The Wisdom Wall

“being an entrepreneur is Uh, a safer job than actually having a job. And I, I really, I mean, obviously you need to have like some good foundations, but I do think there's some truth to that because I don't feel at risk of losing income right now because I know that I could adapt in so many ways.”

“I actually learned how to, like, fully integrate multiple APIs into an app before I even knew what API stands for, because you can, you don't need to know with a, uh, with, with the AI tools.”

“I think you have, you should pick a stack and you should stick with it. Um, I think moving from hot tool to hot tool is actually not the right strategy.”

“all of these companies are deciding that this is kind of the correct interface to interact with AI agents.”

“This is how I normally set up automations. People sometimes want to create an automation before they do it. It's just like do it once and then tell the agent to do that every time on this day. And that's a kind of a good workflow.”

“The number one thing that you can do, uh, in a company right now, and we're talking to a lot of companies that are trying to implement AI, is just collect as many good examples as possible. Um, this allows your agents to have examples that they can reference.”

“what I've noticed, you know, and being in San Francisco, uh, I've noticed that the people who have been, like, really successful creating startups are people who just, like, want to experiment and tinker, and they don't have so many people who are, like, type A, want to get an immediate benefit after 30 minutes of…”

“And so, in terms of, like, a, in terms of business ideas, some of the best business ideas might literally come from collecting good examples. I mean, look at this example, right? Like, AI never gave me good hooks until I created this little hooks database, so whenever I'm scrolling, like, if I find a hook that I like,…”

“part of your job as kind of the quarterback of the AI agent with access to tools is you need to decide what tools it has or hasn't. The more tools you give it access to without corresponding instructions, the more it's just going to get confused, and it might actually make your life harder.”

“I'm not a huge fan of like note taking apps where you have a lot of creative freedom, uh, because, uh, anytime you try and collaborate, uh, things become unclear. Notion, there's just too many options and bells and whistles in my opinion”

“And I think, I think most of the leverage, most of the leverage from these tools comes from doing things When they're janky and bad, understanding that it's not going to be janky and bad, right?”

“I think of AI coding like Legos, right? You're looking for the pieces that you need to like put together, and APIs are kind of like finding instruction manuals, you know, like, and you need to give that to Cursor because Cursor doesn't have an inherent understanding of how these APIs work. All APIs have different, um,…”

“I just said, I, I, it's basically instructions, examples, token. That's what I do when it's an API. You give an example, uh, or you give instructions, like I want you to create an image generator. And because Claude is probably trained on a bunch of GitHub repos, it'll know what an AI image creator, it might even…”

“as soon as it's one prompt, then everyone's going to do it and you're going to have a lot more competition. And so you always want to be up against the edge.”

“So through this process, you do kind of learn how to code, but it's just in an, in the opposite way. You, you build the thing and then you learn about it instead of learning about it, then building the thing, which, which makes it more fun.”

“what's cool about this is since we're using iOS, you can actually save things to the files, like you have your files thing on your phone, and so you can save things locally, so you don't have to set up Firebase, which takes forever and leads to a lot of errors.”

“In any of these apps, the less context you have in, the better, unless it's relevant. And, um, if you want to iterate on it, I recommend forking, because if you have all of that context in here, it's just going to start performing worse.”

“Because yes, you can, as a creator, I can outsource someone to build apps for me, But the loop is so slow. I'm talking to other creators who do that, and it's like multiple months before basic features are created. Features that I have literally released to my community the same day I have the idea. And so it's a, it's…”

“it's very, very, very useful to come in with a full plan in mind. Expect to get stuck a lot more if you come into diddle-daddle, and I, like, if you're just like, oh, let's add features as we go. It is fun. It will, you'll have fun, and you can just treat it like a for fun type thing, but don't expect to, like, have an…”

“the first prompts are critical. So I would put most of your attention. And then once you get into the flow and you have the base set up, It's a lot easier to make changes to the app, and it becomes more fun once you get to that point, for sure.”

“I actually, I suggest pasting the errors in in the beginning, being like, okay, don't generate any code. Tell me what's the problem. And that, you'll increase the, your learning rate significantly if you actually try and learn along the way.”

“Even if you don't have the core functionality, now you can just make the pretty parts and you can pitch people and send them V zero links. Like, Hey, imagine this app, like a lot of, you know, if you're working at a company and you're like, Hey, I think we should add this feature. You no longer need to send them an…”

“doing it when it's hard is better because by the time the creating what we're doing now gets easy, the people who start now are going to be creating even better sites by then. That's right. Because there's a group of people always pushing the edges of all these new things. Right now there's not very many people pushing…”

“after, I actually, yeah, I get, I start re, like, reiterating things. A lot more once you get into these failure loops. Um, and it's really good. The cadence he has right now where it's like he tries four or five times, he scraps the changes, starts again from like a slightly different strategy. And like, yeah, every…”

“if you have the grit to push through the errors, because there's a lot of errors once you start dealing with databases, but usually Claude will figure it out, and the more times you do it, the better you will be at, like, fixing those errors, and you get better at problem solving, just like anything, and you can create…”

“I like to make sure I give it, I tell it the purpose because it will actually use that in the prompt and it might add to its creativity.”

“I call it composing code. Like, you're, you're kind of, um, You're just kind of guiding it. You're telling it what you want, and you know what things are feasible and what, what types of things aren't feasible the more you do it.”

“We can go to any website you think is cool and literally screenshot it and then describe like what you should do with it. And you can in one minute have a working prototype for it. It's not a full app because it's not storing any of the data, but it is a prototype.”

“If you don't know how to code, this is a good way to do it is to actually create it manually and then say, I want to automate this process and have that whole process happen in the background.”

“Error messages are good. Blank screens are bad, right? This is what should have popped up in the dev log, right? We should see the, the errors right here, and it actually knows what to do, um, and we can actually just see how it reacts.”

“Perplexity will actually find the latest documentation. It's just going to give better instructions. We can feed it to cursor, which will allow it to make better decisions, write better code.”

“And if we just use, like, Python and we didn't care about how good it looks, it would be much easier to create. Because Python is very straightforward and AI is very good at creating it.”

“Like, if you know how to operate in a terminal, like, if you know what the different commands are, then I would say maybe not. Like, maybe you would want to do it a different way. Uh, for example, I work with Anj, who's, uh, like, senior developer level, and he doesn't do it because often he'll run different commands…”

“I can't stress enough how important this step is for if you're just beginning. I promise you, if you forget to do this, you will waste four hours. If you get deep into a project and you don't save, you will ruin your time. It will ruin a night for you. I guarantee it.”

“describe what's going on first, then tell it specifically what to do. You don't want to leave it up to chance.”

“You get in a deeper flow state when you use your voice.”

“sometimes the naming can become an issue. Not saying that's the issue now, but just kind of going through some common problems I've run into.”

“If you're using cursor, hit save all instead of accept all. Accept all is not reversible. You have to ask the AI to reverse it instead of just being able to, like, hit reject.”