actually publish this. This is a blog post I wrote basically all about interacting with my
328:04 YouTube comments. I said uh you know the statues that we are building aka our YouTube comments last
328:11 way longer than the statues that people throughout history have built because we don't know if people
328:16 are going to be looking at these comments in the year 2148 and the year 20,048 or what.
328:21 So there's a lot of potential life there. Okay. Clicked publish. Refreshing. Not seeing a post,
328:27 which is good. I just clicked publish. I'm not seeing a post on the LinkedIn. Uh,
328:34 let me just on the generated content. Really helps to be hyper specific. Did this copy work? Yeah,
328:45 the copy worked. Okay. So, just want to double check. Going to refresh this. And then I'm also
328:51 going to head over to left click and see maybe if we published it to there instead. I should be able
328:56 to pull this up just by going back to the LinkedIn page. Four left clicks. So, I can click on that.
329:01 Go back to the company page and then we'll go page posts. Okay. I'm not seeing a page post here,
329:06 which is nice. Oh, wow. 675 followers. Did not have any idea 675 followers in that company page.
329:12 That's funny. Looks like there was a specific issue with how we pushed this, which is okay. So,
329:16 we're going to use actual API generate calls now. And then I have the post right over here. Just
329:20 going to head right over here. Click publish. Not seeing any sort of notification. That's an issue.
329:25 So, I'll head back to Cloud Code. I'm not seeing any sort of notification after I click publish.
329:29 Honestly, the experience doesn't feel very snappy to me. I think the cursor might also be
329:34 uh reason why. Find a way to just improve the perceived customer experience when they click
329:39 that button. Whatever it is, toast, menus, and whatnot. We'll go back here. I'm just going to
329:45 quadruple check. Make sure I didn't. Did I post? No, I haven't posted. And then I'll do the same
329:50 thing for leftclick. Let's go leftclick LinkedIn. Just double check that that didn't post to either.
329:57 It might have. Just unsure if I'm posting to company pages right now or my own. Okay, doesn't
330:02 look like I'm posting to either. One thing I'm seeing here is we actually have been storing these
330:06 in the database now, which is cool. Um, our local database to be clear, but still a database. And
330:10 so, you know, we can copy this. We could post this to LinkedIn and whatnot if we wanted to manually.
330:15 Um, but I do want to check to see whether or not we could post u specifically like uh, you know,
330:21 using that flow that we we showed you earlier. So, I'll go back to new syndication. We're just
330:24 going to do one more. Okay. Yep, we got it. I got to delete the hell out of this thing ASAP,
330:29 please. Thank you. And uh yeah, we've just verified that this actually does post. So,
330:33 fantastic work. That's incredible. Um, super cool. Super cool. I'm going to go back here. Hey,
330:38 I tried publishing and the first time I clicked it, nothing happened. I waited five more seconds
330:43 and then I clicked it again and that time it went through the whole publishing loop and
330:46 it actually appeared on my LinkedIn. Diagnose why this might be the case. Go ahead and fix. Another
330:51 cool feature is in the top rightand corner we have a new. So I can actually just click new,
330:54 go back here and then do another one. Um and then I can also store all of that as you guys
330:59 saw before inside of the content library along with the specific generation for that um rung. So
331:05 that to me is really really neat. Also the fact that we have sort of the ability to go listical
331:09 view is cool. You can tell that this really ran with the spec that I gave it and it's um it's done
331:14 a good job. I don't know. Okay, cool. Yeah, even the search works. So very high quality stuff here.
331:19 I'm going to head over to voice profile and see if I could maybe set this as the default casual blog,
331:24 do some editing and just double check what's going on. So, as you can see, we can select
331:28 these here. Um, I don't know. Is there any way to like go deeper into what the actual prompt is,
331:32 though? I'm not seeing that. I'm just seeing like the ability to calibrate formality, humor,
331:36 and emoji usage. So, I think I'm going to have to add that feature. Hey, under voice profiles,
331:40 I'm noticing that we can calibrate formality, humor, and emoji usage, but I don't see any way to
331:45 adjust the actual prompt itself. What I want you to do is to add just like we have in the wizard
331:50 some sort of advanced drop down that I can click on that allow people to actually modify the uh the
331:55 underlying text as well. Under analytics, I want you to make sure that we are actually reflecting
331:59 real analytics. Uh right now I'm not sure if we're pulling from our database or what's going on. I do
332:05 see that the recent activity here is updated with the LinkedIn post, which is pretty solid, but I
332:09 want to make sure that everything else is good, too. Finally, under scheduling, um verify and
332:13 test that this works for LinkedIn. It looks like we have a scheduled post coming up. That said, I
332:17 don't want you to actually publish it on LinkedIn. Um, I just want you to verify that everything
332:21 works up until that point. I've now been given this initial schema. What I'm going to do is I'll
332:25 head back to Superbase, go to the SQL editor, and paste this in. Just verifying that these comments
332:29 work. Okay, it looks like they do. I'm now going to hold command and press enter. We're going to
332:33 run this. And we see success. No rows return. I'm going to go back to Cloud Code. And it looks like
332:38 my Gemini subscription is finally coming back. The rate limiting said it would be 1228. So, we have
332:45 just another 10 minutes here before I can get back to that. Um, which I think I'm going to do
332:48 for like a final design. But that should allow us to push through probably most of like the database
332:53 migrations and stuff. Superbase SQL added. You know, just to be clear, I don't like combining
332:59 multiple um different models like while I'm in the middle of a development session because I
333:03 like all of the context that Cloud Code has to be used in the cloud code thread and all the context
333:07 of Gemini has to be used in the Gemini thread. generally speaking, you get much higher quality
333:11 results because uh this thing has processed so many tokens at this point. You know, has so many
333:15 so much history of like past design decisions and stuff like that that it just inherently gets what
333:19 it is that I'm trying to say. If I were to try and just have Gemini, hey, pick up where whatever left
333:23 off, you would basically have to do the entire job of retraversing all of those failed paths. So,
333:28 we're going to push this through with cloud code and then at the end I'll probably do like a little
333:31 design or redesign. Um maybe do some finishing touches, some some final polishing with Gemini.
333:36 Okay, so I'm going to say let's go 100% superbase and we should be good. And it just got back to
333:40 me saying that the superbase migration is now complete. So it's also given me a summary with a
333:45 bunch of API route os. It's verified the build and whatnot. Verifying the build to me is not enough.
333:50 I need to actually go through the whole testing um end to end. So I'm going to have it log in,
333:54 put in some credentials, and actually like do said testing on its own because it has the ability to
333:58 screenshot things and whatnot. Then once all this stuff is done, it's just a matter of pushing that
334:03 to um you know actually like a like a like a Netlefi host and then also adding payments
334:07 and stuff like that. The reason why I'm not adding payments right now is uh I sort of had a change of
334:11 heart. I thought a little bit about um what would Stripe require in order to set all this up and I
334:16 think Stripe would work better with like a live published app since uh it has like a fair amount
334:20 of callback functionality and I want to be able to give it a URL. So I I'll do all that stuff after.
334:24 Anyway, I'm not touching anything here. Model is now proceeding autonomously and it's doing set
334:28 testing without me. spotted a couple of issues so far with the voice profiles table. So, it's
334:33 going to go through and then actually apply the migration. I can see this doing a bunch of silly
334:37 BS here trying to solve some Superbase issue. So, I told it just to give me whatever uh it needs
334:42 and I'm going to go through and actually I can see this doing some silly BS issue. Um what I'm going
334:46 to do is I'm just going to run this directly in the Superbase editor instead. It's saying
334:50 alternative install this via Homebrew to run it from here. I mean, like it can, but I don't know.
334:54 I don't really want it to waste my damn time or my tokens. So, I just created it. Um, should be good.
335:03 Cool. Yeah. And you can see I've already done the creation. So, we've saved ourselves some tokens
335:07 there. I would hope. And uh yeah, I mean like that's why I keep an eye on it. Good mental model
335:11 here is pretend you're at like uh some security desk job and part of your job is just like
335:16 reviewing CCTV footage and there's like 10 CCTV things in front of you. You're just like kind of
335:19 glancing around at each. It's basically what we're doing here. Although um you know with a little
335:23 bit less context switching since I'm using fast mode. But everything that I've done here, you can
335:26 absolutely replicate with like two or three cloud windows open. The reason why I'm starting with
335:30 GitHub first is because I want this to be version controlled. And to be honest, like you could have
335:35 done this from step one. I just uh I'm not working with anybody else in this project. It's just me,
335:40 myself, and I. So this local folder is enough for me until I get to, you know, the part where
335:44 I'm ready to go. You can see it's um looking to ask a question. Uh h I should probably do this
335:49 privately because I don't want anybody to take my tokens. Cool. We'll do that after it's done.
335:56 um push to Netlefi. Use my credentials since we're just demoing. I'll remove
336:02 them later. And that way I'm going to have like my env keys and stuff like
336:05 that so I can actually go through the uh the generation process and stuff.
336:11 Cool. So now it's setting up Netlefi deployment and then now we just need to
336:15 connect to Stripe. So I'm going to head back to Stripe and then I'm going to open up that
336:19 uh publishable key thing. So signing in should now open up a sandbox. So what I can do is I can
336:25 actually copy the publishable key. Oh, that's not it. I'll head over to ENV and then I'll also say
336:32 Stripe publishable key. Add that. Also go Stripe secret key. I'll add that. And I realize it's
336:40 probably going to have to redo the update. Hey, just a heads up. I've added Stripe publishable
336:44 and secret keys tov as well. Our next step is going to be to connect it to Stripe to get our
336:49 payment integration set up. I'd like you to handle this end to end autonomously. Once it's done,
336:55 um, I'll do an endto-end test of the app myself and let you know if there's any final changes.
336:59 Cool. So, we've since pushed this app live and we can actually see it at splinter-app.netlifi.app. I
337:05 don't really think I needed that dash app there, but the model made that choice and that's okay.
337:09 Um, I'm liking this. It also looks like we have that nice little I didn't really notice, but we
337:13 have that nice little 3D geometric background. Um, we're going to have to find ways to insert
337:19 these pipeline visualizations. I've realized now that we haven't done that on the landing page,
337:22 but it shouldn't be too hard. I think we'll be able to sort that out pretty quick. I'm also
337:26 going to want to widen the landing page a little bit because notice how the hero header is really
337:29 wide and then everything else is really kind of compressed. So, I'm just going to voice dump this
337:32 and then um have it run through some final designs. Hey, the landing page looks solid.
337:38 Just checking the live Netifi link. Now, I'd like you to add more platforms and social proof. Um,
337:43 so just add more company logos and stuff. Aside from the hero header, I find that everything
337:48 underneath is pretty squished. Like it's not very wide. It's very narrow. So I'd like you
337:51 to significantly widen the design. Also, we have processing pipeline visualization, tone analysis,
337:56 matrix, multi format, compiler. These three are placeholders that were meant to be filled in.
338:01 What I'd like you to do is actually go through our app and then fill this in with relevant sections.
338:06 um not screenshots, but actually just mini builds that uh elucidate various parts of the app,
338:12 whatever the the specific feature is. Make sure to widen the pricing and then the call to action
338:16 as well. And just in general make this a little bit longer and a little bit sexier. All right,
338:21 let's take a peek at that actual landing page now. We should have everything essentially ready. Oh,
338:27 that is so cool. I don't think I'm going to get over just how interesting it is to move my mouse
338:32 around. Um, looks like we added significantly more context here. So, we could see these little steps.
338:37 And wow, that some of this is actually dynamic, which is wild. So, future content creation isn't
338:43 about producing more. It's about distributing smarter. Here's how we scale our reach 10x without
338:46 hiring a single additional writer. LinkedIn X, blog, whatever. That's cool. We can then actually
338:51 move these things around. That's really, really interesting. Oh, wow. Nice. So, we can move the
338:58 emoji usage and stuff like that around and then add various features and and buttons. And this
339:04 over here has a bunch of different sections for different types of formats. Hot take. If you're
339:10 still copy pasting the same content across every platform, leaving 70% of your engagement on the
339:13 table. Hell yeah. Threads. We added some more steps down here. So, clean. We then added some
339:19 data. We added an additional pricing tier, which is nice. Creators love Splinter. So,
339:23 we have some supposed big creators. And then we can start our free trial or book a demo. I
339:27 don't know if there is a demo feature though. Is there? Yeah. Okay. So this is where we add
339:30 our calendar. It's pretty neat. I'm probably not going to do the demo stuff. Um anyway,
339:34 that's fine. We'll start free trial. So now I'm going to add some context. So we'll go Nikki
339:40 Sarif. Go Nick@niki.com. Actually, why don't we use a real email? We'll go a very simple password.
339:51 So the creating is now taking us to the onboarding. This is super clean. So maybe we just
339:57 want LinkedIn for now. We're going to set up our voice. So move this around. Looks like we don't
340:03 have access to that advanced section just yet. Let me see if I could pull something from my blog.
340:11 Maybe we'll say this. Paste this in. Then I'll click generate. We should go through a generation
340:19 script here and it should be real. Okay. So the output is what you get in production. Nice.
340:31 Cool. This is now taking my post and then it's um iterating on it slightly. Wow. This
340:39 is great. Nice. Oh, nice. Yeah. So I think the the difference here and the reason why
340:49 this reads so well is because I specifically told it do not have those crazy short sentences with
340:56 like super long sentences immediately after and then alternating cuz it's like blah blah
341:01 blah blah blah blah blah that's not pattern that's signal right it's like you know that
341:05 that's AI just the way that it writes it this has solved that for me which is clean okay
341:10 nice anyway finish setup apparently we're all set so we'll go to the dashboard here
341:15 okay And we ran into our first issue, which is an application error. So I'm going to paste this in.
341:22 This occurred right after the onboarding wizard. And now I'm just going to continuously push until
341:28 I get all the way through the app. Now, logically, what we should do after we are
341:31 done our little onboarding wizard is we should go directly to a pricing page. I'm okay with
341:37 people making like their initial request that little LinkedIn rewrite thing without having
341:41 to sign in because while I know some people abuse that um the abuseness I think will be outweighed
341:46 by the convenience and then the wow factor of actually just being able to pump content in and
341:50 then getting it like nicely formatted and tuned for LinkedIn. So I'm going to keep that in. But
341:55 immediately after like we do want to force them to pay and at that point they'll be in a little bit
341:59 of like reciprocity like they will just have used our app for free which allows us to say use for
342:03 free and then in return um you know it's sort of like a like a teeter totter or a scale in return
342:09 they're going to want to balance that by paying us and then I think I'm going to like make the
342:13 intro offer like pretty affordable so people can you know sign up get the ball rolling and stuff
342:18 like that without necessarily having to spend a lot and then um from there you know as they
342:22 go grow addicted to Splinter her then uh you know eventually the monetization will improve. Okay,
342:29 this looks pretty good. Nice. All right, so why don't we give this a little refresh here and
342:33 see if our data is still in. Beautiful. So we have this. The thing is we don't have any tokens. So we
342:40 do have to ask ourselves how many credits. So free plan. Okay, so we can do five I guess in total,
342:44 right? So maybe we'll go new syndication up top here. We can create content. But notice how we
342:50 don't have LinkedIn or Twitter. So, one more change I'm going to make is under Oh, actually,
342:55 I guess that's to be expected because I selected LinkedIn and then that one X or Twitter does not
342:59 have an API and then blog is manual. When I click new syndication, there's currently only LinkedIn
343:05 X/ Twitter and blog available. I'd like you to add all. We also need to force the user to connect
343:10 at minimum LinkedIn and we need to do this post onboarding. To be clear, are we giving them five
343:15 free credits as in five free generations? Another thing on LinkedIn is now that my app is live,
343:20 we actually need to change the URL. So rather than being localhost 3000, which is what it was before,
343:26 we actually have to go back to Splinter and then type in this, not that, this. So that should now
343:34 give us the right redirect URI, which now if I click on this, this will take us back here,
343:39 which is good. So, I'm going to paste in this password, click sign in, see if I have to
343:47 connect via this. Okay, no, and I don't. That's great. I'll head over to dashboard here. Now, we
343:53 have one active platform configured. And um what else we should do is we should offer some sort of
343:57 like notification saying, hey, connect an active platform. If a user has zero apps configured, then
344:03 encourage them to connect to platform. Um, drip this out in various places throughout the app.
344:10 Okay, I'm going to add that here. And then I'm just going to paste this in, then click generate.
344:16 So now I'm actually going to run through and I want to see how this interacts with credits,
344:20 right? We're not doing payments here. We're just doing um credits. It's your consumption.
344:32 Cool. This looks pretty solid. Okay, nice. So I can do that. Let's check and see whether or not
344:37 this is actually going to work by heading back to my page. And then I'll also check my posts.
344:44 Then if I can make the post, uh I'm just not going to test it again. I'm just going to assume
344:48 that this is going to work. Okay, it's saying published. Refresh. Okay, cool. So, I'm going to
344:56 now delete this. That's pretty great. Uh posting functionality, which is the core functionality,
345:01 clearly works well. Okay, going back to the dashboard, we now have one generation,
345:06 but no tokens have been consumed. So, we're going to have to fix that as well. I'm not seeing any
345:11 credit consumption. I just submitted a request as a Okay, cool. So, credit consumption here hasn't
345:17 been fixed, but I do have this, which is nice. So, I have the whole post. That's lovely. Let's
345:23 um see if we can create a voice profile now. Okay. And then we can also adjust the system prompt,
345:27 which is nice. Cool. Looks like there's a uh default system prompt here. And then there's
345:31 also the ability to add writing examples. Nice. I really, really like this design. It's super clean.
345:36 Very brutalist, which is nice. As you can see, we have one data point. Um, it's picking up our
345:40 time. So, 12:57 p.m. we submitted one, which is really cool. And then it looks like we've outputed
345:46 one LinkedIn post, but it's also writing one Xthread. Also, I only published this to LinkedIn,
345:52 but it's telling me that I've also published an X thread. Perhaps we should just add more
345:57 context surrounding output types in analytics so that they know that you have the option to
346:01 copy from Xthread whereas the LinkedIn post was actually published. Okay, heading down to
346:06 scheduling here we could see a content Q. So this is the generation I can actually select
346:11 uh something I have generated which is neat. So maybe instead of like publishing what you do
346:16 is you just generate a bunch of things. You then select the specific platform you want. So in our
346:20 case LinkedIn then you can set the date using this cute little calendar. So, why don't I pretend it's
346:26 2025 0228? Okay. And then I don't know, we'll do 255 in the morning. That looks good. Let's
346:34 add to Q. Cool. And so, now we do have something coming up on Saturday at 255, which is nice. Now,
346:42 moving over here to setup. It looks like I can change my account details here. Let's just pretend
346:49 I'm only saving my name. If I refresh this, you see that that does not persistent. The setup page
346:55 doesn't save my account details when I change it. For instance, I changed my name from Nikki Sariah
347:00 to Nikki Wiki. I press save changes and then refresh the page and there was no um context
347:05 there. I do like how under billing we do have uh both the free plan and then we have starter, pro,
347:10 and business. So, that's nice. Then we have these little notifications and it looks like
347:13 they're toggling fine, which is good. I do wonder I don't think that this is 100% hooked up. So,
347:18 we'll have to double check that. We have the ability to delete an account. Oh, wow. Okay.
347:22 Okay. And that autodeletes. So, we need to set some sort of like feature that basically checks.
347:28 I just clicked delete account and it immediately signed me out. Make sure that there's some sort
347:32 of are you sure message. Okay, that looks pretty nice. Okay, now I guess this is good for me. If
347:40 this actually did delete my account. Okay, no, it didn't actually delete my account. I see. So,
347:45 it just said that it deleted my account, which is unnecessary. Never mind. It just said that
347:49 it deleted my account. It didn't actually do the deletion. Okay, now I'll generate new key example
347:56 key. Okay, and then we need the curl details. I'm just going to see if we could key here.
348:10 Let's reveal this. And I'll say API key send a request to this URL using the format.
348:21 Let me see if it makes any sense whatsoever. API splinter.io. Okay, for the API request, it
348:28 doesn't look like the domain is a live host. Um, update everything so that it reflects the new URL,
348:35 not api.splinter.io. And then finally, we have this web hook feature, which uh I don't know,
348:41 let's just go web hook test. And over here, we can copy a web hook URL. We
348:47 could basically paste that into our app and say, "Hey, when this is complete, scheduled or posted,
348:52 I want you to deliver to this." So then I'm going to go back to content library. And then I'm just
348:56 going to do one more. So I guess we'll go to dashboard, new syndication here. Then I'll just
349:02 copy all of this over again. Paste it in. Okay. And we have all the rest of these buttons now,
349:07 which is wonderful. Click generate. And then I'm going to go here and then check to see whether or
349:13 not a web hook was actually sent. If the web hook wasn't sent, I don't believe it will be. I'm just
349:17 going to notify the agent. Hey, the generation occurred, but the web hook was not sent to the
349:21 address that I added. Um, double check that all of that is okay. I imagine there's probably some
349:25 issue related to the fact that we're not on the URL that we initially thought we'd be on. Yeah,
349:32 cool. So, we have that the generation has occurred. We didn't end up getting that.
349:36 I can copy this, though. Go back to dashboard. Now, I see we have two created. And there's the
349:41 content library here with the the the second post, which is nice. Okay, what else is it
349:45 telling me? It's telling me that um all the code examples have been updated. So, I should be able
349:51 to go back to API access here and then give this a little refresh. I'm giving this a refresh because
349:58 I wanted to hardcode the change. Okay, just taking a look at this code. Example still says
351:02 Okay, I'm going to go to upgrade and let's see if that works. So, we can now select one of these
351:07 three options. So, I'm going to go pro. Seeing that it's opening up a Stripe checkout page,
351:11 which is good. I'll go to USD and then I'm just going to pretend enter some details
351:15 here and then click subscribe. Looks like the processing is occurring, but is it going through?
351:20 Okay, cool. So, it looks like it went through. Did we go back to checkout? Okay, cool. Yeah,
351:24 we have and we've upgraded. When a user pays, um, add some confetti or something upon the redirect
351:30 only when they make it back after paying. Okay, after a little bit more back and forth, you can
351:34 see we actually have the right profile set up. So, I'm going to head back to Stripe, generate a new
351:38 key, and then actually reveal and then copy this whole key. And I'm just going to see if this ends
351:44 up working because that's the API functionality. Okay, we're still getting unauthorized. Um, this
351:53 using this superb basease session. I don't know exactly what that is. I imagine this is probably
352:00 going to solve it. Yeah. Okay. So, we we're going to have to rewrite that a little bit. The good
352:04 news is the name now saves along with various password problems. Uh, we've now solved all of
352:09 that. Wonder what managed subscription is going to look like. I've never been there before. Oh,
352:13 nice. Okay, cool. So we can actually like we we literally have like our own managed subscription
352:17 page which is Sweet. Um why don't I go to dashboard just so I could take a look at that as
352:20 well. Cool. So here are the generations and stuff like that. Nothing upcoming because I don't think
352:24 we have anything scheduled. Yep. Cool. Yeah. All right. This looks pretty good. Generated formats.
352:29 LinkedIn post two generated exert one generated formats generated. Cool. Cool. This tells me what
352:34 they are now. And then we have access to all of our old posts. Awesome. So now I'm just going to
352:39 mobile optimize this and then run security audit. And then honestly that's it. We're live, baby. We
352:44 can see we're actually sending over a live API request to the Splinter-app API as well. So,
352:49 this isn't just a front-end app for us anymore. This is entirely um yeah, this is super clean.
352:54 Super clean. So, yeah, pretty stoked about that. We also have the API functionality. Obviously,
352:58 we could paste in links as you guys have seen. Not going to lie, this is pretty solid as far
353:02 as apps go. We uh now basically have something that's capable of doing everything that I want.
353:06 Last thing is I'm just going to paste in this security prompt. And just because we've done
353:09 this what three times now, I'm not going to bore you all with the details, but suffice to say,
353:13 using Gemini 3.1 Pro in conjunction with Claude Code for both a mixture of front-end design and
353:19 then backend configuration, route creation, and then payments, and so on and so forth,
353:23 is pretty dang efficient. Now, I should note that we used a ton of tokens this time, and I
353:27 don't actually recommend using that many tokens, like committing that many tokens to an app. Um,
353:32 I just did this because I traded off speed uh basically for money. I wanted to get this done
353:37 as quickly as humanly possible because of an upcoming engagement, not necessarily, you know,
353:41 have three or four instances of cloud running or uh, you know, take three or four hours when
353:45 realistically I could have done it in 45 minutes. So, I'm not going to push the fast mode on you.
353:49 It's just an option. Uh, just keep in mind it does cost a fair amount. This session was probably at
353:53 least $70. And I'm sure you can imagine if you develop an app every couple of days or
353:57 work on your codebase every few days, that sort of thing is going to add up pretty quick. For me,
354:01 I'm happy to do it because of the arbitrage and then the value that I got to produce. Hopefully
354:05 you guys now see how to build an app just like this. Not just a simple CRUD app, but a CRUD app
354:09 that also has API wrapping functionality that does OOTH integration with social media platforms even,
354:15 which are some of the most secure and difficult to authenticate and organize. And then finally,
354:20 um, payment integrations as well, like with Stripe. All right, so you now know how to
354:25 vibe code an app. Congratulations. However, most people that have gotten to this point are probably
354:31 not just interested in building internal apps and tools for themselves. Like, if you've gotten to
354:35 this point, you're probably really interested in building for other people, whether it's consumers,
354:40 whether it's other businesses, maybe it's some organizations that you're working with or whatever
354:43 you want to help economize their workflow and so on and so forth. And so, what I wanted to do next
354:48 is round out the course with a module all about pricing, packaging, and selling what you build.
354:54 Now, most people that are here in your shoes, okay, that are probably interested in um pricing,
355:02 packaging, and selling what they just put together, don't really have any experience doing
355:06 so. And so, it's not that they don't have any like vibe coding um business experience. It's that they
355:11 don't have any business experience in general. And so, what I wanted to do is just give you a very
355:14 highle look at some tactics and playbooks that you could follow to significantly streamline your
355:20 ability to actually successfully go out there and then sell this sort of stuff. whether you know at
355:25 a small scale or whether at a large scale, whether your goal is to replace your income or whether
355:28 your goal is to, I don't know, start a business that does $100 million. Now, I think there are
355:32 a lot of people on YouTube that make courses on vibe coding and stuff and um they're like, "Oh,
355:37 you know, here's how you make all these super cool crazy apps and here's how I spun up 500 clones and
355:42 publish them to the app store." But not a lot of these people have actually made money. So, I know
355:45 that this is a vibe coding course, but hopefully it'll allow me to dive a little bit into the
355:49 business side of things because personally, that's what I find the most interesting. Collectively,
355:52 my businesses make over $300,000 a month in profit. Um, and that's a pretty easy number to
355:56 hit revenue-wise, I think, if you know what you're doing. But profit-wise is a different story. So,
356:00 all this to say, you know, I I do this sort of thing professionally. I generate revenue outcomes
356:04 and profit outcomes professionally for businesses at this point. Let me run you guys through at
356:08 least at a high level what I know and what you guys can use to make some money with vibe coding.
356:12 So, the big thing I want you guys to know is over the course of the next, you know, 5, 10, 20 years,
356:17 um, software will no longer be the moat. So back in the day, right, 30, 40 years ago, if you were
356:22 a cool startup and you were working on some new computer system, okay, and you were smarter than,
356:28 you know, your competitors and you spent more time on it than competitors, you might have had like
356:32 a small edge and maybe with that small edge, you would have carved out like an operating system or
356:37 something like that. And maybe potentially you would have called that Windows OS and then you
356:42 would have sold that at scale to people and that's how you would have made your money. So if you
356:45 think about it like Microsoft and Windows, Windows uh uh was like software mode, software as a mode.
356:51 Same thing with like the Apple brand of computers. Same thing with like I don't know applications
356:55 afterwards like Photoshop and like various databases and stuff like that. Businesses that
357:00 were built entirely off of software made sense like 30 or 40 years ago because software back then
357:05 was very difficult to make. Okay. Well, nowadays software is very easy to make as hopefully I've
357:10 just demonstrated here over the course of the last six or seven hours or however long this
357:13 damn course ended up being. So, we've transitioned pretty heavily. Unfortunately, a lot of people are
357:18 still stuck in that old school world where they think, okay, that they're going to put together
357:22 this incredible software solution that nobody else in the market can do because they're smart and
357:27 they're intelligent and they're they're visionary, they're a forward thinker. The probability that
357:31 you do that is extremely low. It's extremely low. Not just because, you know, nobody's as special as
357:37 we think we are, but uh because there are soon to be 100 million times as many software engineers in
357:44 the form of AI agents than there ever would have been human beings. And so moes are no longer made
357:51 through software. Your edge in the market is no longer in the cool algorithm that you come up with
357:56 or whatever the heck. Okay. where the moat is is in distribution, which is fundamentally different.
358:05 And rather than play by the software mode playbook like everybody in their mom is doing right now,
358:10 um I encourage you to play by the distribution mode playbook. Hypothetically, why do you
358:15 think Netflix is still Netflix in a world where literally anybody could just tell their agent,
358:21 hey, here's Netflix.com. can you go and recreate everything about it and then I don't know you
358:27 know host the the servers and set up databases and set up all the infrastructure and then like
358:31 have a little login page everything like that the reason why Netflix is not broke you know today is
358:37 because Netflix contains within it distribution it contains a collection of clients vendors
358:45 relationships their staff their team their culture and so on and so on and so forth and these are
358:51 things that an AI agent and until they, you know, hook it up to the cloning vats and start pumping
358:57 out clients, vendors and and staff members, um, cannot currently do or reproduce. And so software,
359:05 which used to be like the golden goose, right, has basically been replaced almost completely
359:12 with distribution. Okay? And in a world where anybody could build any software, the only thing
359:18 that makes your software different from somebody else's software are the customers essentially the
359:23 vendors, the relationships, and the staff on your team um that manage it. Anybody in 2026,
359:29 2027 and beyond with a couple of ideas, a high degree of agency, which just means your ability to
359:35 like enact your will on the world, go out and do things, and a very small budget, just a few bucks,
359:39 literally 15, 20 bucks, can now build whatever the heck they want. the whole moat, the whole
359:44 edge is just your ability to actually reach and then retain people within an ecosystem. And if you
359:49 can do that, right, and if you can focus your time and energy accordingly, then you can make a lot
359:53 of money. But if you're stuck in the software days, then you're just spinning your tires,
359:56 man. The whole world's up and moved on and you don't even know it yet. Hypothetically speaking,
360:00 I want to pretend right now that um you know, we we we got a little clock here, and this is a
360:05 terrible drawing of a clock, but you know, bear with me. Just pretend that this whole thing is,
360:10 you know, a 60-second um um hand. Imagine that the entire life cycle of this vibe coded business that
360:17 you are about to start is this hand. Okay? And it traverses a whole 60-second length. Here is how
360:23 much I'd recommend that you actually spend on the vibe coding part. Okay? Over the full 60-second
360:30 life of your business, I would recommend you spend maybe 3 or 4 seconds on the actual building. Let
360:39 me make this a little smaller so we can see it better. Everything else, okay, literally the
360:46 rest of all of your time, my recommendation would be to spend it not on building, not on tweaking,
360:53 not on making your server infrastructure better, not on doing whatever the hell. My recommendation
360:58 would be to spend it on marketing. And this isn't a joke. If you spend 3 seconds or 12th or 5% on
361:08 building, you should spend the other 1920ths or 95% on the marketing. I don't know if you guys
361:18 have been in like the the build and public space on X. I used to be uh uh you know following that
361:23 fairly frequently because it was just interesting to me how people would share their revenues and
361:27 talk about the apps they were building. And back then they said you should spend at least as much
361:29 time building as you spend marketing. You should spend at least as much time marketing as you do
361:33 building. And I was like okay so 50/50. Um that was like four or five years ago. That no longer
361:38 applies. You need to spend like 19 to 20 times as much time marketing than building cuz anybody
361:43 could do the building. The building is literally just like your entry ticket to get onto the ride.
361:48 The whole ride itself is your poorly spelled marketing. So without marketing and sales,
361:54 to be clear, you have no product. You may think you have a product, but it's not a product. It's
361:59 just a hobby because without customers, you don't have any sort of business. You need
362:04 revenue and so on and so forth. There are also some additional benefits to having um customers
362:09 that go far beyond the money that they pay you. If you have customers, what you get is you get
362:14 faster iteration because you're listening now to real market feedback. You're not listening to like
362:19 your own opinions and your assumptions, which is what most builders will do. Most builders are like
362:24 heavily biased. I mean, who the hell builds software products anyway? For the most part,
362:27 giant nerds, okay? Myself included. I don't know what the average human being that uses my product
362:33 actually wants or thinks. So, everything that I'm doing is just assuming. I'm using my own opinions
362:38 essentially and I'm hoping that my opinions are correct because I possess a strong level
362:41 of empathy or whatever the hell. But the reality is most of the time I'm wrong. You know, it's like
362:46 a ven diagram. You know, maybe like if this is my opinions, maybe only like 50% of my oh my god,
362:53 I really need to I'm writing like a doctor. Um only like 50% of my opinions are actual
363:00 reality. And so the only part of like this ven diagram that I'm actually moving the needle for
363:05 and like building features into my app that actually make sense, okay, are over here. But
363:09 like the other 90% is all [ __ ] you know? It's all like uh I'm just wrong. So why would you even
363:14 like worry about your opinions? Instead, focus off reality and ground truth. The only way you can get
363:21 reality and ground truth is getting customers. The ideal is sufficient number of customers.
363:26 so many so that you could start averaging out their opinions and beliefs and desires
363:29 and needs and so on and so forth and then you just start designing for them. So rather than
363:33 letting your own assumptions build the product, use customer requirements, use customer needs and
363:37 actually do like customer surveys. Launch your vibecoded app today. You know, hypothetically,
363:43 you've seen how easy it is to do. You know, I can build one of these in just an hour or
363:46 two. Okay? And then contact 20 people and have all of them use your app for free and then tell you,
363:51 hey, I liked this. I didn't like that. Hey, I thought this could have been better. Hey, this
363:54 didn't really solve my need. Hey, I wish it did this. I wish it did that. Take all that feedback
363:58 and then use it to design the next version of your app because it's not the first version of
364:01 your app that's going to make you any money. It's like the 20th version of your app that's going to
364:04 make you money. In addition, because customers and distribution is really the moat, your whole focus
364:09 should be on maximizing the customer experience at every step. It should not be on making the nicest,
364:14 sexiest, most polished app. And I know this is kind of annoying cuz I did just spend the last
364:18 part of, you know, five or six hours hopefully teaching you guys how to do this and how to like
364:23 make a really good product. But in reality, the product, as we've seen, is really only like 5% of
364:27 the whole pie now. So, focus instead on acquiring as much distribution as quickly as possible. I'm
364:32 going to run through some specific ways on how to do that. And then once you have that distribution,
364:36 um try and satisfy the needs of your customer. And then generally and consistently iterate on
364:40 the product. Okay. So, highle advice aside, how do you actually do the big thing that I
364:46 think a lot of people are wondering? How do you price your product? Well, what I want to do next
364:52 is talk about essentially my core principle for pricing. And this is a core principle that I've
364:56 used to generate tens of millions of dollars in revenue across a variety of businesses, small
365:00 to mid-size businesses, my own agencies, digital marketing businesses, uh a couple multi-billion
365:05 dollar portfolio companies. And um this is something that I just I I continuously return
365:09 to you because it's the easiest and simplest way to price. So, it's called VBP or valuebased
365:18 pricing. And so in value based pricing, what you do is you price based off the value that
365:23 your app delivers, not on your costs or your competitor's pricing. You know, and I think a
365:29 lot of people are like, well, I have to anchor to my competitor's price, don't I? And to me, I say
365:32 I mean like obviously your competitor's price is a factor and people are going to be doing some price
365:36 shopping. But if you focus on the value instead of at what your competitors price rather than running
365:41 uh down to the very bottom and it being like a race down below like a lot of these freelance
365:45 platforms and stuff where somebody bids nine, another bids eight, another bid seven till you're
365:49 at freaking zero. What we do is we just establish how tremendously valuable a product is and then
365:54 charge such a vanishingly small percentage of said value that the customers are bought in regardless.
366:00 I mean to them it's like a it's it's a pittance. And I know this because I also purchase software.
366:04 um what ultimately a lot of B2B software users are looking for is something that maximizes their
366:09 return on investment and minimizes the friction involved in making the purchase decision. So let
366:13 me explain what I mean by all this. There are two types of value that you can produce at least in a
366:17 B2B environment. In a B2C environment you have additional types of value. Those types of value
366:21 are nonmaterial and so it will not be discussed. You have the ability to directly reduce their
366:27 expenses which is the money that your product will save a customer if they use you. And then
366:32 you also have the ability to significantly increase their revenue in opportunity cost,
366:38 which is also termed the additional money customers can now earn because they use your
366:42 product. I think direct expense savings are pretty simple, right? If I have product X and product X
366:48 currently costs the user $100 a month and I say, hey, I just built product Y. Product Y only costs
366:55 $5 a month. What do we have there? What I've done is, if you think about it, I've saved the customer
367:01 $95 every month. And so the direct expense savings are 95 bucks. Easy. Now, an opportunity cost. Now,
367:12 opportunity cost is a little bit different. Instead of focusing specifically on what the
367:15 delta between, you know, their old thing and then their new thing is, what we focus on instead is
367:21 how much time do they save and what is the cost of that time. So I'll give you a brief
367:30 little example. Let's say hypothetically you are currently a salesperson. You work at big
367:36 company. Big company pays you on average about $100 per hour. Right now, as part of your day,
367:44 you do some [ __ ] admin task. That admin task involves filling out some CRM or whatever. And
367:50 on average, every single day, you have to spend 2 hours doing this. Okay? So, they're paying you
367:57 $100 an hour. You're doing an admin task that is worth 2 hours. If you hypothetically could build a
368:03 software solution that enable this salesperson to spend zero minutes doing this admin task,
368:08 how much money are you saving this salesperson right off the bat? You're saving this company
368:13 right off the bat. You're saving $2* $100 an hour or $200 an hour. That is your direct expense. But
368:23 if you think about it, what do sales people do? Salespeople are tasked with increasing the revenue
368:29 of the business that they work in. Hypothetically, let's say if instead of focusing on admin time,
368:36 they then focus on sales, aka calling people or whatever. in those two hours they could contact
368:43 50 people and if in one in 50 people end up purchasing a small product or something like
368:48 that okay which is their conversion rate and if the average cost of that product is let's say
368:53 uh I don't know $500 then by saving 2 hours a day not only are you adding $200 sorry $200 an hour
369:03 I meant $200 not only you adding $200 back to the core business that you built the software platform
369:08 for you're also adding If you think about it, an additional $500 in revenue. So this is minus
369:15 $200 of expense. Okay? And this is plus $500 in revenue. And if you think about the total
369:25 amount now that this software product is saving or generating the business, we have come to
369:32 $700 in value and that's per day. Okay. So the expense portion is about saving money whereas
369:40 the revenue portion is about reallocating the time that your software solution is now saved to allow
369:45 a person at a business to focus on higher revenue things that actually produce for a company. And in
369:51 practice usually these expenses are much smaller than the total amount of opportunity cost aka
369:56 the revenue that you are unlocking. So you know how earlier we built a thumbnail generator? Well
370:00 here's a quick example of what that might look like. You have direct cost savings. Let's say
370:05 right now whatever system that they are using cost them $50 a thumbnail and they generate 20
370:10 thumbnails a month. That means that by switching over to nyx thumbnail company.co, also known as
370:16 thumbly, uh you'll save $1,000 a month. But when you take into account the time savings revenue,
370:22 okay, you move this 2 hours per thumbnail design period to 5 minutes. What you're doing is you're
370:28 saving 115 minutes. And hypothetically, let's say these 115 minutes times 20 are 2,300 minutes
370:36 a month. Let's say with this additional time, which works out to be approximately 40 hours,
370:42 this designer or something can actually make an additional $1,000 a month as well. Well,
370:46 now the total value created is $2,000 a month. What we're doing as somebody that is developing
370:51 a thumbnail product is we're pricing at a very small percentage of the total value we produce,
370:55 so maybe 10%. So, we charge 200 bucks a month. And then the customer ends up making 10 times as much
371:00 money as they spend with us for using our service. Now, obviously, this is going to be an average,
371:04 right? Every customer is going to be different. Some people are going to produce way more value
371:08 than your $2,000 a month estimate. Others are going to produce less value. But because you
371:12 can't price individually per every new customer that you onboard, you have to pick a specific
371:16 package price. What we've done now is we've basically used facts and logic to work out what
371:21 a strong value would be for a core product and then how much to charge for it instead of relying
371:27 on things like competitor analysis or worrying about what the dude in the next cubicle over is
371:32 doing. And so this is a much more sustainable and higher ROI way of pricing. You're pricing based
371:36 off value. You're not pricing based off of what everybody else is doing. This young viewers is
371:41 how you zigg when everybody else zags. Once you've established some sort of price for your product,
371:46 my recommendation is I actually establish this as my top price. So, for instance,
371:51 um let's say I kind of screwed up the uh writing here, but let's say this is like your top tier,
371:56 this is your mid tier, and this is your entry tier. You know how there's typically multiple
372:00 subscription tiers for a product, right? Assuming you're doing a monthly thing. What you do is you
372:03 take the top and then you set that one at uh you know, let's say 200 bucks a month. And what you
372:08 do is you set your middle at approximately half of that and you set that at about 100 bucks a month.
372:13 but you uh reduce the ROI to compensate. So in this case, you know, previously I'm offering a
372:17 10x ROI on my top. Well, now I'm offering an 8x ROI on my mid and then a 6x ROI on my entry. And
372:23 so in this way, you have like a reasonable product differentiation. You have a reasonable spread of
372:27 values. And this is enough to get you started before, you know, you can get enough customers,
372:30 you can actually run like strong analytics to determine whether or not people would actually
372:34 prefer a $37 a month product or a $58 a month product or whatever. And that's honestly all there
372:39 is to it. To make a long story short, what I do anytime I'm pricing an app, uh, Pel, an automation
372:44 service, a back-end tool, even like a big business deal, back when I was um, operating a content
372:48 writing agency and we were trying to work out how much to price our product, uh, we do it all based
372:52 off of value pricing, which is determining how much value our product has to the user to begin
372:57 with, an expense, an opportunity cost, and then just charging a small percentage of that. And
373:01 that usually ends up being somewhere between 10 to 20% of the total ROI. And as a business owner, I'm
373:06 thinking like, hey, I could put my money in the S&P 500, I could make 8% a year, or I could give
373:10 my money to NYX Co. and then I'd make a,000% on my initial investment. What am I going to do with my
373:16 money when presented that choice? Obviously, I'm going to give it to Nyx Co. right now. Uh, whether
373:20 or not somebody chooses to invest in you isn't just a product of this math. It's also how much
373:24 they believe the math, and that's another part of marketing. But I'll leave that for another day.
373:28 Hopefully, at least now you guys understand how to price set products. But that takes us to the next
373:33 big thing, okay? which is well there's pricing the product but how do I actually get my product out
373:38 there okay how do I actually market this amazing thing that I have developed well there are three
373:45 major ways the first is outbound a lot of people shy away from outbound but outbound was the very
373:50 first thing that I did when I started my first business my first real business about 10 years ago
373:54 I went door to door literally knocking on business doors coming in trying to shake their hands and
373:59 then sell them on my little marketing package it's very difficult but this is ultimately what works
374:04 So in this case, you go directly to people who need your product. You can consider this like a
374:08 sniper rifle approach. The two most popular methods right now are cold email, which is
374:12 where you actually craft an email, usually using a template that appears to be personalized onetoone
374:18 communication between you and the person that's reading. And then you say, "Hey Pete, I love what
374:22 you're doing over at XYZ Business. I think right now you guys are currently spending all this money
374:26 on the software, and I can save that for you with XYZ product. I would be happy to give this to you
374:31 for like a major discount because you're going to be one of my first five uh you know signups. I've
374:35 also attached a video here that runs through how to do X Y and Z. Um let me know if you have any
374:39 questions. If I can help you out at all would be happy to. Okay. And so in this way you're reaching
374:43 out directly to them. This is you. This is them and this is you bridging that gap. That's why it's
374:50 called outbound. The other main way to do this is through cold DMs. And typically you do this
374:54 on B2B platforms like LinkedIn. Cold DMs stands for direct messages. It's just the same thing
374:59 as cold email. It's just instead of using like an email inbox, which tends to be the the highway to
375:04 the soul, um we're instead using like a LinkedIn message box or like an Instagram message box,
375:08 but it's the exact same idea. Some caveats here. This works really well for B2B products, but it is
375:14 pretty difficult for consumer products, aka B2C products, since most of the lead sources where
375:19 you're going to scrape this information do tend to be B2B. Like for instance, if you think about it,
375:23 LinkedIn is entirely a commercial platform. If you sign up to LinkedIn, odds are you're signing
375:27 up for employment or business purposes. So, you can feel pretty safe that most of the people that
375:31 you're scraping on LinkedIn, you're doing so because it is a B2B sort of transaction. Hey,
375:35 I can help you at XC Corp. Hey, I saw you're employed at whatever position. I think I can
375:38 assist you with that and so on and so forth. If they're not on LinkedIn, crap gets a lot harder,
375:43 right? So, for the most part, anytime I sell B2B, I start with Outbound. The other big benefit to
375:47 outbound is it's just really fast. It is way faster than any of the other methods on the
375:50 list. It's also way harder, right? you sort of have to put your freaking ego on the line. And
375:55 um I can't tell you how many times I got thrown out of businesses when I was knocking on doors.
375:59 Security racing after me being like, "Get the hell out of this plaza." Uh but you know,
376:03 it it worked and it was what enabled me to make my first uh probably $15 $200,000. That said,
376:07 this is not the only thing that you can do. It is not the only way. There are a variety of others.
376:12 The second is inbound, which I think a lot more people here are probably familiar with. Inbound,
376:17 if you kind of think about it logically, is kind of like what I'm doing right now. What
376:21 I'm doing is I'm creating very valuable content. I'm building a very strong and large audience of
376:26 people that enjoy consuming my content. And then what I'll do is I'll direct a small percentage of
376:30 you guys to some paid products so that you guys sign up to my service or whatever. The issue with
376:34 inbound, despite the fact that, you know, if I'm here and then they're here, despite the fact that
376:41 they're now coming to you, is it's a lot slower. It takes a lot longer to build. Okay. And what a
376:46 lot of people don't realize is they'll watch some vibecoded course or whatever and then be like,
376:50 I'm going to make my own app business. It's going to be awesome. And then they start making content
376:53 on it. What they don't realize is like when you make content um on the on the wider internet like
376:58 on YouTube or LinkedIn or Instagram or whatever, what you're basically doing is you're like in a
377:02 sea of a billion people and then you're given a megaphone. And then you're like,
377:06 "Okay, I have a megaphone. This is awesome." And then what you don't realize is every other person
377:10 also has a megaphone. And then the big people that are pretty established have megaphones that are
377:14 way bigger than you. And then the small people like yourself have these tiny little things that
377:17 barely produce any noise uh whatsoever. And so growth on inbound is extraordinarily difficult
377:23 as a beginner unless you have some pre-established success or pre-established wins. And most people
377:28 that are starting these sorts of things that immediately turn to I'm going to post one thread
377:31 on Instagram every day for the next year. Uh they they don't understand this. And so what
377:35 ends up happening with a lot of inbound is because it takes so much longer to build and people are so
377:41 unprepared for this, they end up just screeching into the void, never achieving anything. and then
377:45 quitting before they actually build up the amount of momentum required to succeed. If I could graph
377:50 sort of like the differences between inbound and outbound. And I love graphing stuff. So,
377:54 in case you've watched any of my other videos, get ready for a freaking Nyxive graph. Basically,
377:59 this is the amount of time that it takes to see any sort of win. And then this is the amount
378:03 of money that it takes. Okay? And I'm going to I'm going to pretend that blue here is inbound.
378:08 And I'm going to pretend that orange here is outbound. And you guys are going to see why
378:11 I prefer outbound in terms of the total amount of money you could make. Um, if you use inbound,
378:16 okay, what happens is you start at this time step one and then you make no money for a long time
378:21 and then all of a sudden your brand picks up and then you make a ton of money. With outbound, it's
378:26 basically the exact opposite because every single time you send a piece of outreach, it consumes a
378:32 little bit of your time. What ends up happening is you usually have some success initially and then
378:37 you start tapering out or plateauing and hitting a ceiling. And so if you think about it logically,
378:42 both of these have major trade-offs, right? But with outbound, what happens is you make money much
378:46 much faster. You know, this might be 1 month. This over here might be one year. And so with inbound,
378:52 what we've done is we've sacrificed all our money in the first year for money after year
378:55 number one. And with outbound, what we've done is we've sacrificed money after year 1 for money
378:59 before year 1. Um in reality things are never fully black or white and so the recommendation
379:04 is usually to do some sort of blended take of both where you know at the beginning you start mostly
379:10 with outbound. Okay. And then as time goes on you shift more to inbound which allows you to generate
379:16 revenue quickly without also tapering out. Um that said there are a variety of different ways you
379:20 could do this sort of thing. That's where business programs like u mine maker school and so on and
379:23 so forth come into play. So I'll I'll leave that with you and you guys could do whatever you want
379:27 strategically there. The third major way that you could market as somebody that develops and builds
379:30 products is instead of trying to build your own distribution via you know outbound like we talked
379:36 about earlier or inbound where people come to you. What you do is you just take somebody else okay
379:43 somebody like Nick Sarif and you say yo Nick can you market my product for me and then I'll just
379:48 pay you 30%. And then what happens is Nick, you know, can use a combination of both inbound and
379:54 outbound methods to do that marketing for you. But the idea is because he's already developed sort of
379:59 pre-existing distribution, it's way faster. And uh you know, all you're really doing is you're paying
380:04 a percentage. So it's more predictable for you. Maybe it won't necessarily be cheaper, but it's
380:08 probably cheaper than you initially buying a bunch of software platforms, getting a bunch of cold
380:12 emails, uh getting a a beautiful studio and all that stuff. So, the whole idea is you just partner
380:17 with someone who has pre-established distribution and then you make it a win-win for them. You're
380:20 like, "Hey, man. This software does exactly what the heck you really like to do. Uh, I think I can
380:25 really help your viewers and stuff like that as well." And rather than you having to build a whole
380:28 new product from scratch, why don't you just use my product and I'll just pay you a percentage. You
380:32 like my product, right? Yeah. Okay. Awesome. So, it's a win-winwin. As mentioned, it can be inbound
380:36 or outbound affiliate, though. Inbound tends to be the most popular one because it's more scalable.
380:40 And then yeah, you're just monetizing somebody else's audience or work, which allows you to
380:43 like quickly jump cut in uh basically return for some predictable outflow of your money. Okay, so
380:50 hopefully I've now showed you guys how to not only price but also package together multiple tiers and
380:55 then also get started with the marketing of your product. My recommendation to be clear is to start
380:59 with some form of outbound laser or sniper rifle target specific people whose needs you are solving
381:07 and handling with your product. And once you have a solid base set up, maybe 10, 20, $30,000 a month
381:12 in recurring revenue, then you can transition over to maybe building a brand um um you know,
381:17 doing the whole megaphone analogy that in reality tends to be the best of both worlds. Um affiliate
381:22 is also open to you at any level of the stack. So whether you guys are early on, whether you
381:26 guys are a little later on, I do highly recommend looking for those sorts of partnerships and then
381:30 finding opportunities to, you know, plant your seed and have other people water them from here
381:34 on out. Obviously, I can't cover every possible business permutation. Some people are going to do
381:38 like high ticket SAS style stuff where you have to sit down and do demos. It's going to be more
381:42 sales. Other people are going to do low ticket SAS stuff where basically people guide themselves
381:46 through their onboarding checklist and stuff. Um, you know, that tends to be more marketing. But
381:50 hopefully this at least tells you guys a little bit about where the market is going and then
381:54 how to practically take what I'm talking about here to improve the quality of your guys' lives,
381:58 businesses, and so on and so forth. Okay, that was a hell of a course. I had a lot of fun putting
382:02 all that together. If you guys have made it to the end, y'all are real ones. I have uh one quick ask,
382:07 two, I suppose. The first is if you guys like this sort of thing and you guys are curious about how
382:11 to monetize your own vibe coding business, definitely check out Maker School. It's my
382:15 day-to-day accountability program where I actually guarantee you your first paying customer for an
382:19 AI or automation business in 90 days. If you don't get customer number one in 90 days, I I refund you
382:25 in full. So, it's a full 100% guarantee. Inside of Maker School, you'll learn how to put together
382:29 really classy and clever offers, sort of like the offer I'm using to get you into Maker School,
382:34 as well as do things like set up outbound campaigns, uh, productize your business, and
382:38 then eventually scale to inbound, like I talked about here. Additionally, I'd love it if you
382:41 could check out my podcast with Mr. Jack Roberts. We both talk on AI automation. It's a blend of
382:46 news and then us just goofing around, showing off our boulder shoulders. So, no pressure.
382:51 Do whatever the heck you want. Lastly, you'll find everything that you need down below in the
382:54 project description. And then yeah, if you really like this sort of thing, then please subscribe.
382:57 Helps out my channel. Comment and engage with the video. And I'll catch all y'all on the next one.
$
VIBE CODING FULL COURSE: Gemini 3.1 + Antigravity (6 Hrs)
[AI agents and automation][content creation and YouTube][developer tools and coding][productivity and workflows]
// chapters
// description
🔥 Join Maker School & get customer #1 guaranteed: https://skool.com/makerschool/about
💎 All course files: https://drive.google.com/drive/folders/1eGTwguPbANKzhtA7EFq4YSLsZnqA_ZCH?usp=drive_link
🎙️ Listen to my silly podcast: www.youtube.com/@stackedpod
📚 More free courses
→ Claude Code (4hr full course): https://www.youtube.com/watch?v=QoQBzR1NIqI
→ Agentic Workflows (6hr full course): https://www.youtube.com/watch?v=MxyRjL7NG18
→ N8N (6hr full course, 890K+ views): https://www.youtube.com/watc