The Exchanges

Q No, it makes complete sense. I, you know, maybe this is too in the weeds, but when you're building something, how do you think about using Supabase versus Convex? Like they're both such great plat, you know, platform. So how do you, how do you know what to pick?

A Yeah. It definitely is going to get in the weeds because generally they're both great at what they do. Now, Convex wins when it comes to real time stuff, right? So if you wanted to build a chat application or something where real time, like you need some sort of real time notification or you're building some sort of like collaborative tool and you need people to see what other people are doing, I think Convex wins. Not that Supabase can't do it, but Convex by default Is, uh, real time. So anything you do with Convex, you get the data real time, which is great. But there are people, and this might be too technical, who might need a Postgres database, right? That, that's the main database that Supabase offers, and they're the best at that. No one does Postgres the way Supabase does, in terms of DX, developer experience especially, right? So it really depends on the application the user's building, The best way I would, I would say for someone who might not be as technical as your average developer is, I would ask an AI model. I'd go on ChatGPT Cloud and be like, this is what I'm trying to build, and I, I know there are these two backend as a services, which one is better for my specific use case? There might be one where Convex is better, and there might be one where Supabase is better, but generally speaking, both are great solutions.

AI assessment note: “Convex wins when it comes to real time stuff... who might need a Postgres database”

Q So slash goal is also trending at the moment. You know, is slash goal a loop? Like, how should people think about slash goal and a loop?

A They're all the same thing. They have different names, like slash goal. I know on cursor, I think it's slash loop, and then on another tool, it's slash whatever. They're all the same thing, and basically how All of them work on a high level is you, you, you know, you type in slash goal and then you give it some prompt, right? Like you give it Some prompt, and then you can also, like, attach some, you know, markdown file, and you tell it, like, yeah, build this entire thing out. Don't stop until you're done. Don't make any mistakes. Again, these are cool, but the two issues are, number one, uh, they burn a lot of tokens, right? Um, and if you are not, like, this shouldn't even be a thought if you're not on the 200 dollar a month plan. Like, not a thought. Like, if you're on the 20 dollar, or I think there's a hundred dollar a month plan, You shouldn't even think about this, right? Because it's just going to burn your token usage. Um, number two, you think your plan is good, but it's not. Because it's impossible for you as a human to contextualize every single detail about the product that you want, um, in one document, right? Things evolve, trends change, um, you know, one day liquid glass is cool, the next day we're changing how liquid we want it. Like, it's very impossible for you to fill, like, Uh, your thoughts and exactly how you want the product to be one in one, in one do…

AI assessment note: “They're all the same thing. They have different names, like slash goal.”

Q Yeah. What is the five percent of time I should care about it?

A Proprietary information that like maybe specific to your company or some methodology that is specific to you, that has to be referenced in every single conversation. Cause the annoying part with an agent on MD file is every time you go back and forth with the agent, it's added in the context, right? The cool thing about skills, and I'm going to talk about skills in a second, the way skills are designed, the skills are Used in a way that's called progressive disclosure. Meaning when you have a skill file, the entire thing is an additive context. It's just the title and the description. So the agent has the title and description in the context. And when you, let's say you have a notion report skill, right? And you tell your agent, Hey, I want you to create a notion report. It's then going to check its context and be like, Oh, I have this skill. Let me check out the entire document. So it's not in the context. What's in the context is the name and the description, but that's enough for the agent to be like, oh, this is a skill I need. Let me go use it, which is fantastic. I'm a skills maxi. And I'm going to show later in the episode, like how you craft the perfect skills, but with agent.md and claw.md files, it's context being added at every turn. Right? So let's say you have like a thousand line file claw.md and let's say that's like 7000 tokens. You're spending 7000 tokens on ev…

AI assessment note: “Proprietary information that like maybe specific to your company or some methodology”

Q It's so frustrating too, right? Cause you're like, you give it a task and it seems like so binary, like right or wrong. And then when you tell it, Hey, like, why didn't you look at the trust pilot? Why didn't you see if they've raised money? You're absolutely right. It's like, what?

A And, and the thing is, the reason why this is the case is the models, Um, actually don't think they're predictors of tokens, right? So when you give it English, when I give it English, it maps it on this vector graph, and then it looks for the closest resemblance, and it says, this is the response, right? So when you say, what is the capital of France? It maps it again on this graph, and it says, oh, Paris is pretty close by, then it gives you Paris. It has no, it doesn't think, it doesn't understand. It feels like it understands. It feels like it thinks. Heck, it even feels like it has emotion. That's because it's been trained on so much data. But it actually does not know how to think. And this is where a lot of people will be frustrated, um, with like, why is it not understanding me? You have to walk with it. So I told it, okay, this is how you research. And it's like, okay, it researches. And guess what? This is part of the context. And we're like, okay, now that you're done researching, when it's a good company, these are the qualities you look for. And then when it's really good, send me an email. And then once we had a successful run and we did it again and again, then I converted it to a skill. The reason being is a lot of people create the skills themselves, or I mean, they'll use the AI to create the skill, but it doesn't have the context on what a successful run look…

AI assessment note: “the reason why this is the case is the models, Um, actually don't think”

Q Yeah, it makes complete sense. You're also, You're also going to use less tokens in the end, right? Cause you're going to, right?

A Yeah. Cause the thing is the better your plan, the better your input, the better the initial set of documents that you give the model, um, the, the better the outcome. And if the better the outcome, there's no back and forth, right? Most people will have a route loop running. It'll be a basic plan and it'll do what you told it to do, but you weren't specific. So now you're going back and then maybe you're running another loop or you're going back and doing all these changes, but If you get it done right, if you invest the time in the planning stage, I hundred percent believe you'll save a lot more money, and this will help you clear up a lot of ideas. So like, for example, this idea that we just had, this TikTok UGC farm, um, how do we want it set up? Do we want it to be flat with search? Do we want it to be client campaign assets? There's a lot of like these minute details that You're not thinking about, and because you're not thinking about it, you're allowing cloud code to make those assumptions for you, right? Which at the end, after it's burned through a ton of tokens, now you're going back to change, right? We can save so much headache if we do the proper planning from the beginning. And hopefully, um, people see value in this, um, ask user question tool. Make sure you specify it in your prompt. And hopefully, Greg, that, that made sense.

AI assessment note: “Yeah. Cause the thing is the better your plan... there's no back and forth”

Q No, it makes complete sense. I, you know, maybe this is too in the weeds, but when you're building something, how do you think about using Supabase versus Convex? Like they're both such great plat, you know, platform. So how do you, how do you know what to pick?

A Yeah. It definitely is going to get in the weeds because generally they're both great at what they do. Now, Convex wins when it comes to real time stuff, right? So if you wanted to build a chat application or something where real time, like you need some sort of real time notification or you're building some sort of like collaborative tool and you need people to see what other people are doing, I think Convex wins. Not that Supabase can't do it, but Convex by default Is, uh, real time. So anything you do with Convex, you get the data real time, which is great. But there are people, and this might be too technical, who might need a Postgres database, right? That, that's the main database that Supabase offers, and they're the best at that. No one does Postgres the way Supabase does, in terms of DX, developer experience especially, right? So it really depends on the application the user's building, The best way I would, I would say for someone who might not be as technical as your average developer is, I would ask an AI model. I'd go on ChatGPT Cloud and be like, this is what I'm trying to build, and I, I know there are these two backend as a services, which one is better for my specific use case? There might be one where Convex is better, and there might be one where Supabase is better, but generally speaking, both are great solutions.

AI assessment note: “Convex wins when it comes to real time stuff”

Q So slash goal is also trending at the moment. You know, is slash goal a loop? Like, how should people think about slash goal and a loop?

A They're all the same thing. They have different names, like slash goal. I know on cursor, I think it's slash loop, and then on another tool, it's slash whatever. They're all the same thing, and basically how All of them work on a high level is you, you, you know, you type in slash goal and then you give it some prompt, right? Like you give it Some prompt, and then you can also, like, attach some, you know, markdown file, and you tell it, like, yeah, build this entire thing out. Don't stop until you're done. Don't make any mistakes. Again, these are cool, but the two issues are, number one, uh, they burn a lot of tokens, right? Um, and if you are not, like, this shouldn't even be a thought if you're not on the 200 dollar a month plan. Like, not a thought. Like, if you're on the 20 dollar, or I think there's a hundred dollar a month plan, You shouldn't even think about this, right? Because it's just going to burn your token usage. Um, number two, you think your plan is good, but it's not. Because it's impossible for you as a human to contextualize every single detail about the product that you want, um, in one document, right? Things evolve, trends change, um, you know, one day liquid glass is cool, the next day we're changing how liquid we want it. Like, it's very impossible for you to fill, like, Uh, your thoughts and exactly how you want the product to be one in one, in one do…

AI assessment note: “They're all the same thing. They have different names, like slash goal.”

Q Um, what else do you want to leave people with? Or is this, this is the main point.

A Yeah. Like here's like the, we've got to a point where the models are good. The models are really good. The context matters plus the harness, right? So for example, um, there was this benchmark, although I'm not a hundred percent supporting it, that there was a difference between the quality of output Um, that cursor generated versus cloud code versus codex, right? Um, so what that tells me is that we've reached a point where the models are really, really good. They're probably going to get better. The next iteration is probably going to get better, but the harness and the tools that you surround it, the context that you give it is going to matter even more. And just like in everything in life, less is more. Right? Like, building up step by step, making it productive for you first, before you add the shiny new thing. Like, because I try out all these tools all the time, like, especially Paperclip. Paperclip blew up, and a lot of people have been talking about it, and it's fantastic. But I'm willing to bet if people took two weeks to build up to the version, because you can prompt OpenCloud to do all that stuff. If they built up their own version of Paperclip in two, three weeks, where, like, they're building things that they actually need, their productivity level will skyrocket through the roof.

AI assessment note: “the harness and the tools that you surround it, the context that you give it”

Q Um, what else do you want to leave people with? Or is this, this is the main point.

A Yeah. Like here's like the, we've got to a point where the models are good. The models are really good. The context matters plus the harness, right? So for example, um, there was this benchmark, although I'm not a hundred percent supporting it, that there was a difference between the quality of output Um, that cursor generated versus cloud code versus codex, right? Um, so what that tells me is that we've reached a point where the models are really, really good. They're probably going to get better. The next iteration is probably going to get better, but the harness and the tools that you surround it, the context that you give it is going to matter even more. And just like in everything in life, less is more. Right? Like, building up step by step, making it productive for you first, before you add the shiny new thing. Like, because I try out all these tools all the time, like, especially Paperclip. Paperclip blew up, and a lot of people have been talking about it, and it's fantastic. But I'm willing to bet if people took two weeks to build up to the version, because you can prompt OpenCloud to do all that stuff. If they built up their own version of Paperclip in two, three weeks, where, like, they're building things that they actually need, their productivity level will skyrocket through the roof.

AI assessment note: “the harness and the tools that you surround it, the context that you give”

Q Amen. Amen. Is there anything else people need to know? Like little tips and tricks? I notice, you know, you're not using the Mac terminal. You're using ghosty.

A Yes. Yes. So honestly, it's all preference, right? So like the terminal you use and all this stuff is all preference. Here's what I would say. Like, let's have a tips and tricks list. Tips and tricks. So First, I would say is, my goodness, spelling today. First, I would say is use the ask, what was the specific tool? I just want to make sure I don't forget. Ask user questions tool. Slept on. I don't know why no one's not talking about it. It literally, I saw the tweet from the Anthropic team. Hundred percent, I would use that when planning. Number two, um, don't over obsess. Obsess on MCP skills, et cetera, et cetera. I'm not saying don't get into these. I'm not saying don't read about them. I'm not saying don't use them, but I can almost guarantee you these things are not the reason why your product isn't working, right? Most of the time it's your plan sucks, right? That's number two. Um, number three, I would use Ralph after I've built something without. And the reason being is, again, listen, if you are a baller shot caller and you have all the money to blow and you don't care and you want to donate money to Anthropic, go ahead and use Ralph. But if we were to sit here eye to eye and you haven't built anything, deployed anything, there isn't a URL that I myself or Greg can click on that you've built, you have no business using Ralph. You literally have no business using Ralp…

AI assessment note: “Here's what I would say. Like, let's have a tips and tricks list.”

Q The average person listening to this podcast is building out their ideas. Is this, does this matter or at all for that person?

A Yeah, I think that's a great question. I think if I were, so I'll speak to the technical and the not technical. To the technical, there's a lot of things that a technical person can do here. I just don't have time, Greg, but one thing I was thinking of was like an MCP app store, and I'll just give this idea out for free because this, this podcast is all about ideas. Basically, there's a lot of these repos out there Um, of MCP servers, and it'd be cool if someone can go on a site. I even bought the domain. Um, it does nothing, but again, please anybody like steal this idea. Um, I bought the domain and it'd be cool if someone could, um, go on, uh, like look at the different MCP servers there. They, they see the GitHub code and whatever, and they can click like install or deploy. And they, that server is deployed and gives them a specific URL, and then they can paste that in an MCP client and work that out. So for the technical person, if you make millions, all I ask is just, you know, send me a thousand dollars. But for the non-technical person, what I would really focus on is I would just stay up to date with the platforms that are building out MCP capability and just see where the standards are going, right? Because like you said, um, when the standards are finalized, I don't know If MCP has fully won, I think it needs to be challenged. Um, or I don't know if Anthropix is going…

AI assessment note: “I'll speak to the technical and the not technical.”

Q The average person listening to this podcast is building out their ideas. Is this, does this matter or at all for that person?

A Yeah, I think that's a great question. I think if I were, so I'll speak to the technical and the not technical. To the technical, there's a lot of things that a technical person can do here. I just don't have time, Greg, but one thing I was thinking of was like an MCP app store, and I'll just give this idea out for free because this, this podcast is all about ideas. Basically, there's a lot of these repos out there Um, of MCP servers, and it'd be cool if someone can go on a site. I even bought the domain. Um, it does nothing, but again, please anybody like steal this idea. Um, I bought the domain and it'd be cool if someone could, um, go on, uh, like look at the different MCP servers there. They, they see the GitHub code and whatever, and they can click like install or deploy. And they, that server is deployed and gives them a specific URL, and then they can paste that in an MCP client and work that out. So for the technical person, if you make millions, all I ask is just, you know, send me a thousand dollars. But for the non-technical person, what I would really focus on is I would just stay up to date with the platforms that are building out MCP capability and just see where the standards are going, right? Because like you said, um, when the standards are finalized, I don't know If MCP has fully won, I think it needs to be challenged. Um, or I don't know if Anthropix is going…

AI assessment note: “I'll speak to the technical and the not technical.”

Q And couldn't you go to, let's say, clode or something like that, and just be like, here's my issue?

A I could. The one thing is, I don't know if I can download my code base. Now, what would be sick is, if they allowed me to download my code base, I could run this through cursor. Like, can I, I don't think there's an option. Like, can I tell it? Can I download the code base? Like if I could download this code base, then that would be a sick way to build. Like if I could download this code, run it through cursor, fix my issues, and then place it back here. Um, it says, oh, I have to use their editor. I don't want to do that. So let's just, let me just cheat right now and make sure everything's installed. And then let's do a build myself. So this is where the tough part with Bolt is, is the deployment part is a little finicky when you have external packages. Uh, but other than that, I mean, in 20 minutes we had, uh, well it's building right up, but we had a working prototype in 20 minutes. Um, and that's just great in my opinion.

AI assessment note: “I could. The one thing is, I don't know if I can download my code base.”

Q take your Chrome extension and then go build a SaaS business out of that. Um, a great example of that is vidIQ. vidIQ was a, a Chrome extension for YouTube creators. One of the most popular, I think hundreds of thousands, if not millions of creators use it. And then they pivoted, not pivoted, they evolved into a full on SaaS business. So what do you think of number one?

A Yeah, no, I, you know, I, I agree with you in a sense where I think a Chrome extension is a great, um, MVP to start with, and there are a lot of GitHub issues, uh, like a lot of projects, um, especially open source projects. There's a lot of issues that, you know, if you kind of see a repetitive thing, like that could in and of itself be an opportunity. I'll give you an example. There's a library called, uh, tan stack query, Um, and I'm not too sure what their monetization process looks like, but they solved one of the biggest issues in Reactland, which was data fetching. Um, and there was a way that everybody did data fetching before they came around, and it always caused issues, but they saw that problem. They solved it. It's so good that even React and the docs recommend you use their package. It's not built in React, but they tell you to use there. So I definitely think it's a great, like, place to source Um, information, see what problems, um, uh, developers are struggling with. And I think the developer market is huge. I, I don't know if, uh, you know this great, but Supabase, I think, raised the Series C, eighty million dollars. Solving developer problems does pay.

AI assessment note: “I agree with you in a sense where I think a Chrome extension is a great”

Q Do you even consider yourself An engineer anymore, or are you a product manager?

A You know, um, there, so there's a part of me that although these tools are good, if We went, if someone who's great at using these tools went against myself, or even like there's thousands of engineers better than me, I definitely do think the engineer still has the edge in terms of making the more performant and faster application, right? Because like, just looking at how it's written the code, I'm not saying it's wrong, but I can definitely make it much faster already. So, I still think in cases like that, where speed and optimization is important, um, I will still, I still consider myself an engineer, but five years from now, I, I can't even tell you where this thing is going to go, because it, it honestly is scary.

AI assessment note: “I still consider myself an engineer, but five years from now”

Q take your Chrome extension and then go build a SaaS business out of that. Um, a great example of that is vidIQ. vidIQ was a, a Chrome extension for YouTube creators. One of the most popular, I think hundreds of thousands, if not millions of creators use it. And then they pivoted, not pivoted, they evolved into a full on SaaS business. So what do you think of number one?

A Yeah, no, I, you know, I, I agree with you in a sense where I think a Chrome extension is a great, um, MVP to start with, and there are a lot of GitHub issues, uh, like a lot of projects, um, especially open source projects. There's a lot of issues that, you know, if you kind of see a repetitive thing, like that could in and of itself be an opportunity. I'll give you an example. There's a library called, uh, tan stack query, Um, and I'm not too sure what their monetization process looks like, but they solved one of the biggest issues in Reactland, which was data fetching. Um, and there was a way that everybody did data fetching before they came around, and it always caused issues, but they saw that problem. They solved it. It's so good that even React and the docs recommend you use their package. It's not built in React, but they tell you to use there. So I definitely think it's a great, like, place to source Um, information, see what problems, um, uh, developers are struggling with. And I think the developer market is huge. I, I don't know if, uh, you know this great, but Supabase, I think, raised the Series C, eighty million dollars. Solving developer problems does pay.

AI assessment note: “I agree with you in a sense where I think a Chrome extension is a great”

Q And couldn't you go to, let's say, clode or something like that, and just be like, here's my issue?

A I could. The one thing is, I don't know if I can download my code base. Now, what would be sick is, if they allowed me to download my code base, I could run this through cursor. Like, can I, I don't think there's an option. Like, can I tell it? Can I download the code base? Like if I could download this code base, then that would be a sick way to build. Like if I could download this code, run it through cursor, fix my issues, and then place it back here. Um, it says, oh, I have to use their editor. I don't want to do that. So let's just, let me just cheat right now and make sure everything's installed. And then let's do a build myself. So this is where the tough part with Bolt is, is the deployment part is a little finicky when you have external packages. Uh, but other than that, I mean, in 20 minutes we had, uh, well it's building right up, but we had a working prototype in 20 minutes. Um, and that's just great in my opinion.

AI assessment note: “I could. The one thing is, I don't know if I can download my”

Q And Netlify, you could, you know, is awesome. It's super reliable, right? It's not just any, yeah.

A It's one of the best out there. It's not your, you know, toy, like it's a dude in a school with five servers. So it says there's an error here. What we're going to do is we're going to say, fix this problem. Cause I don't even know what the issue is, nor do I want to look at it. And yeah, Netlify is a great deployment platform. There are, I mean, if we go on their site, there are pretty Netlify. I promise I don't watch Netflix. If we, yeah, so like there are big companies that use Netlify. Um, so it's, it's a great partnership, um, on both, uh, and let's see. Okay. It failed again, which is fantastic. Let's see why. So what I'm going to do is I'm going to say the build keeps on failing. Can you please fix it? And let's see on the code tab what errors there are. I'm going to do, let's see, I'm going to, okay, I know what the error is, but I'm not going to cheat. I'm just going to copy this and paste this here and say this is the error I'm getting. And I paste that, and let's see if it fixes it. I apologize for the force oversight. Such a nice model.

AI assessment note: “It's one of the best out there. It's not your, you know, toy”

Q Do you think, uh, you'll be using lovable in 12 months from now?

A You know, I like these tools to quickly MVP myself. Um, so like, let's say like a client hits me up and I have, they want me to build something. I will kind of, instead of me sitting down and thinking about it, I'll kind of just try to build it like a smaller version with like a bolt or whatever. And then it kind of gives me an idea of like what I have to do, and I kind of take that and then start to refine what I have to do. So I don't, until these integrations get solidified, I haven't gone like end to end, but it's definitely my tester and something that I used to build, um, MVPs with. So it says you can now work with fully featured backend and add powerful features to make your app functional, user accounts, login, all the good stuff. So now I'm going to say, now make the sign up and sign in work using Supabase. I'm going to hit enter. And now we should see it create my tables and do what it needs to do to make this work. It says, please review and approve SQL commands. Now the reason why it's asking me to review this cause SQL is no joke. Um, you can really destroy business writing the wrong commands, which is why, like, you know, you can copy this, maybe take this over to another model and ask it like, what are these commands going to do? Can you review them? Um, but they look good to me. So I'm just going to click apply. Okay, so now it says the migration is being applie…

AI assessment note: “until these integrations get solidified, I haven't gone like end to end”

Q Do you think, uh, you'll be using lovable in 12 months from now?

A You know, I like these tools to quickly MVP myself. Um, so like, let's say like a client hits me up and I have, they want me to build something. I will kind of, instead of me sitting down and thinking about it, I'll kind of just try to build it like a smaller version with like a bolt or whatever. And then it kind of gives me an idea of like what I have to do, and I kind of take that and then start to refine what I have to do. So I don't, until these integrations get solidified, I haven't gone like end to end, but it's definitely my tester and something that I used to build, um, MVPs with. So it says you can now work with fully featured backend and add powerful features to make your app functional, user accounts, login, all the good stuff. So now I'm going to say, now make the sign up and sign in work using Supabase. I'm going to hit enter. And now we should see it create my tables and do what it needs to do to make this work. It says, please review and approve SQL commands. Now the reason why it's asking me to review this cause SQL is no joke. Um, you can really destroy business writing the wrong commands, which is why, like, you know, you can copy this, maybe take this over to another model and ask it like, what are these commands going to do? Can you review them? Um, but they look good to me. So I'm just going to click apply. Okay, so now it says the migration is being applie…

AI assessment note: “I like these tools to quickly MVP myself... So now I'm going to say”