How to Build Effective Claude Code Agents in 2026

What would you say by the end of this What would you say by the end of this podcast [music] that everyone will have podcast [music] that everyone will have podcast [music] that everyone will have learned from you? learned from you? learned from you? >> The main thing that I want to talk about >> The main thing that I want to talk about >> The main thing that I want to talk about today is how we can be the director today is how we can be the director today is how we can be the director [music] of our coding agents. Everyone [music] of our coding agents. Everyone [music] of our coding agents. Everyone is hearing nowadays how large language is hearing nowadays how large language is hearing nowadays how large language models can support up to 1 million models can support up to 1 million models can support up to 1 million tokens in their context. That's like the tokens in their context. That's like the tokens in their context. That's like the Harry Potter book five times over. Large Harry Potter book five times over. Large Harry Potter book five times over. Large language models have what's called the language models have what's called the language models have what's called the dumb zone. With Opus right now, it's dumb zone. With Opus right now, it's dumb zone. With Opus right now, it's usually around 250,000 tokens and I feel usually around 250,000 tokens and I feel usually around 250,000 tokens and I feel like it gets into the dumb zone. like it gets into the dumb zone. like it gets into the dumb zone. >> It definitely comes with a false sense >> It definitely comes with a false sense >> It definitely comes with a false sense of security with people now thinking of security with people now thinking of security with people now thinking that they have the million. that they have the million. that they have the million. >> With coding agents, you spend more time >> With coding agents, you spend more time >> With coding agents, you spend more time planning than you actually do building. planning than you actually do building. planning than you actually do building. >> Without the verification checks, maybe >> Without the verification checks, maybe >> Without the verification checks, maybe it's 65 or 70, but now you can get it's 65 or 70, but now you can get it's 65 or 70, but now you can get something that is 92 on the first pass. something that is 92 on the first pass. something that is 92 on the first pass. >> If you tell it never to to wipe a >> If you tell it never to to wipe a >> If you tell it never to to wipe a database, it's still going to do that. database, it's still going to do that. database, it's still going to do that. If you don't allow it to delete a If you don't allow it to delete a If you don't allow it to delete a folder, it can still write a script to folder, it can still write a script to folder, it can still write a script to do that. do that. do that. >> Recently something did happen to us. The >> Recently something did happen to us. The >> Recently something did happen to us. The agent was trying to be proactive and it agent was trying to be proactive and it agent was trying to be proactive and it actually saw something on its task list, actually saw something on its task list, actually saw something on its task list, but it misinterpreted it and it ended up but it misinterpreted it and it ended up but it misinterpreted it and it ended up sending an email to our entire list with sending an email to our entire list with sending an email to our entire list with a discount code and it was not supposed a discount code and it was not supposed a discount code and it was not supposed to go out. If you have the mindset that to go out. If you have the mindset that to go out. If you have the mindset that anything that the agent can read or can anything that the agent can read or can anything that the agent can read or can touch, you have to assume that it will touch, you have to assume that it will touch, you have to assume that it will even if you never ask it to. That even if you never ask it to. That even if you never ask it to. That assumption is what's going to save you assumption is what's going to save you assumption is what's going to save you from having your database deleted.

All right, Cole. Thank you so much for All right, Cole. Thank you so much for being here today. I'm so excited to dig being here today. I'm so excited to dig being here today. I'm so excited to dig in. in. in. >> I'm excited to be here. Yeah, thanks for >> I'm excited to be here. Yeah, thanks for >> I'm excited to be here. Yeah, thanks for bringing me on your podcast, Nate. I'm bringing me on your podcast, Nate. I'm bringing me on your podcast, Nate. I'm looking forward to this. looking forward to this. looking forward to this. >> Absolutely. Yeah, it's been a a long >> Absolutely. Yeah, it's been a a long >> Absolutely. Yeah, it's been a a long time since we've talked, so I'm excited time since we've talked, so I'm excited time since we've talked, so I'm excited to hear what you've been up to and to to hear what you've been up to and to to hear what you've been up to and to hear kind of like the sauce that you're hear kind of like the sauce that you're hear kind of like the sauce that you're going to drop on everyone today. So real going to drop on everyone today. So real going to drop on everyone today. So real quick, what would you say by the end of quick, what would you say by the end of quick, what would you say by the end of this podcast that everyone will have this podcast that everyone will have this podcast that everyone will have learned from you? learned from you? learned from you? >> Yeah, so the main thing that I want to >> Yeah, so the main thing that I want to >> Yeah, so the main thing that I want to talk about today is how we can really be talk about today is how we can really be talk about today is how we can really be the director of our coding agents and the director of our coding agents and the director of our coding agents and specifically Claude Code cuz that's what specifically Claude Code cuz that's what specifically Claude Code cuz that's what most people use right now. That's what I most people use right now. That's what I most people use right now. That's what I use. But really it's creating that use. But really it's creating that use. But really it's creating that system where you have your your way of system where you have your your way of system where you have your your way of working with Claude Code that evolves working with Claude Code that evolves working with Claude Code that evolves itself over time. And we're going to itself over time. And we're going to itself over time. And we're going to talk about more than just using it to talk about more than just using it to talk about more than just using it to code. Really I use my Claude Code as my code. Really I use my Claude Code as my code. Really I use my Claude Code as my second brain I like to call it. I know second brain I like to call it. I know second brain I like to call it. I know Nate kind of calls it as AIOS. Everyone Nate kind of calls it as AIOS. Everyone Nate kind of calls it as AIOS. Everyone has their term for it, but really like has their term for it, but really like has their term for it, but really like using Cloud Code as the tool to make using Cloud Code as the tool to make using Cloud Code as the tool to make your business AI native. We're going to your business AI native. We're going to your business AI native. We're going to get into all of that. And just some get into all of that. And just some get into all of that. And just some high-level strategies that honestly you high-level strategies that honestly you high-level strategies that honestly you can start applying today. can start applying today. can start applying today. >> I love that. Yeah, I'm I'm super excited >> I love that. Yeah, I'm I'm super excited >> I love that. Yeah, I'm I'm super excited to dig in because, you know, I don't to dig in because, you know, I don't to dig in because, you know, I don't come from a formal software engineering come from a formal software engineering come from a formal software engineering background, and I think that I would I background, and I think that I would I background, and I think that I would I would guess that the majority of my would guess that the majority of my would guess that the majority of my audience doesn't either. But obviously audience doesn't either. But obviously audience doesn't either. But obviously with the the products being called Cloud with the the products being called Cloud with the the products being called Cloud Code, I think a lot of people that I Code, I think a lot of people that I Code, I think a lot of people that I bring that up to who aren't super deep bring that up to who aren't super deep bring that up to who aren't super deep in the AI space, they obviously think in the AI space, they obviously think in the AI space, they obviously think that it's a tool that is for coders, and that it's a tool that is for coders, and that it's a tool that is for coders, and you need to understand code in order to you need to understand code in order to you need to understand code in order to use it. So, um I love that framing. And use it. So, um I love that framing. And use it. So, um I love that framing. And real quick before we jump in, real quick before we jump in, real quick before we jump in, you know, me and you have we've known you know, me and you have we've known you know, me and you have we've known each other for quite a bit, I feel like, each other for quite a bit, I feel like, each other for quite a bit, I feel like, you know, right when I kind of quit my you know, right when I kind of quit my you know, right when I kind of quit my job and started on this space, you were job and started on this space, you were job and started on this space, you were one of the main channels that I followed one of the main channels that I followed one of the main channels that I followed and I still follow to stay up to date and I still follow to stay up to date and I still follow to stay up to date and to to learn about how to work with and to to learn about how to work with and to to learn about how to work with AI in the right way. And um we've kind

AI in the right way. And um we've kind AI in the right way. And um we've kind of just been able to see each other grow of just been able to see each other grow of just been able to see each other grow and and, you know, check in. So, I'm and and, you know, check in. So, I'm and and, you know, check in. So, I'm really excited to dive in, but I wanted really excited to dive in, but I wanted really excited to dive in, but I wanted to make sure you got a chance to real to make sure you got a chance to real to make sure you got a chance to real quick give everyone a quick intro if quick give everyone a quick intro if quick give everyone a quick intro if they haven't seen your channel before on they haven't seen your channel before on they haven't seen your channel before on what you do. And um what you do. And um what you do. And um yeah, what you're up to. yeah, what you're up to. yeah, what you're up to. >> Yeah, sounds good. You know, before I >> Yeah, sounds good. You know, before I >> Yeah, sounds good. You know, before I give an intro though, I kind of want to give an intro though, I kind of want to give an intro though, I kind of want to share something a little bit about what share something a little bit about what share something a little bit about what you're talking about. Like when we first you're talking about. Like when we first you're talking about. Like when we first met, it's funny cuz I I actually met, it's funny cuz I I actually met, it's funny cuz I I actually remember I had um about 50,000 remember I had um about 50,000 remember I had um about 50,000 subscribers when Nate first reached out subscribers when Nate first reached out subscribers when Nate first reached out to me, and he had like 10,000. And now to me, and he had like 10,000. And now to me, and he had like 10,000. And now it's a little bit different. I have like it's a little bit different. I have like it's a little bit different. I have like 200,000, and you're you're almost 200,000, and you're you're almost 200,000, and you're you're almost 800,000 now, right? Like it's pretty 800,000 now, right? Like it's pretty 800,000 now, right? Like it's pretty crazy. Um it's been really cool to see crazy. Um it's been really cool to see crazy. Um it's been really cool to see you grow, how fast you've grown. But you grow, how fast you've grown. But you grow, how fast you've grown. But yeah, we were both like smaller channels yeah, we were both like smaller channels yeah, we were both like smaller channels at the time. at the time. at the time. Um so yeah, it's it's been a long time Um so yeah, it's it's been a long time Um so yeah, it's it's been a long time wild journey. wild journey. wild journey. Uh yeah, anyway, as far as what I Uh yeah, anyway, as far as what I Uh yeah, anyway, as far as what I actually do, so like Nate said, I come actually do, so like Nate said, I come actually do, so like Nate said, I come from a software engineering background. from a software engineering background. from a software engineering background. So, I've been an engineer my entire life So, I've been an engineer my entire life So, I've been an engineer my entire life ever since I was 8 years old actually. I ever since I was 8 years old actually. I ever since I was 8 years old actually. I I started with this language called I started with this language called I started with this language called Scratch. It's developed by MIT. So, I Scratch. It's developed by MIT. So, I Scratch. It's developed by MIT. So, I was just like building video games as a was just like building video games as a was just like building video games as a kid, like Super Mario Bros. and Pokémon, kid, like Super Mario Bros. and Pokémon, kid, like Super Mario Bros. and Pokémon, like really cliché stuff. Um but that like really cliché stuff. Um but that like really cliché stuff. Um but that that's what got me to the world of that's what got me to the world of that's what got me to the world of coding. And so I took that through high coding. And so I took that through high coding. And so I took that through high school, college, got my bachelor's in school, college, got my bachelor's in school, college, got my bachelor's in computer science, and um then I had just computer science, and um then I had just computer science, and um then I had just like a software engineering job in a like a software engineering job in a like a software engineering job in a Fortune 500 company, and it was great, Fortune 500 company, and it was great, Fortune 500 company, and it was great, but I always wanted to be an but I always wanted to be an but I always wanted to be an entrepreneur. And so, when generative AI entrepreneur. And so, when generative AI entrepreneur. And so, when generative AI started really become a big thing at the started really become a big thing at the started really become a big thing at the end of 2022 with the release of chat end of 2022 with the release of chat end of 2022 with the release of chat GPT, you know, when it took the world by GPT, you know, when it took the world by GPT, you know, when it took the world by storm, that's when I knew like, "Okay, storm, that's when I knew like, "Okay, storm, that's when I knew like, "Okay, this is where I want to go all in." cuz this is where I want to go all in." cuz this is where I want to go all in." cuz there's like a really big opportunity there's like a really big opportunity there's like a really big opportunity for a software engineer specifically to for a software engineer specifically to for a software engineer specifically to build agentic applications. And so, I

build agentic applications. And so, I build agentic applications. And so, I started doing a lot of that like for my started doing a lot of that like for my started doing a lot of that like for my company and for friends with their company and for friends with their company and for friends with their startups, pretty much dedicating all day startups, pretty much dedicating all day startups, pretty much dedicating all day and all night to it for a very long and all night to it for a very long and all night to it for a very long time, like over a year. time, like over a year. time, like over a year. And so, it got to the point, well, I And so, it got to the point, well, I And so, it got to the point, well, I know, a year might not feel like a long know, a year might not feel like a long know, a year might not feel like a long time, but in the AI space, a year is a time, but in the AI space, a year is a time, but in the AI space, a year is a long time. long time. long time. >> Oh, yeah. >> Oh, yeah. >> Oh, yeah. >> So, like it it got to the point where >> So, like it it got to the point where >> So, like it it got to the point where like, "Okay, I got some things to teach like, "Okay, I got some things to teach like, "Okay, I got some things to teach people." So, that's why I started my people." So, that's why I started my people." So, that's why I started my YouTube channel. So, originally, it was YouTube channel. So, originally, it was YouTube channel. So, originally, it was like really, really technical. Like I like really, really technical. Like I like really, really technical. Like I was there like writing line by line. I was there like writing line by line. I was there like writing line by line. I wasn't even using AI coding assistants wasn't even using AI coding assistants wasn't even using AI coding assistants back then, just showing how to build AI back then, just showing how to build AI back then, just showing how to build AI agents with like, you know, LangChain agents with like, you know, LangChain agents with like, you know, LangChain and LangGraph at the time. And now and LangGraph at the time. And now and LangGraph at the time. And now that's evolved to a lot of different that's evolved to a lot of different that's evolved to a lot of different things like I I do a lot of like things like I I do a lot of like things like I I do a lot of like focusing on AI coding assistants, which focusing on AI coding assistants, which focusing on AI coding assistants, which is why we're talking about that today. is why we're talking about that today. is why we're talking about that today. Um and yeah, I quit my my full-time job Um and yeah, I quit my my full-time job Um and yeah, I quit my my full-time job like 3 months after starting my YouTube like 3 months after starting my YouTube like 3 months after starting my YouTube channel, which I think is about the same channel, which I think is about the same channel, which I think is about the same for you, Nate. for you, Nate. for you, Nate. >> Yeah. >> Yeah. >> Yeah. >> Um cuz it's crazy like how fast when you >> Um cuz it's crazy like how fast when you >> Um cuz it's crazy like how fast when you when you do it right and and you're when you do it right and and you're when you do it right and and you're teaching people valuable things like how teaching people valuable things like how teaching people valuable things like how fast a channel can explode. And so, now fast a channel can explode. And so, now fast a channel can explode. And so, now now what I'm up to is I have my AI now what I'm up to is I have my AI now what I'm up to is I have my AI community um similar to Nate, where I've community um similar to Nate, where I've community um similar to Nate, where I've got course content, weekly workshops got course content, weekly workshops got course content, weekly workshops that I do. I've also been doing some that I do. I've also been doing some that I do. I've also been doing some more enterprise-level training. So, more enterprise-level training. So, more enterprise-level training. So, coming into a team and doing like a coming into a team and doing like a coming into a team and doing like a 4-hour session, helping them adopt a 4-hour session, helping them adopt a 4-hour session, helping them adopt a full system for using AI coding full system for using AI coding full system for using AI coding assistants so they can really have it as assistants so they can really have it as assistants so they can really have it as like a standard for the team. You know, like a standard for the team. You know, like a standard for the team. You know, get get away [clears throat] from vibe get get away [clears throat] from vibe get get away [clears throat] from vibe coding to really have a structured coding to really have a structured coding to really have a structured approach and helping them actually bring approach and helping them actually bring approach and helping them actually bring that into their existing processes and that into their existing processes and that into their existing processes and tech stack and things like that. So, tech stack and things like that. So, tech stack and things like that. So, that's been pretty awesome. And so, like that's been pretty awesome. And so, like that's been pretty awesome. And so, like really like that and everything I teach really like that and everything I teach really like that and everything I teach in the community, I'm bringing a lot of in the community, I'm bringing a lot of in the community, I'm bringing a lot of that here to uh what we're going to be that here to uh what we're going to be that here to uh what we're going to be chatting about today.

chatting about today. chatting about today. >> 100%. Real quick, guys, quick break to >> 100%. Real quick, guys, quick break to >> 100%. Real quick, guys, quick break to tell you about today's sponsor, ClickUp. tell you about today's sponsor, ClickUp. tell you about today's sponsor, ClickUp. ClickUp is the software to replace all ClickUp is the software to replace all ClickUp is the software to replace all software, which I think is pretty funny, software, which I think is pretty funny, software, which I think is pretty funny, but very true. If you guys have been but very true. If you guys have been but very true. If you guys have been following me for a while, you know that following me for a while, you know that following me for a while, you know that I've been using ClickUp for a long, long I've been using ClickUp for a long, long I've been using ClickUp for a long, long time. Everything that I do with my team time. Everything that I do with my team time. Everything that I do with my team lives in ClickUp, all of our lives in ClickUp, all of our lives in ClickUp, all of our communication, all of our project communication, all of our project communication, all of our project management, all of our chats, and management, all of our chats, and management, all of our chats, and everything I was doing with my clients everything I was doing with my clients everything I was doing with my clients back when I was running the agency back when I was running the agency back when I was running the agency day-to-day, we were also inviting them day-to-day, we were also inviting them day-to-day, we were also inviting them to a ClickUp. So, it had replaced Slack to a ClickUp. So, it had replaced Slack to a ClickUp. So, it had replaced Slack for us, and it had also replaced our for us, and it had also replaced our for us, and it had also replaced our project management tools. So, if you're project management tools. So, if you're project management tools. So, if you're already using ClickUp, you have to try already using ClickUp, you have to try already using ClickUp, you have to try this new feature called Brain 2. But, if this new feature called Brain 2. But, if this new feature called Brain 2. But, if you don't use ClickUp already, then you don't use ClickUp already, then you don't use ClickUp already, then Brain 2 is an amazing reason to try out Brain 2 is an amazing reason to try out Brain 2 is an amazing reason to try out ClickUp. It's kind of like a ClickUp. It's kind of like a ClickUp. It's kind of like a supercomputer that can do a ton of cool supercomputer that can do a ton of cool supercomputer that can do a ton of cool stuff, and I'll talk about it in a sec, stuff, and I'll talk about it in a sec, stuff, and I'll talk about it in a sec, they have super agents in here. But, you they have super agents in here. But, you they have super agents in here. But, you can switch between the different chat can switch between the different chat can switch between the different chat models that you probably already use and models that you probably already use and models that you probably already use and love. Right here, you can see that I've love. Right here, you can see that I've love. Right here, you can see that I've used Brain myself to look through used Brain myself to look through used Brain myself to look through everything that's going on in our everything that's going on in our everything that's going on in our projects, and then create me a monthly projects, and then create me a monthly projects, and then create me a monthly presentation for the team. So, what that presentation for the team. So, what that presentation for the team. So, what that could look like is me asking Brain to could look like is me asking Brain to could look like is me asking Brain to create an investor presentation pitch create an investor presentation pitch create an investor presentation pitch deck for our text-to-speech startup deck for our text-to-speech startup deck for our text-to-speech startup called Glydo, and I told it to just use called Glydo, and I told it to just use called Glydo, and I told it to just use mock data, but make sure that it's mock data, but make sure that it's mock data, but make sure that it's professional and engaging. And just like professional and engaging. And just like professional and engaging. And just like that, we have the deck, which I can open that, we have the deck, which I can open that, we have the deck, which I can open up full screen right here. We've got the up full screen right here. We've got the up full screen right here. We've got the voice AI platform that makes every brain voice AI platform that makes every brain voice AI platform that makes every brain sound human. And as I start to navigate sound human. And as I start to navigate sound human. And as I start to navigate through here, you can see that we also through here, you can see that we also through here, you can see that we also have animations in here. So, it's not have animations in here. So, it's not have animations in here. So, it's not just a static, you know, slide deck. We just a static, you know, slide deck. We just a static, you know, slide deck. We get to actually go through, and we feel get to actually go through, and we feel get to actually go through, and we feel the animations. And think about the fact the animations. And think about the fact the animations. And think about the fact that this was just a one-sentence that this was just a one-sentence that this was just a one-sentence prompt. If we really started to put more prompt. If we really started to put more prompt. If we really started to put more and more data into this thing, it would and more data into this thing, it would and more data into this thing, it would be really, really solid. And this right be really, really solid. And this right be really, really solid. And this right here is just one of the many use cases here is just one of the many use cases here is just one of the many use cases of Brain 2. So, it's not just a chatbot, of Brain 2. So, it's not just a chatbot, of Brain 2. So, it's not just a chatbot, like I said, it can do things, and you like I said, it can do things, and you like I said, it can do things, and you can build your own super agents in here.

can build your own super agents in here. can build your own super agents in here. And what I think is really cool about And what I think is really cool about And what I think is really cool about the super agents is they're 24/7 agents, the super agents is they're 24/7 agents, the super agents is they're 24/7 agents, you can tag them in ClickUp, you know, you can tag them in ClickUp, you know, you can tag them in ClickUp, you know, you can at message them, and they'll you can at message them, and they'll you can at message them, and they'll wake up and respond to you, and they can wake up and respond to you, and they can wake up and respond to you, and they can search through everything, which is why, search through everything, which is why, search through everything, which is why, in my opinion, it's a lot cooler that in my opinion, it's a lot cooler that in my opinion, it's a lot cooler that ClickUp is doing this compared to ClickUp is doing this compared to ClickUp is doing this compared to something like chucking an open claw or something like chucking an open claw or something like chucking an open claw or Hermes agent into ClickUp, because these Hermes agent into ClickUp, because these Hermes agent into ClickUp, because these agents already have full context and can agents already have full context and can agents already have full context and can search through everything. So, right search through everything. So, right search through everything. So, right now, because you're watching this video, now, because you're watching this video, now, because you're watching this video, you can claim this super awesome offer you can claim this super awesome offer you can claim this super awesome offer that is on screen right now by using the that is on screen right now by using the that is on screen right now by using the link in the description. Now, let's link in the description. Now, let's link in the description. Now, let's Let's back to the video. Yeah, well, I Let's back to the video. Yeah, well, I Let's back to the video. Yeah, well, I am just I'm so glad that that we both am just I'm so glad that that we both am just I'm so glad that that we both took the leap cuz it's it's you know, took the leap cuz it's it's you know, took the leap cuz it's it's you know, it's not an easy decision, but um your it's not an easy decision, but um your it's not an easy decision, but um your brain just gets it. And so, it's been brain just gets it. And so, it's been brain just gets it. And so, it's been great to see, you know, the consistency great to see, you know, the consistency great to see, you know, the consistency in what you've been up to, but I think in what you've been up to, but I think in what you've been up to, but I think that if you think back to, I don't know, that if you think back to, I don't know, that if you think back to, I don't know, 5, 10 years ago when people were going 5, 10 years ago when people were going 5, 10 years ago when people were going out to get their, you know, CS degrees out to get their, you know, CS degrees out to get their, you know, CS degrees and stuff, it's like that was such a and stuff, it's like that was such a and stuff, it's like that was such a safe bet at the time, you know? And I safe bet at the time, you know? And I safe bet at the time, you know? And I don't think a lot of people don't think a lot of people don't think a lot of people were predicting how much how quick that were predicting how much how quick that were predicting how much how quick that was going to flip as far as like, you was going to flip as far as like, you was going to flip as far as like, you know, that graphic of what is AI being know, that graphic of what is AI being know, that graphic of what is AI being applied to. And right now, it's just applied to. And right now, it's just applied to. And right now, it's just majority is coding and software majority is coding and software majority is coding and software engineering. And obviously, everything's engineering. And obviously, everything's engineering. And obviously, everything's going to catch up, but um going to catch up, but um going to catch up, but um it's just great that you were able to, it's just great that you were able to, it's just great that you were able to, you know, make that pivot and be ahead you know, make that pivot and be ahead you know, make that pivot and be ahead of the curve. And now, now here we are.

of the curve. And now, now here we are. of the curve. And now, now here we are. So, um being able to us have this So, um being able to us have this So, um being able to us have this conversation, one of us coming from like conversation, one of us coming from like conversation, one of us coming from like a non-technical background completely, a non-technical background completely, a non-technical background completely, and one of us coming from a technical and one of us coming from a technical and one of us coming from a technical background, it's going to be really background, it's going to be really background, it's going to be really cool. So, yeah, let's just jump right cool. So, yeah, let's just jump right cool. So, yeah, let's just jump right in. in. in. >> Yeah, sounds good. Cool. So, for for >> Yeah, sounds good. Cool. So, for for >> Yeah, sounds good. Cool. So, for for what I have prepared for today, um what I have prepared for today, um what I have prepared for today, um you'll see like you'll see like you'll see like you'll see it shine through that I come you'll see it shine through that I come you'll see it shine through that I come from a technical background. But but from a technical background. But but from a technical background. But but really, what it comes down to is like really, what it comes down to is like really, what it comes down to is like I'm going to bring these concepts into I'm going to bring these concepts into I'm going to bring these concepts into using Claude code for far more than just using Claude code for far more than just using Claude code for far more than just coding, like I alluded to at the start. coding, like I alluded to at the start. coding, like I alluded to at the start. And so, I think um you know, for me, And so, I think um you know, for me, And so, I think um you know, for me, like I I really like I I really like I I really enjoy leaning on my technical expertise enjoy leaning on my technical expertise enjoy leaning on my technical expertise because a lot of the ways that you'll because a lot of the ways that you'll because a lot of the ways that you'll use an AI coding assistant for your ops, use an AI coding assistant for your ops, use an AI coding assistant for your ops, your AIOS, your second brain, whatever your AIOS, your second brain, whatever your AIOS, your second brain, whatever you want to call it, um it you are going you want to call it, um it you are going you want to call it, um it you are going to be borrowing from software to be borrowing from software to be borrowing from software engineering principles, whether you engineering principles, whether you engineering principles, whether you realize it or not. So, a lot of times, realize it or not. So, a lot of times, realize it or not. So, a lot of times, just as you learn how to use these tools just as you learn how to use these tools just as you learn how to use these tools effectively, and you're just learning effectively, and you're just learning effectively, and you're just learning best practices from Nate's YouTube or best practices from Nate's YouTube or best practices from Nate's YouTube or Anthropic's blog or Boris Cherney or Anthropic's blog or Boris Cherney or Anthropic's blog or Boris Cherney or whoever, like they're bringing software whoever, like they're bringing software whoever, like they're bringing software engineering principles and a lot of like engineering principles and a lot of like engineering principles and a lot of like product management manager principles as product management manager principles as product management manager principles as well. And so, yeah, like some of the well. And so, yeah, like some of the well. And so, yeah, like some of the examples that I have here um that we'll examples that I have here um that we'll examples that I have here um that we'll cover, like they're a little technical, cover, like they're a little technical, cover, like they're a little technical, um but that's really just like to um but that's really just like to um but that's really just like to illustrate how how I started using this illustrate how how I started using this illustrate how how I started using this tool, and then of course, I'll like tool, and then of course, I'll like tool, and then of course, I'll like generalize things a lot as well.

generalize things a lot as well. generalize things a lot as well. And um give some specific examples, too. And um give some specific examples, too. And um give some specific examples, too. Um so, if you if you want, Nate, I can Um so, if you if you want, Nate, I can Um so, if you if you want, Nate, I can just like dive right into the just like dive right into the just like dive right into the >> Yeah, let's >> Yeah, let's >> Yeah, let's >> first part that we have here. Okay, >> first part that we have here. Okay, >> first part that we have here. Okay, cool. Yeah, so I got like just quick cool. Yeah, so I got like just quick cool. Yeah, so I got like just quick over I mean, we'll go pretty quick over I mean, we'll go pretty quick over I mean, we'll go pretty quick through this cuz I want to keep this through this cuz I want to keep this through this cuz I want to keep this pretty casual, and I know you you do as pretty casual, and I know you you do as pretty casual, and I know you you do as well, Nate, but just like a few well, Nate, but just like a few well, Nate, but just like a few different pillars here of how we can go different pillars here of how we can go different pillars here of how we can go from simply using Claude code to what a from simply using Claude code to what a from simply using Claude code to what a lot of people call vibe coding, you lot of people call vibe coding, you lot of people call vibe coding, you know, prompting and praying where you're know, prompting and praying where you're know, prompting and praying where you're you're pulling that lever like a slot you're pulling that lever like a slot you're pulling that lever like a slot machine, getting to the point where machine, getting to the point where machine, getting to the point where we're really directing it and having we're really directing it and having we're really directing it and having that system for reliable and repeatable that system for reliable and repeatable that system for reliable and repeatable results. results. results. And um it really can be simpler than you And um it really can be simpler than you And um it really can be simpler than you would think, right? Like most of what would think, right? Like most of what would think, right? Like most of what people do that you really shouldn't do people do that you really shouldn't do people do that you really shouldn't do is you throw in a request, and you don't is you throw in a request, and you don't is you throw in a request, and you don't do much of the planning up front or the do much of the planning up front or the do much of the planning up front or the validation after. Like those are the two validation after. Like those are the two validation after. Like those are the two things that I really want to talk about things that I really want to talk about things that I really want to talk about here, and that applies to uh writing any here, and that applies to uh writing any here, and that applies to uh writing any code or any kind of application. It code or any kind of application. It code or any kind of application. It applies to evolving your system like as applies to evolving your system like as applies to evolving your system like as you're creating skills and integrations you're creating skills and integrations you're creating skills and integrations for Claude code, or even just using it for Claude code, or even just using it for Claude code, or even just using it to automate things in your business.

to automate things in your business. to automate things in your business. Um and so, yeah, the approach is you Um and so, yeah, the approach is you Um and so, yeah, the approach is you always want to plan with context, always want to plan with context, always want to plan with context, build out that thing that you're looking build out that thing that you're looking build out that thing that you're looking to do, and then have an approach for to do, and then have an approach for to do, and then have an approach for verifying. Like as high-level as I can verifying. Like as high-level as I can verifying. Like as high-level as I can possibly keep it. And then the other possibly keep it. And then the other possibly keep it. And then the other like kind of golden nugget here like kind of golden nugget here like kind of golden nugget here is every time you go through this loop is every time you go through this loop is every time you go through this loop with Claude code, any kind of agentic with Claude code, any kind of agentic with Claude code, any kind of agentic workflow or thing that you're building, workflow or thing that you're building, workflow or thing that you're building, there's always going to be an there's always going to be an there's always going to be an opportunity at the end to evolve your opportunity at the end to evolve your opportunity at the end to evolve your system. And we'll talk about what that system. And we'll talk about what that system. And we'll talk about what that means in a little bit here, but like means in a little bit here, but like means in a little bit here, but like really that comes down to there's going really that comes down to there's going really that comes down to there's going to be something in the way you work with to be something in the way you work with to be something in the way you work with Claude code that you can improve so that Claude code that you can improve so that Claude code that you can improve so that next time it's going to be better. next time it's going to be better. next time it's going to be better. >> Mhm. >> Mhm. >> Mhm. >> And I'm I'm being high-level here on >> And I'm I'm being high-level here on >> And I'm I'm being high-level here on purpose cuz I'll get into some more purpose cuz I'll get into some more purpose cuz I'll get into some more examples. examples. examples. But a lot of people don't think about But a lot of people don't think about But a lot of people don't think about doing this, right? They kind of like get doing this, right? They kind of like get doing this, right? They kind of like get to the point where it's like, "Okay, my to the point where it's like, "Okay, my to the point where it's like, "Okay, my application works. Like this website application works. Like this website application works. Like this website looks good. Or it's now able to automate looks good. Or it's now able to automate looks good. Or it's now able to automate creating invoices." Like whatever it is, creating invoices." Like whatever it is, creating invoices." Like whatever it is, and they're like, "All right, we're and they're like, "All right, we're and they're like, "All right, we're done. Like let's next time I want to done. Like let's next time I want to done. Like let's next time I want to create an invoice, I'm just going to go create an invoice, I'm just going to go create an invoice, I'm just going to go through the same process again." But through the same process again." But through the same process again." But like really there are going to be those like really there are going to be those like really there are going to be those problems that come up over time where problems that come up over time where problems that come up over time where you can engineer so that they happen you can engineer so that they happen you can engineer so that they happen less often, right? That that system less often, right? That that system less often, right? That that system evolution is kind of what I like to call evolution is kind of what I like to call evolution is kind of what I like to call it.

it. it. >> Yeah. >> Yeah. >> Yeah. >> So you're having you're having it learn >> So you're having you're having it learn >> So you're having you're having it learn just like you would an employee, right? just like you would an employee, right? just like you would an employee, right? >> Absolutely. >> Absolutely. >> Absolutely. >> Yeah. My my second brain, I literally >> Yeah. My my second brain, I literally >> Yeah. My my second brain, I literally call it my co-founder, right? So I want call it my co-founder, right? So I want call it my co-founder, right? So I want it to like learn me better over time and it to like learn me better over time and it to like learn me better over time and how I like to work, how I want it to how I like to work, how I want it to how I like to work, how I want it to work as well. work as well. work as well. >> Mhm. Yeah, and I think this four-step >> Mhm. Yeah, and I think this four-step >> Mhm. Yeah, and I think this four-step kind of framework or whatever you want kind of framework or whatever you want kind of framework or whatever you want to call it, it to call it, it to call it, it yes, when you kind of maybe look at it yes, when you kind of maybe look at it yes, when you kind of maybe look at it like this, it might feel like it's a like this, it might feel like it's a like this, it might feel like it's a technical software engineering thing, technical software engineering thing, technical software engineering thing, but if you just relate that back to the but if you just relate that back to the but if you just relate that back to the same way you would maybe like, let's same way you would maybe like, let's same way you would maybe like, let's just say build a treehouse. Like you just say build a treehouse. Like you just say build a treehouse. Like you would plan that thing out first. You would plan that thing out first. You would plan that thing out first. You would draw it out. You would understand would draw it out. You would understand would draw it out. You would understand how much wood you need and where. You how much wood you need and where. You how much wood you need and where. You would get the right gear, and then once would get the right gear, and then once would get the right gear, and then once you've built it, you're not just going you've built it, you're not just going you've built it, you're not just going to put your kids on it. You're going to to put your kids on it. You're going to to put your kids on it. You're going to like test it. You're going to make sure like test it. You're going to make sure like test it. You're going to make sure that thing's not going to fall. So um that thing's not going to fall. So um that thing's not going to fall. So um it's just a great way to think about it, it's just a great way to think about it, it's just a great way to think about it, and especially if you think about some and especially if you think about some and especially if you think about some of the the pitfalls that these models of the the pitfalls that these models of the the pitfalls that these models have with like the sycophancy, have with like the sycophancy, have with like the sycophancy, essentially just being a yes man. If you essentially just being a yes man. If you essentially just being a yes man. If you say, "Hey, you know, I want to do this. say, "Hey, you know, I want to do this. say, "Hey, you know, I want to do this. Does that look good?" And they're just Does that look good?" And they're just Does that look good?" And they're just going to say, "Yeah, it does." Without going to say, "Yeah, it does." Without going to say, "Yeah, it does." Without really looking over the plan. And then really looking over the plan. And then really looking over the plan. And then on the verification side, on the verification side, on the verification side, you know, sometimes they do tell you you know, sometimes they do tell you you know, sometimes they do tell you something's done, but it's not. So something's done, but it's not. So something's done, but it's not. So having your own method of doing that as having your own method of doing that as having your own method of doing that as well well well really important.

really important. really important. >> Yeah. >> Yeah. >> Yeah. >> By the way, guys, I know we are diving >> By the way, guys, I know we are diving >> By the way, guys, I know we are diving into a ton of information in this into a ton of information in this into a ton of information in this episode. So what I did is I broke all of episode. So what I did is I broke all of episode. So what I did is I broke all of this down into a free resource guide this down into a free resource guide this down into a free resource guide that you can access for completely free that you can access for completely free that you can access for completely free by joining the free school community. by joining the free school community. by joining the free school community. The link for that is down in the The link for that is down in the The link for that is down in the description. Also, if you want to check description. Also, if you want to check description. Also, if you want to check out some of the key moments from this out some of the key moments from this out some of the key moments from this episode and all future podcasts on my episode and all future podcasts on my episode and all future podcasts on my channel, then go ahead and check out the channel, then go ahead and check out the channel, then go ahead and check out the AI Automation Society YouTube channel AI Automation Society YouTube channel AI Automation Society YouTube channel where we're going to be posting some of where we're going to be posting some of where we're going to be posting some of the best moments from the podcast over the best moments from the podcast over the best moments from the podcast over there. I'll link that YouTube channel in there. I'll link that YouTube channel in there. I'll link that YouTube channel in the description of this video as well. the description of this video as well. the description of this video as well. Anyways, thanks, guys. Let's get back to Anyways, thanks, guys. Let's get back to Anyways, thanks, guys. Let's get back to the podcast. the podcast. the podcast. >> Yeah, verification really comes down to >> Yeah, verification really comes down to >> Yeah, verification really comes down to prove to me it's actually done and prove to me it's actually done and prove to me it's actually done and working. working. working. >> Mhm. >> Mhm. >> Mhm. >> Right? And so like for any kind of >> Right? And so like for any kind of >> Right? And so like for any kind of coding task, that's things like unit coding task, that's things like unit coding task, that's things like unit tests and linting and like that's where tests and linting and like that's where tests and linting and like that's where it gets a little bit more technical, but it gets a little bit more technical, but it gets a little bit more technical, but like really you can apply that to like really you can apply that to like really you can apply that to anything. anything. anything. Um like I This is the example that I'm Um like I This is the example that I'm Um like I This is the example that I'm going to spoil right now. Um I used going to spoil right now. Um I used going to spoil right now. Um I used Claude Code to generate this entire Claude Code to generate this entire Claude Code to generate this entire diagram. diagram. diagram. >> I had a feeling you did, yeah. >> I had a feeling you did, yeah. >> I had a feeling you did, yeah. >> Yeah, yeah, yeah. So, I have I have a >> Yeah, yeah, yeah. So, I have I have a >> Yeah, yeah, yeah. So, I have I have a skill. It's like Excalidraw diagram skill. It's like Excalidraw diagram skill. It's like Excalidraw diagram skill. I've covered it on my YouTube skill. I've covered it on my YouTube skill. I've covered it on my YouTube channel, actually. So, I use it to build channel, actually. So, I use it to build channel, actually. So, I use it to build this whole thing. And um I was going to this whole thing. And um I was going to this whole thing. And um I was going to talk about this example a bit more right talk about this example a bit more right talk about this example a bit more right here when we really get into like here when we really get into like here when we really get into like verifying the work. Um but I think it's verifying the work. Um but I think it's verifying the work. Um but I think it's just such a good like non There's just such a good like non There's just such a good like non There's nothing to do with coding here. It's nothing to do with coding here. It's nothing to do with coding here. It's just creating a diagram. But as far as just creating a diagram. But as far as just creating a diagram. But as far as far as verification goes, I actually far as verification goes, I actually far as verification goes, I actually have it take the Excalidraw diagram and have it take the Excalidraw diagram and have it take the Excalidraw diagram and render a PNG. So, there's like an render a PNG. So, there's like an render a PNG. So, there's like an integration that I built into the skill integration that I built into the skill integration that I built into the skill for Claude Code, so it can render it as for Claude Code, so it can render it as for Claude Code, so it can render it as an image. And as a lot of you know, like an image. And as a lot of you know, like an image. And as a lot of you know, like Claude Code is able to understand images Claude Code is able to understand images Claude Code is able to understand images incredibly well now. For like the last incredibly well now. For like the last incredibly well now. For like the last year, it's been so good. And it's um year, it's been so good. And it's um year, it's been so good. And it's um even viewing like a like if I zoom out

even viewing like a like if I zoom out even viewing like a like if I zoom out here, like there's quite a bit of here, like there's quite a bit of here, like there's quite a bit of context. But like it can pick out the context. But like it can pick out the context. But like it can pick out the tiniest piece of text in a larger image tiniest piece of text in a larger image tiniest piece of text in a larger image like this. And so, I have it look at like this. And so, I have it look at like this. And so, I have it look at that that that and then figure out like if there's any and then figure out like if there's any and then figure out like if there's any kind of like padding or spacing issues, kind of like padding or spacing issues, kind of like padding or spacing issues, like if there's any sort of overlap. And like if there's any sort of overlap. And like if there's any sort of overlap. And And trust me, there was. Like it had to And trust me, there was. Like it had to And trust me, there was. Like it had to iterate a couple times to build iterate a couple times to build iterate a couple times to build something this big. Um but then the the something this big. Um but then the the something this big. Um but then the the point is like it is able to iterate by point is like it is able to iterate by point is like it is able to iterate by itself. So, we don't really care about itself. So, we don't really care about itself. So, we don't really care about the initial mess-ups that it has. As the initial mess-ups that it has. As the initial mess-ups that it has. As long as it like does that by itself, we long as it like does that by itself, we long as it like does that by itself, we just care about that that last thing it just care about that that last thing it just care about that that last thing it hands back to us when it says it's done. hands back to us when it says it's done. hands back to us when it says it's done. >> Absolutely. >> Absolutely. >> Absolutely. >> this If we have the step when it says >> this If we have the step when it says >> this If we have the step when it says it's done, then like it actually is, or it's done, then like it actually is, or it's done, then like it actually is, or at least it's closer. I mean, it's still at least it's closer. I mean, it's still at least it's closer. I mean, it's still probably not going to be perfect, but probably not going to be perfect, but probably not going to be perfect, but you get the idea. Yeah. you get the idea. Yeah. you get the idea. Yeah. >> Yeah, 100%. I've done something pretty >> Yeah, 100%. I've done something pretty >> Yeah, 100%. I've done something pretty similar with my video editing pipeline similar with my video editing pipeline similar with my video editing pipeline with the motion graphics it adds. And with the motion graphics it adds. And with the motion graphics it adds. And sometimes things would be out of bounds, sometimes things would be out of bounds, sometimes things would be out of bounds, but like you said, the whole idea is but like you said, the whole idea is but like you said, the whole idea is it's almost never going to be 100% on it's almost never going to be 100% on it's almost never going to be 100% on that first pass. But without the that first pass. But without the that first pass. But without the verification checks, maybe it's 65 or verification checks, maybe it's 65 or verification checks, maybe it's 65 or 70. But now you can get something that 70. But now you can get something that 70. But now you can get something that is 92 on the first pass. is 92 on the first pass. is 92 on the first pass. >> Right. Exactly. Yeah. >> Right. Exactly. Yeah. >> Right. Exactly. Yeah. Yeah, it's it's good. So, I mean, Yeah, it's it's good. So, I mean, Yeah, it's it's good. So, I mean, verification, validation, whatever you verification, validation, whatever you verification, validation, whatever you want to call it. Like, that is one of want to call it. Like, that is one of want to call it. Like, that is one of the biggest things that I'm focusing on the biggest things that I'm focusing on the biggest things that I'm focusing on right now for any kind of application or right now for any kind of application or right now for any kind of application or automation that I'm creating. I want automation that I'm creating. I want automation that I'm creating. I want some kind of harness for the coding some kind of harness for the coding some kind of harness for the coding agent to be able to validate its own agent to be able to validate its own agent to be able to validate its own work. It's a lot of code to validate its work. It's a lot of code to validate its work. It's a lot of code to validate its own work. And for some things like own work. And for some things like own work. And for some things like website design, it's actually pretty website design, it's actually pretty website design, it's actually pretty easy. There's a lot of tools out there.

easy. There's a lot of tools out there. easy. There's a lot of tools out there. Maybe you've heard of Playwright or Maybe you've heard of Playwright or Maybe you've heard of Playwright or Vercel's agent browser Vercel's agent browser Vercel's agent browser for it to really just spin up the site, for it to really just spin up the site, for it to really just spin up the site, right? You can run the command to start right? You can run the command to start right? You can run the command to start the website and then it can visit it the website and then it can visit it the website and then it can visit it just as a user would. Take screenshots just as a user would. Take screenshots just as a user would. Take screenshots along the way to prove things to you or along the way to prove things to you or along the way to prove things to you or even just view the the UI itself. It's even just view the the UI itself. It's even just view the the UI itself. It's pretty easy. For other kinds of things pretty easy. For other kinds of things pretty easy. For other kinds of things that you'll build, that you'll build, that you'll build, it can be kind of hard to have the agent it can be kind of hard to have the agent it can be kind of hard to have the agent really verify its own work effectively. really verify its own work effectively. really verify its own work effectively. One like really simple example, kind of One like really simple example, kind of One like really simple example, kind of silly example, silly example, silly example, I In my spare time, like I've I've I In my spare time, like I've I've I In my spare time, like I've I've always loved like video games as a kid. always loved like video games as a kid. always loved like video games as a kid. I mean, like I talked about with I mean, like I talked about with I mean, like I talked about with Scratch, I mean, I was building like Scratch, I mean, I was building like Scratch, I mean, I was building like Pokémon and and Mario Bros. and stuff. Pokémon and and Mario Bros. and stuff. Pokémon and and Mario Bros. and stuff. And so, like I've actually like been And so, like I've actually like been And so, like I've actually like been doing a little bit of just trying to I doing a little bit of just trying to I doing a little bit of just trying to I mean, I hate to admit it, but vibe code mean, I hate to admit it, but vibe code mean, I hate to admit it, but vibe code video games, right? It's just a hobby. video games, right? It's just a hobby. video games, right? It's just a hobby. I'm not trying to like do something too I'm not trying to like do something too I'm not trying to like do something too crazy. It's more just like having it run crazy. It's more just like having it run crazy. It's more just like having it run in the background for fun. But like one in the background for fun. But like one in the background for fun. But like one of the things I've had to think about is of the things I've had to think about is of the things I've had to think about is like how do I build a harness for the like how do I build a harness for the like how do I build a harness for the coding agent to be able to actually play coding agent to be able to actually play coding agent to be able to actually play the video game. It's a bit trickier cuz the video game. It's a bit trickier cuz the video game. It's a bit trickier cuz it can't Like coding agents, they need it can't Like coding agents, they need it can't Like coding agents, they need time to think, right? So, if you have a time to think, right? So, if you have a time to think, right? So, if you have a game that's running at 60 frames per game that's running at 60 frames per game that's running at 60 frames per second, it's not really going to be able second, it's not really going to be able second, it's not really going to be able to react to things the way that human to react to things the way that human to react to things the way that human would. So, thinking about a system where would. So, thinking about a system where would. So, thinking about a system where it can basically like slow down the it can basically like slow down the it can basically like slow down the frame rate. I know it's kind of like a frame rate. I know it's kind of like a frame rate. I know it's kind of like a silly example, but it's just like that's silly example, but it's just like that's silly example, but it's just like that's one of the biggest things you have to one of the biggest things you have to one of the biggest things you have to engineer for for anything is like how engineer for for anything is like how engineer for for anything is like how would the agent actually verify that as would the agent actually verify that as would the agent actually verify that as a user would? Cuz just like looking at a user would? Cuz just like looking at a user would? Cuz just like looking at the code it creates or the skill it the code it creates or the skill it the code it creates or the skill it builds for you, like that's not enough builds for you, like that's not enough builds for you, like that's not enough for it to just do that sort of like for it to just do that sort of like for it to just do that sort of like review, high-level review, which is review, high-level review, which is review, high-level review, which is good, but like you need a way for it to good, but like you need a way for it to good, but like you need a way for it to really like use the application or really like use the application or really like use the application or whatever you're making as you would.

whatever you're making as you would. whatever you're making as you would. >> Yeah, absolutely. And real quick for >> Yeah, absolutely. And real quick for >> Yeah, absolutely. And real quick for anyone that might not have heard the anyone that might not have heard the anyone that might not have heard the term harness before, what is your kind term harness before, what is your kind term harness before, what is your kind of quick definition of that? of quick definition of that? of quick definition of that? >> Yeah, no, that's good. I appreciate you >> Yeah, no, that's good. I appreciate you >> Yeah, no, that's good. I appreciate you calling me out. Yeah. calling me out. Yeah. calling me out. Yeah. >> It gets It gets [laughter] technical. >> It gets It gets [laughter] technical. >> It gets It gets [laughter] technical. >> Right, yeah. So, um >> Right, yeah. So, um >> Right, yeah. So, um usually when people talk about usually when people talk about usually when people talk about harnesses, they're talking about harnesses, they're talking about harnesses, they're talking about something more like what I was going to something more like what I was going to something more like what I was going to talk about a bit here at the end. talk about a bit here at the end. talk about a bit here at the end. Um so, what I'm talking about as far as Um so, what I'm talking about as far as Um so, what I'm talking about as far as like validation is more like like validation is more like like validation is more like I mean, it's it's kind of I I have to I mean, it's it's kind of I I have to I mean, it's it's kind of I I have to think about like how to actually explain think about like how to actually explain think about like how to actually explain what a harness is. Really, it's it's the what a harness is. Really, it's it's the what a harness is. Really, it's it's the wrapper around the large language model, wrapper around the large language model, wrapper around the large language model, the tools and context that it has access the tools and context that it has access the tools and context that it has access to, so it knows what it's working on and to, so it knows what it's working on and to, so it knows what it's working on and how to work on it effectively. how to work on it effectively. how to work on it effectively. So, if we think of like a harness for AI So, if we think of like a harness for AI So, if we think of like a harness for AI coding, Claude Code is actually a coding, Claude Code is actually a coding, Claude Code is actually a harness, right? Like it when you harness, right? Like it when you harness, right? Like it when you download Claude Code and you run it, it download Claude Code and you run it, it download Claude Code and you run it, it loads a system prompt on top of Claude loads a system prompt on top of Claude loads a system prompt on top of Claude as a large language model, it gives it as a large language model, it gives it as a large language model, it gives it the tools so it can run commands and the tools so it can run commands and the tools so it can run commands and create files on your computer. Um that's create files on your computer. Um that's create files on your computer. Um that's what really makes it a harness. And And what really makes it a harness. And And what really makes it a harness. And And then, when I was giving the example of then, when I was giving the example of then, when I was giving the example of like a harness for testing, it's more like a harness for testing, it's more like a harness for testing, it's more like like like um giving it a system where it's like, um giving it a system where it's like, um giving it a system where it's like, "Okay, these are the commands I can run "Okay, these are the commands I can run "Okay, these are the commands I can run to start the game and then like slow to start the game and then like slow to start the game and then like slow down the frame rate so that I can down the frame rate so that I can down the frame rate so that I can interact with it frame by frame and like interact with it frame by frame and like interact with it frame by frame and like really stop and analyze and think before really stop and analyze and think before really stop and analyze and think before I take another action."

I take another action." I take another action." So, it You can think of it kind of like So, it You can think of it kind of like So, it You can think of it kind of like a So, I mean, maybe I will just jump a So, I mean, maybe I will just jump a So, I mean, maybe I will just jump ahead here. You can think of the harness ahead here. You can think of the harness ahead here. You can think of the harness [laughter] as the thing that just wraps [laughter] as the thing that just wraps [laughter] as the thing that just wraps the model. And then, there's also that the model. And then, there's also that the model. And then, there's also that that component of the harness that you that component of the harness that you that component of the harness that you get to build yourself. I call it the AI get to build yourself. I call it the AI get to build yourself. I call it the AI layer. And so, for Claude Code, that's layer. And so, for Claude Code, that's layer. And so, for Claude Code, that's like your Claude.md and your skills and like your Claude.md and your skills and like your Claude.md and your skills and your hooks and any kind of MCP servers your hooks and any kind of MCP servers your hooks and any kind of MCP servers that you're bringing in to connect it to that you're bringing in to connect it to that you're bringing in to connect it to your other platforms like your CRM or your other platforms like your CRM or your other platforms like your CRM or your task management software, right? your task management software, right? your task management software, right? That's that's building on top of the That's that's building on top of the That's that's building on top of the harness. So, it's kind of like the large harness. So, it's kind of like the large harness. So, it's kind of like the large language model is the reasoning. It's language model is the reasoning. It's language model is the reasoning. It's It's the brain at the center. And then, It's the brain at the center. And then, It's the brain at the center. And then, you pick the tool like Claude Code or you pick the tool like Claude Code or you pick the tool like Claude Code or Codex or whatever, and then you can sort Codex or whatever, and then you can sort Codex or whatever, and then you can sort of like build the context and of like build the context and of like build the context and integrations on top. integrations on top. integrations on top. >> Absolutely. I love it. Yeah, well said. >> Absolutely. I love it. Yeah, well said. >> Absolutely. I love it. Yeah, well said. I think something something fun anyone I think something something fun anyone I think something something fun anyone listening should try real quick is if listening should try real quick is if listening should try real quick is if you go to an AI model and ask it to you go to an AI model and ask it to you go to an AI model and ask it to explain an AI harness or an agent explain an AI harness or an agent explain an AI harness or an agent harness, I would be willing to bet it harness, I would be willing to bet it harness, I would be willing to bet it does the whole car analogy where the does the whole car analogy where the does the whole car analogy where the engine is the AI model [laughter] and engine is the AI model [laughter] and engine is the AI model [laughter] and the car is the harness. So, let me know the car is the harness. So, let me know the car is the harness. So, let me know if you guys run that and and see if if you guys run that and and see if if you guys run that and and see if that's what you get. that's what you get. that's what you get. >> [laughter] >> [laughter] >> [laughter] >> Sounds good. I mean, we could we could >> Sounds good. I mean, we could we could >> Sounds good. I mean, we could we could test it right now.

test it right now. test it right now. No, no. We won't we don't need to do it No, no. We won't we don't need to do it No, no. We won't we don't need to do it right now. But yeah, that's that's your right now. But yeah, that's that's your right now. But yeah, that's that's your homework for today. homework for today. homework for today. >> Yeah. >> Yeah. >> Yeah. >> [laughter] >> [laughter] >> [laughter] >> Yeah. >> Yeah. >> Yeah. Yeah, cool. Yeah, cool. Yeah, cool. Um yeah, so we're I mean, we we talked Um yeah, so we're I mean, we we talked Um yeah, so we're I mean, we we talked about like validation a lot. Um planning about like validation a lot. Um planning about like validation a lot. Um planning is the other thing that I really want to is the other thing that I really want to is the other thing that I really want to hit on cuz most people don't do enough hit on cuz most people don't do enough hit on cuz most people don't do enough of it. of it. >> [clears throat] >> And it takes it takes patience. And this >> And it takes it takes patience. And this >> And it takes it takes patience. And this is like one of those um software is like one of those um software is like one of those um software engineering disciplines that I like to engineering disciplines that I like to engineering disciplines that I like to bring into um even when I'm talking to bring into um even when I'm talking to bring into um even when I'm talking to someone who is not writing code or who someone who is not writing code or who someone who is not writing code or who isn't technical. isn't technical. isn't technical. Cuz you have to spend I mean, with Cuz you have to spend I mean, with Cuz you have to spend I mean, with coding agents, you spend more time coding agents, you spend more time coding agents, you spend more time planning than you actually do building planning than you actually do building planning than you actually do building because you you really put a lot of your because you you really put a lot of your because you you really put a lot of your effort up front into the plan and then effort up front into the plan and then effort up front into the plan and then you use that to delegate as much of the you use that to delegate as much of the you use that to delegate as much of the coding as you possibly can or for a lot coding as you possibly can or for a lot coding as you possibly can or for a lot of us all of the coding to the AI coding of us all of the coding to the AI coding of us all of the coding to the AI coding assistant. And so, its success is really assistant. And so, its success is really assistant. And so, its success is really just dependent on how good is your plan. just dependent on how good is your plan. just dependent on how good is your plan. Usually, you have some kind of like a Usually, you have some kind of like a Usually, you have some kind of like a lot of people like using markdown, lot of people like using markdown, lot of people like using markdown, right? I use markdown a lot. So, I'll right? I use markdown a lot. So, I'll right? I use markdown a lot. So, I'll have like a single markdown document have like a single markdown document have like a single markdown document that outlines that outlines that outlines um you know, like the goal, what are we um you know, like the goal, what are we um you know, like the goal, what are we building here? What does success building here? What does success building here? What does success actually look like? And like of course actually look like? And like of course actually look like? And like of course with that comes the validation strategy with that comes the validation strategy with that comes the validation strategy um that we've already talked about. So, um that we've already talked about. So, um that we've already talked about. So, how does it know that's uh the work is how does it know that's uh the work is how does it know that's uh the work is done and working well? And then um not done and working well? And then um not done and working well? And then um not to get like too technical here, but to get like too technical here, but to get like too technical here, but especially more for any kind of like especially more for any kind of like especially more for any kind of like coding task, you're going to have like coding task, you're going to have like coding task, you're going to have like the integration points, right? Like if the integration points, right? Like if the integration points, right? Like if you're building on top of an existing you're building on top of an existing you're building on top of an existing automation or application or website, automation or application or website, automation or application or website, whatever, like what are the parts of the whatever, like what are the parts of the whatever, like what are the parts of the code base that we actually have to code base that we actually have to code base that we actually have to touch? And so, if you are more touch? And so, if you are more touch? And so, if you are more technical, you can sort of evaluate like technical, you can sort of evaluate like technical, you can sort of evaluate like make sure it's understanding is correct make sure it's understanding is correct make sure it's understanding is correct of like, okay, what files are we really

of like, okay, what files are we really of like, okay, what files are we really going to create and edit here? going to create and edit here? going to create and edit here? Not that you need that. Um and then once Not that you need that. Um and then once Not that you need that. Um and then once you have that plan, then this is kind of you have that plan, then this is kind of you have that plan, then this is kind of what my workflow looks like. And then what my workflow looks like. And then what my workflow looks like. And then this is for anything. So you you do some this is for anything. So you you do some this is for anything. So you you do some kind of like context loading up front, kind of like context loading up front, kind of like context loading up front, any sorts of like documents that your any sorts of like documents that your any sorts of like documents that your agent needs related to the task at hand. agent needs related to the task at hand. agent needs related to the task at hand. And then I'll typically have it do some And then I'll typically have it do some And then I'll typically have it do some kind of research, usually using sub kind of research, usually using sub kind of research, usually using sub agents for that. So if I'm building a agents for that. So if I'm building a agents for that. So if I'm building a new application, maybe I'll have one sub new application, maybe I'll have one sub new application, maybe I'll have one sub agent research what's a good tech stack agent research what's a good tech stack agent research what's a good tech stack for this. What's a good like approach for this. What's a good like approach for this. What's a good like approach are people that have built similar are people that have built similar are people that have built similar applications, right? So like especially applications, right? So like especially applications, right? So like especially if you're not as technical, that could if you're not as technical, that could if you're not as technical, that could be really useful for it to just gather a be really useful for it to just gather a be really useful for it to just gather a lot of information and then propose a lot of information and then propose a lot of information and then propose a plan to you. And so that's when you you plan to you. And so that's when you you plan to you. And so that's when you you create the plan with the coding agent. create the plan with the coding agent. create the plan with the coding agent. And this is also where usually you want And this is also where usually you want And this is also where usually you want to have the coding agent ask you a lot to have the coding agent ask you a lot to have the coding agent ask you a lot of questions. Like I know Nate, you just of questions. Like I know Nate, you just of questions. Like I know Nate, you just put out a video today on Matt Pocock's put out a video today on Matt Pocock's put out a video today on Matt Pocock's grill me skill, which is really good. grill me skill, which is really good. grill me skill, which is really good. Like you need to make sure that you that Like you need to make sure that you that Like you need to make sure that you that the coding agent is not assuming a ton the coding agent is not assuming a ton the coding agent is not assuming a ton of things about what you want it to do. of things about what you want it to do. of things about what you want it to do. Like the workflow you want to build, the Like the workflow you want to build, the Like the workflow you want to build, the skill you want to build, whatever. And skill you want to build, whatever. And skill you want to build, whatever. And so having it ask you a lot of questions so having it ask you a lot of questions so having it ask you a lot of questions to clarify those things is good. So that to clarify those things is good. So that to clarify those things is good. So that way you can be confident that once you way you can be confident that once you way you can be confident that once you have that final plan, like this is about have that final plan, like this is about have that final plan, like this is about this is what we're going to go and do this is what we're going to go and do this is what we're going to go and do now, that both you and the coding agent now, that both you and the coding agent now, that both you and the coding agent are aligned on what's actually going to are aligned on what's actually going to are aligned on what's actually going to be done and and how you're going to be done and and how you're going to be done and and how you're going to validate it.

validate it. validate it. >> Absolutely. Yeah, I love it. When you do >> Absolutely. Yeah, I love it. When you do >> Absolutely. Yeah, I love it. When you do that, are you typically using in Cloud that, are you typically using in Cloud that, are you typically using in Cloud Code plan mode or are you kind of Code plan mode or are you kind of Code plan mode or are you kind of planning but not in plan mode? planning but not in plan mode? planning but not in plan mode? >> Yeah, usually I don't use plan mode. >> Yeah, usually I don't use plan mode. >> Yeah, usually I don't use plan mode. >> Okay. >> Okay. >> Okay. >> It's it's good, but plan mode like puts >> It's it's good, but plan mode like puts >> It's it's good, but plan mode like puts Cloud Code into a bit of a different Cloud Code into a bit of a different Cloud Code into a bit of a different behavior that I'd rather be able to behavior that I'd rather be able to behavior that I'd rather be able to control my control my control my control more myself. So my skill for control more myself. So my skill for control more myself. So my skill for planning is like instructions for how I planning is like instructions for how I planning is like instructions for how I want it to ask me questions and then want it to ask me questions and then want it to ask me questions and then just like generally how I want to go just like generally how I want to go just like generally how I want to go about researching and organizing things about researching and organizing things about researching and organizing things into a plan. And so like I want to into a plan. And so like I want to into a plan. And so like I want to define the sections. If you don't, then define the sections. If you don't, then define the sections. If you don't, then you're just using Cloud Code's plan you're just using Cloud Code's plan you're just using Cloud Code's plan mode. Like it'll build something mode. Like it'll build something mode. Like it'll build something actually pretty much like this. actually pretty much like this. actually pretty much like this. But I just like having that more But I just like having that more But I just like having that more that that higher level of control. I that that higher level of control. I that that higher level of control. I think that's a theme that you get a lot think that's a theme that you get a lot think that's a theme that you get a lot through my content in general is that I through my content in general is that I through my content in general is that I I like to have control and I like to have control and I like to have control and customizability cuz in the end that's customizability cuz in the end that's customizability cuz in the end that's how you get the best results. It's just how you get the best results. It's just how you get the best results. It's just it's kind of like that learning curve to it's kind of like that learning curve to it's kind of like that learning curve to get to the point. Like for example, I I get to the point. Like for example, I I get to the point. Like for example, I I don't use open claw or Hermes. I have my don't use open claw or Hermes. I have my don't use open claw or Hermes. I have my own second brain that literally is just own second brain that literally is just own second brain that literally is just built directly on top of Claude code.

built directly on top of Claude code. built directly on top of Claude code. And I'm a big proponent of that even And I'm a big proponent of that even And I'm a big proponent of that even though those other open source tools are though those other open source tools are though those other open source tools are very powerful very powerful very powerful because you're running something that because you're running something that because you're running something that you don't understand and it's harder for you don't understand and it's harder for you don't understand and it's harder for you to like really take as your own and you to like really take as your own and you to like really take as your own and it's not like a foundational component it's not like a foundational component it's not like a foundational component that you can create your own system on that you can create your own system on that you can create your own system on top of. So you're more like adopting top of. So you're more like adopting top of. So you're more like adopting someone else's system and these tools someone else's system and these tools someone else's system and these tools have done a really really good job have done a really really good job have done a really really good job making it easy to extend and and really making it easy to extend and and really making it easy to extend and and really make your own. But like in the end make your own. But like in the end make your own. But like in the end building something from the ground up is building something from the ground up is building something from the ground up is always going to give you the most always going to give you the most always going to give you the most control even though that can be pretty control even though that can be pretty control even though that can be pretty daunting. daunting. daunting. >> Yeah, I hear you. Yeah, that's >> Yeah, I hear you. Yeah, that's >> Yeah, I hear you. Yeah, that's interesting. It I mean it it really does interesting. It I mean it it really does interesting. It I mean it it really does make sense. I always love make sense. I always love make sense. I always love you know, that's something I just say a you know, that's something I just say a you know, that's something I just say a lot which is a very simple lot which is a very simple lot which is a very simple theory is just to be theory is just to be theory is just to be genuinely curious to understand what's genuinely curious to understand what's genuinely curious to understand what's going on especially when going on especially when going on especially when I don't understand what these lines of I don't understand what these lines of I don't understand what these lines of Python code that it that just got Python code that it that just got Python code that it that just got written mean, you know, and the whole written mean, you know, and the whole written mean, you know, and the whole idea of dark code. idea of dark code. idea of dark code. And I guess what do you think about that And I guess what do you think about that And I guess what do you think about that whole idea cuz I know you talk a lot whole idea cuz I know you talk a lot whole idea cuz I know you talk a lot about vibe coding and and preaching about vibe coding and and preaching about vibe coding and and preaching understanding things at their core. So understanding things at their core. So understanding things at their core. So when someone is generating automations when someone is generating automations when someone is generating automations or code that they don't or code that they don't or code that they don't understand how to read understand how to read understand how to read how do they actually how do they actually how do they actually feel secure and safe about that?

feel secure and safe about that? feel secure and safe about that? Yeah, that's a really good question. Yeah, that's a really good question. Yeah, that's a really good question. >> Pretty loaded too. >> Pretty loaded too. >> Pretty loaded too. >> [laughter] >> [laughter] >> [laughter] >> No no, it's it's good. I I welcome it. >> No no, it's it's good. I I welcome it. >> No no, it's it's good. I I welcome it. So I'll I'll answer in two ways. I'll So I'll I'll answer in two ways. I'll So I'll I'll answer in two ways. I'll answer first by saying that like answer first by saying that like answer first by saying that like maybe not everyone loves to hear this maybe not everyone loves to hear this maybe not everyone loves to hear this but I can if you are using AI coding but I can if you are using AI coding but I can if you are using AI coding assistant to write code cuz you're assistant to write code cuz you're assistant to write code cuz you're building your second brain, you're building your second brain, you're building your second brain, you're creating automations, whatever it is, I creating automations, whatever it is, I creating automations, whatever it is, I would recommend at least trying to get would recommend at least trying to get would recommend at least trying to get to the point where you can understand to the point where you can understand to the point where you can understand the code. And really at first that can the code. And really at first that can the code. And really at first that can be as simple as just asking Claude Code be as simple as just asking Claude Code be as simple as just asking Claude Code or whatever coding agent to explain what or whatever coding agent to explain what or whatever coding agent to explain what it just wrote. it just wrote. it just wrote. Because code can look pretty Because code can look pretty Because code can look pretty intimidating, but when you get over that intimidating, but when you get over that intimidating, but when you get over that like initial hump, like it kind of reads like initial hump, like it kind of reads like initial hump, like it kind of reads like English. And maybe that's just me like English. And maybe that's just me like English. And maybe that's just me being extremely ignorant because I've being extremely ignorant because I've being extremely ignorant because I've lived and breathed it since I was 8 lived and breathed it since I was 8 lived and breathed it since I was 8 years old, but it starts like as long as years old, but it starts like as long as years old, but it starts like as long as you understand that like this is a you understand that like this is a you understand that like this is a class, this is a while loop, this is a class, this is a while loop, this is a class, this is a while loop, this is a if statement, like it starts to read if statement, like it starts to read if statement, like it starts to read like English. You're like, okay, I like English. You're like, okay, I like English. You're like, okay, I understand when this part of the code is understand when this part of the code is understand when this part of the code is going to execute now. You're just asking going to execute now. You're just asking going to execute now. You're just asking your coding agent constantly. And so I your coding agent constantly. And so I your coding agent constantly. And so I mean like in Claude Code there's the mean like in Claude Code there's the mean like in Claude Code there's the slash by the way feature. So like you slash by the way feature. So like you slash by the way feature. So like you can always just kind of have a side car can always just kind of have a side car can always just kind of have a side car conversation where it's like, hey, help conversation where it's like, hey, help conversation where it's like, hey, help me understand like what the heck is me understand like what the heck is me understand like what the heck is going on right here. And then it doesn't going on right here. And then it doesn't going on right here. And then it doesn't have to to dilute your main context and have to to dilute your main context and have to to dilute your main context and just kind of like just kind of like just kind of like keep throwing context at Claude Code. If keep throwing context at Claude Code. If keep throwing context at Claude Code. If you can have that separate conversation you can have that separate conversation you can have that separate conversation for your own understanding and then go for your own understanding and then go for your own understanding and then go back to the main task at hand without it back to the main task at hand without it back to the main task at hand without it being affected.

being affected. being affected. So I would recommend that. And then, you So I would recommend that. And then, you So I would recommend that. And then, you know, someone is really not inclined to know, someone is really not inclined to know, someone is really not inclined to learn how to code, like that's just not learn how to code, like that's just not learn how to code, like that's just not your goal. You want to use Claude Code your goal. You want to use Claude Code your goal. You want to use Claude Code to automate things and not have to like to automate things and not have to like to automate things and not have to like engineer applications. I totally get engineer applications. I totally get engineer applications. I totally get that as well. Really comes down to your that as well. Really comes down to your that as well. Really comes down to your validation strategies what's going to validation strategies what's going to validation strategies what's going to dictate how confident you can really be dictate how confident you can really be dictate how confident you can really be in what is created. So if you're in what is created. So if you're in what is created. So if you're spending a lot of time and this is why I spending a lot of time and this is why I spending a lot of time and this is why I say like whenever you're building say like whenever you're building say like whenever you're building something with Claude Code, the way that something with Claude Code, the way that something with Claude Code, the way that you don't vibe code is that you sandwich you don't vibe code is that you sandwich you don't vibe code is that you sandwich the delegation of the coding between the the delegation of the coding between the the delegation of the coding between the planning and the validation process that planning and the validation process that planning and the validation process that you're heavily involved with. you're heavily involved with. you're heavily involved with. Right? Like the only reason I'm ever Right? Like the only reason I'm ever Right? Like the only reason I'm ever going to say, all right, Claude, go rip going to say, all right, Claude, go rip going to say, all right, Claude, go rip through this is because I made sure I through this is because I made sure I through this is because I made sure I created a really detailed spec and I've created a really detailed spec and I've created a really detailed spec and I've defined like this is how you're going to defined like this is how you're going to defined like this is how you're going to tell me that you're done and how you can tell me that you're done and how you can tell me that you're done and how you can be confident that you actually are. be confident that you actually are. be confident that you actually are. >> I love it. Very well said. Nothing to >> I love it. Very well said. Nothing to >> I love it. Very well said. Nothing to Nothing to add there. Nothing to add there. Nothing to add there. >> Cool. All right, sounds good. >> Cool. All right, sounds good. >> Cool. All right, sounds good. Yeah. Yeah. Yeah. Um yeah, as far as like creating that Um yeah, as far as like creating that Um yeah, as far as like creating that plan with the coding agent, the most plan with the coding agent, the most plan with the coding agent, the most important thing is to manage the important thing is to manage the important thing is to manage the context. Like what your coding agent is context. Like what your coding agent is context. Like what your coding agent is going to really be paying attention to going to really be paying attention to going to really be paying attention to at the start of any kind of planning at the start of any kind of planning at the start of any kind of planning session.

session. session. So, the the thing here is that attention So, the the thing here is that attention So, the the thing here is that attention is scarce. is scarce. is scarce. And so, there's a big misconception And so, there's a big misconception And so, there's a big misconception right now for a lot of people where they right now for a lot of people where they right now for a lot of people where they think that like it doesn't really matter think that like it doesn't really matter think that like it doesn't really matter how much you throw at a coding agent how much you throw at a coding agent how much you throw at a coding agent because everyone is hearing nowadays how because everyone is hearing nowadays how because everyone is hearing nowadays how like large language models can support like large language models can support like large language models can support up to 1 million tokens in their context up to 1 million tokens in their context up to 1 million tokens in their context when they're like, "Oh, that That's like when they're like, "Oh, that That's like when they're like, "Oh, that That's like the Harry Potter book five times over." the Harry Potter book five times over." the Harry Potter book five times over." I forget the exact I forget the exact I forget the exact >> [laughter] >> [laughter] >> [laughter] >> but people like always throw like some >> but people like always throw like some >> but people like always throw like some some analogy where it just like makes it some analogy where it just like makes it some analogy where it just like makes it pretty obvious where it's like 1 million pretty obvious where it's like 1 million pretty obvious where it's like 1 million tokens is an insane amount of tokens is an insane amount of tokens is an insane amount of information. And it actually is, but information. And it actually is, but information. And it actually is, but there's two massive caveats here. The there's two massive caveats here. The there's two massive caveats here. The first one first one first one is that that context will go way faster is that that context will go way faster is that that context will go way faster than you think. Cuz if it's reading than you think. Cuz if it's reading than you think. Cuz if it's reading through through through um a bunch of skills that you set up for um a bunch of skills that you set up for um a bunch of skills that you set up for it or a bunch of code, that can be tens it or a bunch of code, that can be tens it or a bunch of code, that can be tens of hundreds of thousands of tokens very of hundreds of thousands of tokens very of hundreds of thousands of tokens very quickly. And then the other thing is uh quickly. And then the other thing is uh quickly. And then the other thing is uh large language models have what's called large language models have what's called large language models have what's called the dumb zone. the dumb zone. the dumb zone. And so, you have the the little bit of And so, you have the the little bit of And so, you have the the little bit of context up front. Maybe I can just draw context up front. Maybe I can just draw context up front. Maybe I can just draw like a quick little analogy here. So, if like a quick little analogy here. So, if like a quick little analogy here. So, if like this is Oh, that is a like this is Oh, that is a like this is Oh, that is a fat marker. Um fat marker. Um fat marker. Um All right. Okay, I'm I give up already.

All right. Okay, I'm I give up already. All right. Okay, I'm I give up already. I'm not going [laughter] to try that. I'm not going [laughter] to try that. I'm not going [laughter] to try that. Okay, so you you you have to imagine Okay, so you you you have to imagine Okay, so you you you have to imagine this with me here, but imagine you have this with me here, but imagine you have this with me here, but imagine you have a box that represents the the LLM's a box that represents the the LLM's a box that represents the the LLM's context window. You have that initial context window. You have that initial context window. You have that initial part at the start of the conversation up part at the start of the conversation up part at the start of the conversation up to the first, you know, 100 or 200,000 to the first, you know, 100 or 200,000 to the first, you know, 100 or 200,000 tokens where the large language model tokens where the large language model tokens where the large language model feels very sharp, or at least it feels feels very sharp, or at least it feels feels very sharp, or at least it feels like it's at its best. like it's at its best. like it's at its best. Once the conversation surpasses that Once the conversation surpasses that Once the conversation surpasses that first 100, 200,000 tokens, obviously it first 100, 200,000 tokens, obviously it first 100, 200,000 tokens, obviously it depends on the model. When you reach the depends on the model. When you reach the depends on the model. When you reach the dumb zone, you get to the point where it dumb zone, you get to the point where it dumb zone, you get to the point where it just feels like it's overloaded with just feels like it's overloaded with just feels like it's overloaded with information and it starts missing things information and it starts missing things information and it starts missing things and making mistakes that seem so obvious and making mistakes that seem so obvious and making mistakes that seem so obvious to you. Or like the kind of thing where to you. Or like the kind of thing where to you. Or like the kind of thing where you're like, if I had had a fresh you're like, if I had had a fresh you're like, if I had had a fresh context here, like there's no way it context here, like there's no way it context here, like there's no way it would have made that mistake. Like it would have made that mistake. Like it would have made that mistake. Like it writes a really bad line of code or it writes a really bad line of code or it writes a really bad line of code or it doesn't use a skill that you thought it doesn't use a skill that you thought it doesn't use a skill that you thought it should have known to use, right? Like should have known to use, right? Like should have known to use, right? Like that kind of thing if it's in the middle that kind of thing if it's in the middle that kind of thing if it's in the middle of a larger workflow. of a larger workflow. of a larger workflow. And so that that's why I say attention And so that that's why I say attention And so that that's why I say attention is scarce. Like don't don't get to under is scarce. Like don't don't get to under is scarce. Like don't don't get to under that false notion that you don't really that false notion that you don't really that false notion that you don't really have to care about how much you give it.

have to care about how much you give it. have to care about how much you give it. Like if you're trying to have it handle Like if you're trying to have it handle Like if you're trying to have it handle a larger workflow, you still have to you a larger workflow, you still have to you a larger workflow, you still have to you have to be very careful like what you have to be very careful like what you have to be very careful like what you give it up front versus what you allow give it up front versus what you allow give it up front versus what you allow it to discover when it actually needs. it to discover when it actually needs. it to discover when it actually needs. Like that's one of the most important Like that's one of the most important Like that's one of the most important things with skills with Claude is you're things with skills with Claude is you're things with skills with Claude is you're giving it procedures and best practices, giving it procedures and best practices, giving it procedures and best practices, but it gets to decide like, okay, now I but it gets to decide like, okay, now I but it gets to decide like, okay, now I need to rely on this process or this need to rely on this process or this need to rely on this process or this information. So you're not just dumping information. So you're not just dumping information. So you're not just dumping a bunch of things up front. a bunch of things up front. a bunch of things up front. A lot of people do that like even with A lot of people do that like even with A lot of people do that like even with MCP servers back in the day. They would MCP servers back in the day. They would MCP servers back in the day. They would they would connect their like 20 MCP they would connect their like 20 MCP they would connect their like 20 MCP servers to Claude code and each one of servers to Claude code and each one of servers to Claude code and each one of them was was them was was them was was filling the context with like 20,000 filling the context with like 20,000 filling the context with like 20,000 tokens up front of information cuz it tokens up front of information cuz it tokens up front of information cuz it has like all of the tool calls or the has like all of the tool calls or the has like all of the tool calls or the tools that come with the MCP server. And tools that come with the MCP server. And tools that come with the MCP server. And so their large language model would so their large language model would so their large language model would always act super dumb. And so they're always act super dumb. And so they're always act super dumb. And so they're like, I'm using the latest Opus, like like, I'm using the latest Opus, like like, I'm using the latest Opus, like why am I getting terrible results? And why am I getting terrible results? And why am I getting terrible results? And it's really it comes down to just how it's really it comes down to just how it's really it comes down to just how much of the context is filled right much of the context is filled right much of the context is filled right away. away. away. >> Yeah. Oh my gosh, it drives me nuts. It >> Yeah. Oh my gosh, it drives me nuts. It >> Yeah. Oh my gosh, it drives me nuts. It it truly drives me crazy when you hear it truly drives me crazy when you hear it truly drives me crazy when you hear people blaming the model when it really people blaming the model when it really people blaming the model when it really is kind of a skills problem. And we see is kind of a skills problem. And we see is kind of a skills problem. And we see this at this at this at you know, when you look at these studies you know, when you look at these studies you know, when you look at these studies and surveys too about business adoption and surveys too about business adoption and surveys too about business adoption where it really is where it really is where it really is these people either have not yet felt these people either have not yet felt these people either have not yet felt the ROI because they can't the ROI because they can't the ROI because they can't they don't know enough about how to use they don't know enough about how to use they don't know enough about how to use it truly.

it truly. it truly. >> Right. >> Right. >> Right. >> And >> And >> And also people claiming that they have the also people claiming that they have the also people claiming that they have the skills to, but they're just not doing skills to, but they're just not doing skills to, but they're just not doing it. And like the adoption is then it. And like the adoption is then it. And like the adoption is then another problem. But I mean, obviously another problem. But I mean, obviously another problem. But I mean, obviously I'm not doing I'm not doing I'm not doing heavy heavy coding, building software heavy heavy coding, building software heavy heavy coding, building software and and apps. But, you know, we're doing and and apps. But, you know, we're doing and and apps. But, you know, we're doing some pretty cool things. And I've seen some pretty cool things. And I've seen some pretty cool things. And I've seen some people do some really awesome some people do some really awesome some people do some really awesome things. And it's just things. And it's just things. And it's just >> Yeah. >> Yeah. >> Yeah. >> there's a lot of things like, you know, >> there's a lot of things like, you know, >> there's a lot of things like, you know, if you kind of think about your your if you kind of think about your your if you kind of think about your your diagram that you had, you got the model diagram that you had, you got the model diagram that you had, you got the model in the middle, you got the agent in the middle, you got the agent in the middle, you got the agent hardness around that, and then obviously hardness around that, and then obviously hardness around that, and then obviously a huge layer is what you put in there as a huge layer is what you put in there as a huge layer is what you put in there as well. And the way that you manage your well. And the way that you manage your well. And the way that you manage your stuff. And I think that the 1 million stuff. And I think that the 1 million stuff. And I think that the 1 million context window, specifically for, you context window, specifically for, you context window, specifically for, you know, like let's just say Opus 4.8 at know, like let's just say Opus 4.8 at know, like let's just say Opus 4.8 at the moment, obviously it's great, but it the moment, obviously it's great, but it the moment, obviously it's great, but it definitely comes with a false sense of definitely comes with a false sense of definitely comes with a false sense of security. But people now thinking that security. But people now thinking that security. But people now thinking that they have the million. But they have the million. But they have the million. But when when when and I know this might be outdated by and I know this might be outdated by and I know this might be outdated by next month or 2 months away. But let's next month or 2 months away. But let's next month or 2 months away. But let's say you right now when you're in Cloud say you right now when you're in Cloud say you right now when you're in Cloud Code, when do you typically Code, when do you typically Code, when do you typically do your compact or a session handoff and do your compact or a session handoff and do your compact or a session handoff and clear, and when do you get out of there? clear, and when do you get out of there? clear, and when do you get out of there? >> Yeah, so with Opus right now, >> Yeah, so with Opus right now, >> Yeah, so with Opus right now, it's usually around 250,000 tokens that it's usually around 250,000 tokens that it's usually around 250,000 tokens that I feel like it gets into the dumb I feel like it gets into the dumb I feel like it gets into the dumb >> That's my exact number, too.

>> That's my exact number, too. >> That's my exact number, too. >> Oh, really? Okay, yeah, yeah. Good. >> Oh, really? Okay, yeah, yeah. Good. >> Oh, really? Okay, yeah, yeah. Good. Cool. So, and that, by the way, is like Cool. So, and that, by the way, is like Cool. So, and that, by the way, is like really subjective. Like, I'm not going really subjective. Like, I'm not going really subjective. Like, I'm not going to um to um to um bet a million dollars on on like the on bet a million dollars on on like the on bet a million dollars on on like the on Boris Cherny or someone saying like, you Boris Cherny or someone saying like, you Boris Cherny or someone saying like, you know, it's also 250,000 like know, it's also 250,000 like know, it's also 250,000 like >> Quarter million is clean, right? >> Quarter million is clean, right? >> Quarter million is clean, right? >> Yeah, it just it it sounds good. And it >> Yeah, it just it it sounds good. And it >> Yeah, it just it it sounds good. And it is like pretty accurate, I would say. is like pretty accurate, I would say. is like pretty accurate, I would say. Like, Opus 4.7 was around like 200,000. Like, Opus 4.7 was around like 200,000. Like, Opus 4.7 was around like 200,000. And then like Sonnet 4.6 is like And then like Sonnet 4.6 is like And then like Sonnet 4.6 is like honestly probably only like 100 125,000. honestly probably only like 100 125,000. honestly probably only like 100 125,000. Um like it as you go to these smaller Um like it as you go to these smaller Um like it as you go to these smaller models, like the dumb zone becomes a models, like the dumb zone becomes a models, like the dumb zone becomes a pretty small amount of context relative pretty small amount of context relative pretty small amount of context relative to like what it theoretically can to like what it theoretically can to like what it theoretically can handle. You just never want to get to handle. You just never want to get to handle. You just never want to get to that point. that point. that point. >> So, then with the dumb zone thing, I've >> So, then with the dumb zone thing, I've >> So, then with the dumb zone thing, I've also heard stuff about the model being also heard stuff about the model being also heard stuff about the model being really good at remembering things that really good at remembering things that really good at remembering things that are at the front and the very end. And are at the front and the very end. And are at the front and the very end. And the middle is where it loses. So, where the middle is where it loses. So, where the middle is where it loses. So, where does that play into the whole dumb zone does that play into the whole dumb zone does that play into the whole dumb zone conversation? conversation? conversation? >> Yeah, so basically that issue is just >> Yeah, so basically that issue is just >> Yeah, so basically that issue is just amplified the more you get into the dumb amplified the more you get into the dumb amplified the more you get into the dumb zone. Yeah, and um yeah, as far as like zone. Yeah, and um yeah, as far as like zone. Yeah, and um yeah, as far as like I mean we don't have to get into like I mean we don't have to get into like I mean we don't have to get into like the super technical details for how the the super technical details for how the the super technical details for how the attention mechanism works for LLMs, attention mechanism works for LLMs, attention mechanism works for LLMs, [laughter] but yeah, you could think of [laughter] but yeah, you could think of [laughter] but yeah, you could think of it I mean like the analogy I always like it I mean like the analogy I always like it I mean like the analogy I always like to use is the needle in the haystack to use is the needle in the haystack to use is the needle in the haystack problem. Yeah. Like if you have that problem. Yeah. Like if you have that problem. Yeah. Like if you have that like little piece of information that like little piece of information that like little piece of information that you want the agent to remember in the you want the agent to remember in the you want the agent to remember in the middle of a massive conversation, it's middle of a massive conversation, it's middle of a massive conversation, it's like trying to find a needle in the like trying to find a needle in the like trying to find a needle in the haystack. Like you can't expect the haystack. Like you can't expect the haystack. Like you can't expect the model to just cuz of the way that large model to just cuz of the way that large model to just cuz of the way that large language models are engineered, language models are engineered, language models are engineered, um you can't expect it to like always be um you can't expect it to like always be um you can't expect it to like always be able to pick out that little piece of able to pick out that little piece of able to pick out that little piece of information.

information. information. >> 100% yeah. >> 100% yeah. >> 100% yeah. >> Yeah, I wish it could. That would be >> Yeah, I wish it could. That would be >> Yeah, I wish it could. That would be nice. If there wasn't such thing as a nice. If there wasn't such thing as a nice. If there wasn't such thing as a dumb zone, it would make it much more dumb zone, it would make it much more dumb zone, it would make it much more convenient for us to hand it massive convenient for us to hand it massive convenient for us to hand it massive tasks and let it just rip through tasks and let it just rip through tasks and let it just rip through things, but a lot of the reason we have things, but a lot of the reason we have things, but a lot of the reason we have to create a harness. And like a lot of to create a harness. And like a lot of to create a harness. And like a lot of the things I'm focusing on right now on the things I'm focusing on right now on the things I'm focusing on right now on my channel and just like generally what my channel and just like generally what my channel and just like generally what I'm building is creating harnesses that I'm building is creating harnesses that I'm building is creating harnesses that build a workflow that combine multiple build a workflow that combine multiple build a workflow that combine multiple coding agent sessions together. coding agent sessions together. coding agent sessions together. And so basically it's like one model And so basically it's like one model And so basically it's like one model does the planning and then my does the planning and then my does the planning and then my orchestrator will like automatically orchestrator will like automatically orchestrator will like automatically take that handoff document, like the take that handoff document, like the take that handoff document, like the plan, and then feed it into another plan, and then feed it into another plan, and then feed it into another agent for implementation. And then when agent for implementation. And then when agent for implementation. And then when the implementation is done, it'll create the implementation is done, it'll create the implementation is done, it'll create like an execution report and then it'll like an execution report and then it'll like an execution report and then it'll hand that off to the next agent to hand that off to the next agent to hand that off to the next agent to validate things and do a code review. validate things and do a code review. validate things and do a code review. And it might sound like like that's a And it might sound like like that's a And it might sound like like that's a lot of engineering and it is, but it's lot of engineering and it is, but it's lot of engineering and it is, but it's very necessary right now because if very necessary right now because if very necessary right now because if you're trying to do any kind of like you're trying to do any kind of like you're trying to do any kind of like real work for like production grade real work for like production grade real work for like production grade software or building an automation software or building an automation software or building an automation that's like critical for your business, that's like critical for your business, that's like critical for your business, you can't just throw the whole thing at you can't just throw the whole thing at you can't just throw the whole thing at a single Claude code session unless you a single Claude code session unless you a single Claude code session unless you can like confidently build it in that um can like confidently build it in that um can like confidently build it in that um that zone that you have before you get that zone that you have before you get that zone that you have before you get to the dumb zone. And most of the time to the dumb zone. And most of the time to the dumb zone. And most of the time you just can't do that or at least you you just can't do that or at least you you just can't do that or at least you can't really trust that's going to be can't really trust that's going to be can't really trust that's going to be the case cuz you never know how much the case cuz you never know how much the case cuz you never know how much it's going to have to iterate on it's going to have to iterate on it's going to have to iterate on something. Mhm. So, that's why I'm something. Mhm. So, that's why I'm something. Mhm. So, that's why I'm really like I guess you could say really like I guess you could say really like I guess you could say bullish right now on um harness bullish right now on um harness bullish right now on um harness engineering, which is like building a engineering, which is like building a engineering, which is like building a the workflow that orchestrates many the workflow that orchestrates many the workflow that orchestrates many coding agent sessions to handle a larger coding agent sessions to handle a larger coding agent sessions to handle a larger task. And like a really basic example of task. And like a really basic example of task. And like a really basic example of that kind of harness is the Ralph loop.

that kind of harness is the Ralph loop. that kind of harness is the Ralph loop. It went like super viral the start of It went like super viral the start of It went like super viral the start of this year. this year. this year. So I feel I feel like even if you So I feel I feel like even if you So I feel I feel like even if you haven't heard too much about harness haven't heard too much about harness haven't heard too much about harness engineering, you probably have at least engineering, you probably have at least engineering, you probably have at least heard of the Ralph loop. And that's like heard of the Ralph loop. And that's like heard of the Ralph loop. And that's like really like the foundation of that kind really like the foundation of that kind really like the foundation of that kind of harness, right? Like the Ralph loop of harness, right? Like the Ralph loop of harness, right? Like the Ralph loop is stringing together multiple coding is stringing together multiple coding is stringing together multiple coding agent sessions. I I wish I had one of my agent sessions. I I wish I had one of my agent sessions. I I wish I had one of my diagrams up for this right now. I wish I diagrams up for this right now. I wish I diagrams up for this right now. I wish I had to explain it verbally, but like, had to explain it verbally, but like, had to explain it verbally, but like, you know, basically, you have the first you know, basically, you have the first you know, basically, you have the first Claude code session read in your larger Claude code session read in your larger Claude code session read in your larger spec for like a bigger automation you spec for like a bigger automation you spec for like a bigger automation you want to build. want to build. want to build. And then it'll define like the the task And then it'll define like the the task And then it'll define like the the task list. Like first phase is this, second list. Like first phase is this, second list. Like first phase is this, second phase is this, and then it'll have many phase is this, and then it'll have many phase is this, and then it'll have many coding agents handle one phase at a coding agents handle one phase at a coding agents handle one phase at a time. But it'll like do it all time. But it'll like do it all time. But it'll like do it all automatically in a loop. That's why it's automatically in a loop. That's why it's automatically in a loop. That's why it's called a Ralph loop. Cuz like agent one called a Ralph loop. Cuz like agent one called a Ralph loop. Cuz like agent one will do phase one, and then it'll write will do phase one, and then it'll write will do phase one, and then it'll write up its little report, like it's handoff up its little report, like it's handoff up its little report, like it's handoff to the second agent that'll continue the to the second agent that'll continue the to the second agent that'll continue the work. And like the main reason the Ralph work. And like the main reason the Ralph work. And like the main reason the Ralph loop matters is because you can't have loop matters is because you can't have loop matters is because you can't have one agent handle that larger task one agent handle that larger task one agent handle that larger task without it getting into the dumb zone without it getting into the dumb zone without it getting into the dumb zone and like, you know, halfway through and like, you know, halfway through and like, you know, halfway through phase two. Right? Like you have to break phase two. Right? Like you have to break phase two. Right? Like you have to break things up.

things up. things up. >> Yeah. So it sounds like from like a >> Yeah. So it sounds like from like a >> Yeah. So it sounds like from like a a high-level view, the idea or kind of a high-level view, the idea or kind of a high-level view, the idea or kind of the mindset that the mindset that the mindset that you've got like this assembly line, and you've got like this assembly line, and you've got like this assembly line, and you have an agent doing something. Each you have an agent doing something. Each you have an agent doing something. Each agent kind of does one thing really agent kind of does one thing really agent kind of does one thing really well, and hands over their input to the well, and hands over their input to the well, and hands over their input to the next agent in a way where next agent in a way where next agent in a way where the agent has enough context to the agent has enough context to the agent has enough context to understand what has been done and what understand what has been done and what understand what has been done and what is left to do, and what its current job is left to do, and what its current job is left to do, and what its current job is. is. is. >> Yeah. Exactly. Yeah, assembly line is a >> Yeah. Exactly. Yeah, assembly line is a >> Yeah. Exactly. Yeah, assembly line is a really good analogy. really good analogy. really good analogy. And I mean that that applies to a lot And I mean that that applies to a lot And I mean that that applies to a lot more than than just writing code. Like more than than just writing code. Like more than than just writing code. Like like one example that comes to mind when like one example that comes to mind when like one example that comes to mind when I think about like cuz I know that I've I think about like cuz I know that I've I think about like cuz I know that I've been talking about like coding as an been talking about like coding as an been talking about like coding as an example for a lot of things, but example for a lot of things, but example for a lot of things, but um I I work with a lot of companies that um I I work with a lot of companies that um I I work with a lot of companies that are in sort of like the are in sort of like the are in sort of like the like B2B side of things. And when you're like B2B side of things. And when you're like B2B side of things. And when you're B2B, like you do a lot of um creating B2B, like you do a lot of um creating B2B, like you do a lot of um creating quotes, like estimates, right? Like you quotes, like estimates, right? Like you quotes, like estimates, right? Like you have um construction company or uh like have um construction company or uh like have um construction company or uh like I've worked with companies in the print I've worked with companies in the print I've worked with companies in the print industry, where like they'll have like a industry, where like they'll have like a industry, where like they'll have like a request for like, "All right, make me request for like, "All right, make me request for like, "All right, make me like 100,000 flyers or whatever."

like 100,000 flyers or whatever." like 100,000 flyers or whatever." And like for those companies, one of the And like for those companies, one of the And like for those companies, one of the biggest opportunities for them to use AI biggest opportunities for them to use AI biggest opportunities for them to use AI is to use something like Claude to help is to use something like Claude to help is to use something like Claude to help them take in a request and automatically them take in a request and automatically them take in a request and automatically create an estimate, like a quote for how create an estimate, like a quote for how create an estimate, like a quote for how much that uh job's going to cost. much that uh job's going to cost. much that uh job's going to cost. Cuz that's like a really, really Cuz that's like a really, really Cuz that's like a really, really laborious job. Like more than you would laborious job. Like more than you would laborious job. Like more than you would think. Like when I when I've talked to think. Like when I when I've talked to think. Like when I when I've talked to these companies, like it's crazy how these companies, like it's crazy how these companies, like it's crazy how much work goes into that because they much work goes into that because they much work goes into that because they have to like take the request and they have to like take the request and they have to like take the request and they have to understand like how much labor have to understand like how much labor have to understand like how much labor goes into this, the parts, obviously goes into this, the parts, obviously goes into this, the parts, obviously like depending on the industry. And then like depending on the industry. And then like depending on the industry. And then they have to do research on like the they have to do research on like the they have to do research on like the latest prices for things and making sure latest prices for things and making sure latest prices for things and making sure they're getting it from the right they're getting it from the right they're getting it from the right vendor. Like there is so much that goes vendor. Like there is so much that goes vendor. Like there is so much that goes into that. And so like that kind of into that. And so like that kind of into that. And so like that kind of thing thing thing uh is it's like a really good example. uh is it's like a really good example. uh is it's like a really good example. Like nothing to do with creating code, Like nothing to do with creating code, Like nothing to do with creating code, still using something like Claude code. still using something like Claude code. still using something like Claude code. Cuz you can use coding agents for this Cuz you can use coding agents for this Cuz you can use coding agents for this to go through that larger workflow of to go through that larger workflow of to go through that larger workflow of like looking at their inventory, looking like looking at their inventory, looking like looking at their inventory, looking at prices, comparing vendors, um all at prices, comparing vendors, um all at prices, comparing vendors, um all based on what's going to be needed to based on what's going to be needed to based on what's going to be needed to accomplish that task, like that remodel, accomplish that task, like that remodel, accomplish that task, like that remodel, that the 100,000 flyers for whatever that the 100,000 flyers for whatever that the 100,000 flyers for whatever that request is from the other company, that request is from the other company, that request is from the other company, and then creating that estimate. And and then creating that estimate. And and then creating that estimate. And then understanding how the company then understanding how the company then understanding how the company works, like what kind of padding they works, like what kind of padding they works, like what kind of padding they want on top of um based on the uh the want on top of um based on the uh the want on top of um based on the uh the labor and the costs of for the parts or labor and the costs of for the parts or labor and the costs of for the parts or whatever. Like there's a lot that goes whatever. Like there's a lot that goes whatever. Like there's a lot that goes into that. And so like that's the kind into that. And so like that's the kind into that. And so like that's the kind of thing where like you'd build a of thing where like you'd build a of thing where like you'd build a workflow, where you have one agent workflow, where you have one agent workflow, where you have one agent that's going to research inventory, one that's going to research inventory, one that's going to research inventory, one agent that's going to look at uh prices agent that's going to look at uh prices agent that's going to look at uh prices and and compare prices for parts, and and and compare prices for parts, and and and compare prices for parts, and then one agent that's going to draft the then one agent that's going to draft the then one agent that's going to draft the PDF, and then maybe another one that's PDF, and then maybe another one that's PDF, and then maybe another one that's going to make it look good. I mean, I'm going to make it look good. I mean, I'm going to make it look good. I mean, I'm kind of stretching the example here, but

kind of stretching the example here, but kind of stretching the example here, but you get the idea of like you actually you get the idea of like you actually you get the idea of like you actually don't have just one agent handle the don't have just one agent handle the don't have just one agent handle the entire thing for something that big. And entire thing for something that big. And entire thing for something that big. And you are going to be doing a lot of you are going to be doing a lot of you are going to be doing a lot of planning. Right? Like you're going to planning. Right? Like you're going to planning. Right? Like you're going to plan, you're going to have a validation plan, you're going to have a validation plan, you're going to have a validation at the end. So like what kind of at the end. So like what kind of at the end. So like what kind of calculations can I do at the end to make calculations can I do at the end to make calculations can I do at the end to make sure that like this job sure that like this job sure that like this job has the the margin that we want on it has the the margin that we want on it has the the margin that we want on it for example. for example. for example. >> Yeah. >> Yeah. >> Yeah. Yeah, and I think Yeah, and I think Yeah, and I think I think back to I think back to I think back to one of our biggest failures back when I one of our biggest failures back when I one of our biggest failures back when I was still kind of in the day-to-day of was still kind of in the day-to-day of was still kind of in the day-to-day of running in the agency was that exact use running in the agency was that exact use running in the agency was that exact use case. Was having to look through tons case. Was having to look through tons case. Was having to look through tons and tons of examples, past quotes, past and tons of examples, past quotes, past and tons of examples, past quotes, past client work, past proposals, and and client work, past proposals, and and client work, past proposals, and and needing to generate these quotes with so needing to generate these quotes with so needing to generate these quotes with so many different factors that go into it. many different factors that go into it. many different factors that go into it. >> Yeah. >> Yeah. >> Yeah. >> And that was one of our biggest failures >> And that was one of our biggest failures >> And that was one of our biggest failures because me personally, I underscoped because me personally, I underscoped because me personally, I underscoped that build. And we went into it not that build. And we went into it not that build. And we went into it not realizing how much actually is necessary realizing how much actually is necessary realizing how much actually is necessary to get to an accurate quote. So that was to get to an accurate quote. So that was to get to an accurate quote. So that was a great lesson for me to learn not only a great lesson for me to learn not only a great lesson for me to learn not only about the importance of asking enough about the importance of asking enough about the importance of asking enough questions and scoping, but just in the questions and scoping, but just in the questions and scoping, but just in the way that you way that you way that you split up the work. And I think, you split up the work. And I think, you split up the work. And I think, you know, obviously Cole mentioned he's he's know, obviously Cole mentioned he's he's know, obviously Cole mentioned he's he's talked a lot of these examples have been talked a lot of these examples have been talked a lot of these examples have been kind of wrong coding, but I don't really kind of wrong coding, but I don't really kind of wrong coding, but I don't really do much do much do much coding. I mean, at the end of the day coding. I mean, at the end of the day coding. I mean, at the end of the day these automations are code, so yes, it's these automations are code, so yes, it's these automations are code, so yes, it's coding. But I'm not doing like coding. But I'm not doing like coding. But I'm not doing like software. I'm not building products, but software. I'm not building products, but software. I'm not building products, but every one of these theories that we every one of these theories that we every one of these theories that we talked about in these mindsets and talked about in these mindsets and talked about in these mindsets and frameworks has, you know, up directly frameworks has, you know, up directly frameworks has, you know, up directly applies to the knowledge work is kind of applies to the knowledge work is kind of applies to the knowledge work is kind of what I like to call it of of what I do what I like to call it of of what I do what I like to call it of of what I do on the day-to-day and what probably most on the day-to-day and what probably most on the day-to-day and what probably most of you guys need to do that gives you an of you guys need to do that gives you an of you guys need to do that gives you an insane amount of leverage right away in insane amount of leverage right away in insane amount of leverage right away in cloud code. And I think that

cloud code. And I think that cloud code. And I think that when you think about your job or you when you think about your job or you when you think about your job or you think about some of your think about some of your think about some of your responsibilities, it's not just one responsibilities, it's not just one responsibilities, it's not just one responsibility. It is responsibility. It is responsibility. It is you can drill that down into so many you can drill that down into so many you can drill that down into so many little subtasks. Like Cole just said, little subtasks. Like Cole just said, little subtasks. Like Cole just said, like one agent does the research, one like one agent does the research, one like one agent does the research, one agent does the PDF generation, all these agent does the PDF generation, all these agent does the PDF generation, all these little little little strings of subtasks that flow up strings of subtasks that flow up strings of subtasks that flow up together to actually make the overall together to actually make the overall together to actually make the overall responsibility, which might be responsibility, which might be responsibility, which might be 10 little tasks that get strung 10 little tasks that get strung 10 little tasks that get strung together. So, when you can actually together. So, when you can actually together. So, when you can actually break down a process by just writing it break down a process by just writing it break down a process by just writing it down or or, you know, down or or, you know, down or or, you know, flowing it out on on a piece of paper, flowing it out on on a piece of paper, flowing it out on on a piece of paper, it makes things a lot more clear. it makes things a lot more clear. it makes things a lot more clear. >> Right. Yeah. >> Right. Yeah. >> Right. Yeah. Yeah, and one thing I want to say here Yeah, and one thing I want to say here Yeah, and one thing I want to say here is that a lot of people, they want to is that a lot of people, they want to is that a lot of people, they want to simplify it down to just using simplify it down to just using simplify it down to just using sub-agents. So, they're like, "For this sub-agents. So, they're like, "For this sub-agents. So, they're like, "For this this larger workflow, what if I just this larger workflow, what if I just this larger workflow, what if I just have my main Claude code dish out a have my main Claude code dish out a have my main Claude code dish out a bunch of tasks to sub-agents?" And like, bunch of tasks to sub-agents?" And like, bunch of tasks to sub-agents?" And like, that can work for some things. I do love that can work for some things. I do love that can work for some things. I do love using sub-agents, especially when I'm using sub-agents, especially when I'm using sub-agents, especially when I'm initially planning any kind of initially planning any kind of initially planning any kind of automation or or application. automation or or application. automation or or application. >> [clears throat] >> [clears throat] >> [clears throat] >> But, it's hard to really make those >> But, it's hard to really make those >> But, it's hard to really make those communicate well with each other. Like, communicate well with each other. Like, communicate well with each other. Like, we've talked a lot about handoffs here.

we've talked a lot about handoffs here. we've talked a lot about handoffs here. A lot of times, one agent, when it's A lot of times, one agent, when it's A lot of times, one agent, when it's taking that next step in a workflow, it taking that next step in a workflow, it taking that next step in a workflow, it has to understand the work that was done has to understand the work that was done has to understand the work that was done with the by the previous one. with the by the previous one. with the by the previous one. Whether that's work, you know, actually Whether that's work, you know, actually Whether that's work, you know, actually writing code, or if it's just doing writing code, or if it's just doing writing code, or if it's just doing research, or if it's pulling information research, or if it's pulling information research, or if it's pulling information from your CRM, for example. Like, it has from your CRM, for example. Like, it has from your CRM, for example. Like, it has to have that kind of handoff document, to have that kind of handoff document, to have that kind of handoff document, and it's really difficult and it's really difficult and it's really difficult to to to um do that well with sub-agents. Claude um do that well with sub-agents. Claude um do that well with sub-agents. Claude Claude has tried their hand at doing Claude has tried their hand at doing Claude has tried their hand at doing something with agent teams. So, they something with agent teams. So, they something with agent teams. So, they they That's kind of like the step above they That's kind of like the step above they That's kind of like the step above sub-agents, where they can really sub-agents, where they can really sub-agents, where they can really communicate with each other. But, uh communicate with each other. But, uh communicate with each other. But, uh that is like really unrefined. It's a that is like really unrefined. It's a that is like really unrefined. It's a really good idea, but it's really really good idea, but it's really really good idea, but it's really unrefined, and it's very expensive, like unrefined, and it's very expensive, like unrefined, and it's very expensive, like token-heavy. token-heavy. token-heavy. >> Yeah. >> Yeah. >> Yeah. >> And so, yeah, like I mean, that's >> And so, yeah, like I mean, that's >> And so, yeah, like I mean, that's actually what I'm working on. So, actually what I'm working on. So, actually what I'm working on. So, there's a open-source project that I'm there's a open-source project that I'm there's a open-source project that I'm working on called Arkon, and that's working on called Arkon, and that's working on called Arkon, and that's really the problem it's solving. It's really the problem it's solving. It's really the problem it's solving. It's how can you be more like The word I use how can you be more like The word I use how can you be more like The word I use is deterministic. Like, how can we build is deterministic. Like, how can we build is deterministic. Like, how can we build the AI model, like build Claude code the AI model, like build Claude code the AI model, like build Claude code into a system, instead of having Claude into a system, instead of having Claude into a system, instead of having Claude code trying to orchestrate everything? code trying to orchestrate everything? code trying to orchestrate everything? Cuz that's when it becomes difficult for Cuz that's when it becomes difficult for Cuz that's when it becomes difficult for communication, and everything becomes communication, and everything becomes communication, and everything becomes very token-heavy. Right? So, like the very token-heavy. Right? So, like the very token-heavy. Right? So, like the way that I like to put it is we want to way that I like to put it is we want to way that I like to put it is we want to um pick when the AI model works in a um pick when the AI model works in a um pick when the AI model works in a workflow, instead of having it drive the workflow, instead of having it drive the workflow, instead of having it drive the whole thing.

whole thing. whole thing. >> Mhm. >> Mhm. >> Mhm. Yeah. Yeah. Yeah. Yeah. How do you make Yeah. How do you make Yeah. How do you make such an autonomous non-deterministic such an autonomous non-deterministic such an autonomous non-deterministic system as deterministic as possible? system as deterministic as possible? system as deterministic as possible? >> Pretty much. Yep. Yep. As deterministic >> Pretty much. Yep. Yep. As deterministic >> Pretty much. Yep. Yep. As deterministic as possible. I wish I could say make it as possible. I wish I could say make it as possible. I wish I could say make it deterministic. deterministic. deterministic. >> [laughter] >> [laughter] >> [laughter] >> That's never going to happen. >> That's never going to happen. >> That's never going to happen. Unfortunately, that is fundamentally Unfortunately, that is fundamentally Unfortunately, that is fundamentally impossible. impossible. impossible. >> Yeah. I love it. Yeah, completely agree >> Yeah. I love it. Yeah, completely agree >> Yeah. I love it. Yeah, completely agree with you there. with you there. with you there. >> Cool. Yeah. >> Cool. Yeah. >> Cool. Yeah. Um so, I mean really we we've talked Um so, I mean really we we've talked Um so, I mean really we we've talked about most of the other things I have in about most of the other things I have in about most of the other things I have in the diagram here. Like we've talked the diagram here. Like we've talked the diagram here. Like we've talked about verification, making sure that about verification, making sure that about verification, making sure that it's able to check its own work. it's able to check its own work. it's able to check its own work. And um yeah, I mean like the the main And um yeah, I mean like the the main And um yeah, I mean like the the main thing here is we don't really care about thing here is we don't really care about thing here is we don't really care about what it does it's for on its first pass. what it does it's for on its first pass. what it does it's for on its first pass. If we build a system where it's able to If we build a system where it's able to If we build a system where it's able to iterate, that's all we really care iterate, that's all we really care iterate, that's all we really care about. As long as it doesn't take about. As long as it doesn't take about. As long as it doesn't take billions of tokens to get to that final billions of tokens to get to that final billions of tokens to get to that final stage. stage. stage. But like when I'm whenever I'm using But like when I'm whenever I'm using But like when I'm whenever I'm using Claude code for something, Claude code for something, Claude code for something, I'm never optimizing for speed. I'm never optimizing for speed. I'm never optimizing for speed. I mean at least like I don't want it to I mean at least like I don't want it to I mean at least like I don't want it to be unrealistically slow, but any kind of be unrealistically slow, but any kind of be unrealistically slow, but any kind of task I have for it, I don't really care task I have for it, I don't really care task I have for it, I don't really care if it's something that I have to if it's something that I have to if it's something that I have to have it work through for a half hour or have it work through for a half hour or have it work through for a half hour or an hour and a half. Like I'll send off an hour and a half. Like I'll send off an hour and a half. Like I'll send off that request and it'll just go to that request and it'll just go to that request and it'll just go to another Claude code session for whatever another Claude code session for whatever another Claude code session for whatever else I have to work on. Or I'll do else I have to work on. Or I'll do else I have to work on. Or I'll do something, believe it or not, without an something, believe it or not, without an something, believe it or not, without an agent for a little bit. Like if I have agent for a little bit. Like if I have agent for a little bit. Like if I have to to to record a video.

record a video. record a video. Um well, I mean maybe I'm using an agent Um well, I mean maybe I'm using an agent Um well, I mean maybe I'm using an agent in the video, but you get the point. But in the video, but you get the point. But in the video, but you get the point. But anyway, like the the point is that I anyway, like the the point is that I anyway, like the the point is that I don't really care how long it takes don't really care how long it takes don't really care how long it takes because I just care getting the best because I just care getting the best because I just care getting the best results possible. results possible. results possible. >> Mhm. >> Mhm. >> Mhm. >> Um and so, yeah, that's why like I I >> Um and so, yeah, that's why like I I >> Um and so, yeah, that's why like I I spend a lot of time engineering systems spend a lot of time engineering systems spend a lot of time engineering systems for for for coding agents to check their own work, coding agents to check their own work, coding agents to check their own work, whether it's browser automation for a whether it's browser automation for a whether it's browser automation for a website or the silly example I gave website or the silly example I gave website or the silly example I gave earlier, like a way for it to sort of earlier, like a way for it to sort of earlier, like a way for it to sort of like play a video game as a human would. like play a video game as a human would. like play a video game as a human would. And that's like a really fascinating And that's like a really fascinating And that's like a really fascinating problem for me to solve right now. It's problem for me to solve right now. It's problem for me to solve right now. It's just like that verification layer at the just like that verification layer at the just like that verification layer at the end for a coding agent, which um also end for a coding agent, which um also end for a coding agent, which um also extends the things like security as extends the things like security as extends the things like security as well. And so, like that's not something well. And so, like that's not something well. And so, like that's not something as interesting to talk about right now, as interesting to talk about right now, as interesting to talk about right now, but like security is pretty important to but like security is pretty important to but like security is pretty important to me. It's something that um Vine coders me. It's something that um Vine coders me. It's something that um Vine coders get very burned for. If you hear those get very burned for. If you hear those get very burned for. If you hear those horror stories like at least once a horror stories like at least once a horror stories like at least once a month month month of you know, like their super bass of you know, like their super bass of you know, like their super bass private or secret key getting leaked in private or secret key getting leaked in private or secret key getting leaked in their their their JavaScript files and things like that JavaScript files and things like that JavaScript files and things like that because they're just completely vibe because they're just completely vibe because they're just completely vibe coding. Like I mean that's like the coding. Like I mean that's like the coding. Like I mean that's like the simplest example, but yeah, like that simplest example, but yeah, like that simplest example, but yeah, like that kind of part of verification is really kind of part of verification is really kind of part of verification is really important as well.

important as well. important as well. >> Yeah, and >> Yeah, and >> Yeah, and on that whole element of security and on that whole element of security and on that whole element of security and what could go wrong, what could go wrong, what could go wrong, when you think about sort of like the when you think about sort of like the when you think about sort of like the permission layer that you're putting permission layer that you're putting permission layer that you're putting around your agents, I see a lot of around your agents, I see a lot of around your agents, I see a lot of false sense of security once again where false sense of security once again where false sense of security once again where people people people think that their prompts think that their prompts think that their prompts are a good enough permission layer. are a good enough permission layer. are a good enough permission layer. When really that permission layer needs When really that permission layer needs When really that permission layer needs to be to be to be scoped keys or you actually can't touch scoped keys or you actually can't touch scoped keys or you actually can't touch this at all because I think I was this at all because I think I was this at all because I think I was talking to my team and we kind of got to talking to my team and we kind of got to talking to my team and we kind of got to this conclusion of if you have the this conclusion of if you have the this conclusion of if you have the mindset that mindset that mindset that anything that the agent can read or can anything that the agent can read or can anything that the agent can read or can touch, it will. Like you have to assume touch, it will. Like you have to assume touch, it will. Like you have to assume that it will even if you never ask it that it will even if you never ask it that it will even if you never ask it to, that assumption is what's going to to, that assumption is what's going to to, that assumption is what's going to save you from having your database save you from having your database save you from having your database deleted. deleted. deleted. >> Yes. >> Yes. >> Yes. >> [laughter] >> [laughter] >> [laughter] >> And that's funny you bring up that >> And that's funny you bring up that >> And that's funny you bring up that example specifically cuz I was just example specifically cuz I was just example specifically cuz I was just about to say like if you tell it never about to say like if you tell it never about to say like if you tell it never to to wipe a database, it's still going to to wipe a database, it's still going to to wipe a database, it's still going to do that. to do that. to do that. Like there was a a story that went viral Like there was a a story that went viral Like there was a a story that went viral like a month or two ago was someone like like a month or two ago was someone like like a month or two ago was someone like really high up at meta that had their really high up at meta that had their really high up at meta that had their database wiped. I'm still not convinced database wiped. I'm still not convinced database wiped. I'm still not convinced that's real. I feel like they might have that's real. I feel like they might have that's real. I feel like they might have just been just been just been I don't know cuz people get so much I don't know cuz people get so much I don't know cuz people get so much attention when they have stupid stories attention when they have stupid stories attention when they have stupid stories like that. But but anyway like that. But but anyway like that. But but anyway >> Conspiracy theories with Cole.

>> Conspiracy theories with Cole. >> Conspiracy theories with Cole. >> [laughter] >> [laughter] >> [laughter] >> Right. Yeah, >> Right. Yeah, >> Right. Yeah, right. Yeah, but like it is it is right. Yeah, but like it is it is right. Yeah, but like it is it is definitely possible and I do know some definitely possible and I do know some definitely possible and I do know some stories of that actually happening just stories of that actually happening just stories of that actually happening just to a smaller extent. It just feels so to a smaller extent. It just feels so to a smaller extent. It just feels so weird that or it sounds so stupid that weird that or it sounds so stupid that weird that or it sounds so stupid that it's like their actual production it's like their actual production it's like their actual production database was wiped, but I mean even if database was wiped, but I mean even if database was wiped, but I mean even if you have a test database wiped, it can you have a test database wiped, it can you have a test database wiped, it can still be a bummer if that slows you down still be a bummer if that slows you down still be a bummer if that slows you down a lot. And so so yeah, it is super a lot. And so so yeah, it is super a lot. And so so yeah, it is super important. You never want to assume that important. You never want to assume that important. You never want to assume that just because you tell an agent to not do just because you tell an agent to not do just because you tell an agent to not do something, it never will. something, it never will. something, it never will. I mean it's the same thing like if you I mean it's the same thing like if you I mean it's the same thing like if you tell a kid tell a kid tell a kid to not do something, they just might not to not do something, they just might not to not do something, they just might not listen. I mean, even even adults. listen. I mean, even even adults. listen. I mean, even even adults. >> There actually recently something did >> There actually recently something did >> There actually recently something did happen to us, which is kind of why we happen to us, which is kind of why we happen to us, which is kind of why we started talking about this. started talking about this. started talking about this. >> Okay. >> Okay. >> Okay. >> We had this this incident where the >> We had this this incident where the >> We had this this incident where the agent had the right intentions. It was agent had the right intentions. It was agent had the right intentions. It was trying to be proactive, and it actually trying to be proactive, and it actually trying to be proactive, and it actually saw something on its task list, but it saw something on its task list, but it saw something on its task list, but it misinterpreted it. And it ended up misinterpreted it. And it ended up misinterpreted it. And it ended up sending an email to our entire list sending an email to our entire list sending an email to our entire list with a discount code, and it was like with a discount code, and it was like with a discount code, and it was like not supposed to go out. So, we had to not supposed to go out. So, we had to not supposed to go out. So, we had to like change the code, update the page. like change the code, update the page. like change the code, update the page. We emailed out an apology. So, if you We emailed out an apology. So, if you We emailed out an apology. So, if you guys are on the email list, and you got guys are on the email list, and you got guys are on the email list, and you got that, that's what happened. But it's that, that's what happened. But it's that, that's what happened. But it's just like, you know, I wasn't mad at the just like, you know, I wasn't mad at the just like, you know, I wasn't mad at the person who was kind of responsible for person who was kind of responsible for person who was kind of responsible for the agent. It was just a really good the agent. It was just a really good the agent. It was just a really good opportunity for us to think about, okay, opportunity for us to think about, okay, opportunity for us to think about, okay, why did this happen? And, you know, she why did this happen? And, you know, she why did this happen? And, you know, she wrote up a case study. We sent it to the wrote up a case study. We sent it to the wrote up a case study. We sent it to the whole team, and everyone was like, okay, whole team, and everyone was like, okay, whole team, and everyone was like, okay, that's a really really good reminder of that's a really really good reminder of that's a really really good reminder of how careful you have to be. Because, you how careful you have to be. Because, you how careful you have to be. Because, you know, if you connect to an MCP server, know, if you connect to an MCP server, know, if you connect to an MCP server, and you don't limit the permissions, it and you don't limit the permissions, it and you don't limit the permissions, it has everything, you know?

has everything, you know? has everything, you know? >> Yeah. >> Yeah. >> Yeah. Yep. No, that's good. Yeah, the the main Yep. No, that's good. Yeah, the the main Yep. No, that's good. Yeah, the the main way that I restrict actions from my way that I restrict actions from my way that I restrict actions from my coding agent is with hooks. coding agent is with hooks. coding agent is with hooks. So, like Cloud Code hooks is a really So, like Cloud Code hooks is a really So, like Cloud Code hooks is a really good way cuz um basically a hook in good way cuz um basically a hook in good way cuz um basically a hook in Cloud Code Cloud Code Cloud Code is a little piece of code that you can is a little piece of code that you can is a little piece of code that you can run whenever a certain event happens in run whenever a certain event happens in run whenever a certain event happens in the tool. the tool. the tool. So, whenever you start a session, So, whenever you start a session, So, whenever you start a session, whenever you end a session, right before whenever you end a session, right before whenever you end a session, right before Cloud Code uses a tool, you can run some Cloud Code uses a tool, you can run some Cloud Code uses a tool, you can run some kind of code that does a security check. kind of code that does a security check. kind of code that does a security check. I mean, there's a lot of other things, I mean, there's a lot of other things, I mean, there's a lot of other things, but like I love using hooks for but like I love using hooks for but like I love using hooks for security. And so, what you can do in security. And so, what you can do in security. And so, what you can do in Cloud is every time it's about to invoke Cloud is every time it's about to invoke Cloud is every time it's about to invoke a tool, like it wants to write out to a a tool, like it wants to write out to a a tool, like it wants to write out to a file, or make some requests to the web, file, or make some requests to the web, file, or make some requests to the web, you can uh check against that command to you can uh check against that command to you can uh check against that command to make sure it's not trying to mess with a make sure it's not trying to mess with a make sure it's not trying to mess with a folder you don't want it to touch, or folder you don't want it to touch, or folder you don't want it to touch, or run some kind of command you don't want run some kind of command you don't want run some kind of command you don't want it to run. And there's a lot of it to run. And there's a lot of it to run. And there's a lot of different ways you can check for that different ways you can check for that different ways you can check for that that we don't have to get into right that we don't have to get into right that we don't have to get into right now. Um but that's like one of my now. Um but that's like one of my now. Um but that's like one of my favorite ways to make sure it's like not favorite ways to make sure it's like not favorite ways to make sure it's like not reading my environment variables, or reading my environment variables, or reading my environment variables, or it's not running a a delete command for it's not running a a delete command for it's not running a a delete command for a database.

a database. a database. Um and it it it's really hard to make Um and it it it's really hard to make Um and it it it's really hard to make sure you're you're covering all the sure you're you're covering all the sure you're you're covering all the loopholes cuz there's a lot of things loopholes cuz there's a lot of things loopholes cuz there's a lot of things that coding agents can do that coding agents can do that coding agents can do >> Yeah. >> Yeah. >> Yeah. >> to get around those kind of checks as >> to get around those kind of checks as >> to get around those kind of checks as well. A lot of people have false false well. A lot of people have false false well. A lot of people have false false sense of security around that as well. sense of security around that as well. sense of security around that as well. So you kind of have that like first So you kind of have that like first So you kind of have that like first false sense of security where it's like, false sense of security where it's like, false sense of security where it's like, "Well, I told it to never delete my "Well, I told it to never delete my "Well, I told it to never delete my database." And then you have the second database." And then you have the second database." And then you have the second level where it's like, "I block all level where it's like, "I block all level where it's like, "I block all delete SQL statements." But then there's delete SQL statements." But then there's delete SQL statements." But then there's that third level that you have to like that third level that you have to like that third level that you have to like make sure you're engineering for. make sure you're engineering for. make sure you're engineering for. Um like for example, a coding agent if Um like for example, a coding agent if Um like for example, a coding agent if you if you don't allow it to call the you if you don't allow it to call the you if you don't allow it to call the like delete like remove command to like delete like remove command to like delete like remove command to delete a folder, it can still write a delete a folder, it can still write a delete a folder, it can still write a script to do that. So it just has to do script to do that. So it just has to do script to do that. So it just has to do two steps like write the script and then two steps like write the script and then two steps like write the script and then run the script and then it's still able run the script and then it's still able run the script and then it's still able to remove a file or folder on your to remove a file or folder on your to remove a file or folder on your computer. So it's I mean they're less computer. So it's I mean they're less computer. So it's I mean they're less likely to do that so it's still like likely to do that so it's still like likely to do that so it's still like you're getting there if you are at least you're getting there if you are at least you're getting there if you are at least have like that that second false sense have like that that second false sense have like that that second false sense of security but like you got to be of security but like you got to be of security but like you got to be really safe and you got to like it's really safe and you got to like it's really safe and you got to like it's it's actually a tough problem to solve. it's actually a tough problem to solve. it's actually a tough problem to solve. >> Yeah, I mean AGI is it's it's scary. >> Yeah, I mean AGI is it's it's scary. >> Yeah, I mean AGI is it's it's scary. >> [laughter] >> [laughter] >> [laughter] >> Yeah.

>> Yeah. >> Yeah. >> But I would love to see and maybe you've >> But I would love to see and maybe you've >> But I would love to see and maybe you've already got one out but I would love to already got one out but I would love to already got one out but I would love to see a a Cole Hooks masterclass because I see a a Cole Hooks masterclass because I see a a Cole Hooks masterclass because I actually just recorded one and I don't actually just recorded one and I don't actually just recorded one and I don't use hooks that much to be honest. Like I use hooks that much to be honest. Like I use hooks that much to be honest. Like I really don't. I think my my main hook really don't. I think my my main hook really don't. I think my my main hook that I have is just to give me a noise that I have is just to give me a noise that I have is just to give me a noise notification when it's done or when it notification when it's done or when it notification when it's done or when it needs me. But yeah, like I have under needs me. But yeah, like I have under needs me. But yeah, like I have under utilized hooks for sure and I'm not sure utilized hooks for sure and I'm not sure utilized hooks for sure and I'm not sure if that's because if that's because if that's because they're mainly valuable when you're they're mainly valuable when you're they're mainly valuable when you're doing heavy coding but doing heavy coding but doing heavy coding but I would assume that there's a lot of I would assume that there's a lot of I would assume that there's a lot of things that I could be doing in my things that I could be doing in my things that I could be doing in my day-to-day where hooks would be really day-to-day where hooks would be really day-to-day where hooks would be really good and I need to definitely look into good and I need to definitely look into good and I need to definitely look into a little bit more how I can be utilizing a little bit more how I can be utilizing a little bit more how I can be utilizing them but anyways. them but anyways. them but anyways. >> Yeah. >> Yeah. >> Yeah. Yeah, I I definitely should do a Yeah, I I definitely should do a Yeah, I I definitely should do a masterclass on hooks cuz there's a lot masterclass on hooks cuz there's a lot masterclass on hooks cuz there's a lot of ways that I use them. Um yeah, since of ways that I use them. Um yeah, since of ways that I use them. Um yeah, since we're on the topic like one of the we're on the topic like one of the we're on the topic like one of the really interesting way to use hooks is really interesting way to use hooks is really interesting way to use hooks is you can use them to automatically you can use them to automatically you can use them to automatically suggest like you can have Claude code suggest like you can have Claude code suggest like you can have Claude code like automatically suggest ways to like automatically suggest ways to like automatically suggest ways to improve your AI layer. Like make your improve your AI layer. Like make your improve your AI layer. Like make your rules better, make your skills better.

rules better, make your skills better. rules better, make your skills better. And a lot a lot of tools like Hermes and And a lot a lot of tools like Hermes and And a lot a lot of tools like Hermes and Open Claude, they kind of do this. I Open Claude, they kind of do this. I Open Claude, they kind of do this. I don't think they like explicitly use don't think they like explicitly use don't think they like explicitly use hooks, but like Open Claude for example, hooks, but like Open Claude for example, hooks, but like Open Claude for example, every like 10 20 turns, I think it's every like 10 20 turns, I think it's every like 10 20 turns, I think it's configurable, it will like kind of configurable, it will like kind of configurable, it will like kind of compact your conversation and store it compact your conversation and store it compact your conversation and store it as a memory, right? So that you have as a memory, right? So that you have as a memory, right? So that you have [clears throat] like the whole like [clears throat] like the whole like [clears throat] like the whole like daily log thing with the uh memory.md daily log thing with the uh memory.md daily log thing with the uh memory.md file. Like all that comes from what's file. Like all that comes from what's file. Like all that comes from what's essentially a Claude code hook. Like so essentially a Claude code hook. Like so essentially a Claude code hook. Like so with the way I use Claude code with my with the way I use Claude code with my with the way I use Claude code with my second brain second brain second brain is uh every time I have a memory is uh every time I have a memory is uh every time I have a memory compaction, which I try to avoid those. compaction, which I try to avoid those. compaction, which I try to avoid those. I don't want to get that far in a I don't want to get that far in a I don't want to get that far in a conversation, um or I end a session, it conversation, um or I end a session, it conversation, um or I end a session, it automatically creates a summary of the automatically creates a summary of the automatically creates a summary of the conversation, puts that in a daily log, conversation, puts that in a daily log, conversation, puts that in a daily log, and then I have a process every day. and then I have a process every day. and then I have a process every day. It's basically like Claude code It's basically like Claude code It's basically like Claude code dreaming, where it's going to look at dreaming, where it's going to look at dreaming, where it's going to look at the daily log and then extract any like the daily log and then extract any like the daily log and then extract any like really important things to store and really important things to store and really important things to store and sort of like promote to my primary sort of like promote to my primary sort of like promote to my primary memory file. Like here are the decisions memory file. Like here are the decisions memory file. Like here are the decisions that I've made recently or like things that I've made recently or like things that I've made recently or like things that I'm actively working on and where that I'm actively working on and where that I'm actively working on and where I'm at them. So like hook hooks actually I'm at them. So like hook hooks actually I'm at them. So like hook hooks actually drives the whole thing. Like this drives the whole thing. Like this drives the whole thing. Like this terminal that that this like the second terminal that that this like the second terminal that that this like the second time it's popped up, time it's popped up, time it's popped up, um that's actually a hook that just um that's actually a hook that just um that's actually a hook that just fired there. So I'm just like testing fired there. So I'm just like testing fired there. So I'm just like testing some other things. I forgot to turn it some other things. I forgot to turn it some other things. I forgot to turn it off, which is unfortunate, but actually off, which is unfortunate, but actually off, which is unfortunate, but actually now it made for a good illustration cuz now it made for a good illustration cuz now it made for a good illustration cuz I had I had a hook run as I'm talking I had I had a hook run as I'm talking I had I had a hook run as I'm talking about it. So I'm just testing something about it. So I'm just testing something about it. So I'm just testing something else right now.

else right now. else right now. >> Yeah, just just yet another way to make >> Yeah, just just yet another way to make >> Yeah, just just yet another way to make these non-deterministic things as these non-deterministic things as these non-deterministic things as deterministic as possible. deterministic as possible. deterministic as possible. So what do we have next after this So what do we have next after this So what do we have next after this verify the work section? verify the work section? verify the work section? >> Yeah. So really this is the last thing >> Yeah. So really this is the last thing >> Yeah. So really this is the last thing cuz we've already talked about the the cuz we've already talked about the the cuz we've already talked about the the harness, but the the last and honestly harness, but the the last and honestly harness, but the the last and honestly probably the most important thing is the probably the most important thing is the probably the most important thing is the system evolution that I talked about system evolution that I talked about system evolution that I talked about just a little bit earlier. And and just a little bit earlier. And and just a little bit earlier. And and really the the mindset here really the the mindset here really the the mindset here is what is what is what Like I this is I out of everything that Like I this is I out of everything that Like I this is I out of everything that makes it so you're really directing makes it so you're really directing makes it so you're really directing Claude code instead of just being a user Claude code instead of just being a user Claude code instead of just being a user of it, the building the system is the of it, the building the system is the of it, the building the system is the most important thing. So, anytime most important thing. So, anytime most important thing. So, anytime there's an issue that comes up, there's an issue that comes up, there's an issue that comes up, instead of just fixing the issue and instead of just fixing the issue and instead of just fixing the issue and moving on, it's an opportunity for you moving on, it's an opportunity for you moving on, it's an opportunity for you to, with the help of the coding agent, to, with the help of the coding agent, to, with the help of the coding agent, with the help of Claude Code, figuring with the help of Claude Code, figuring with the help of Claude Code, figuring out like what could we make better so out like what could we make better so out like what could we make better so that this doesn't happen again. Like that this doesn't happen again. Like that this doesn't happen again. Like maybe there's a new rule that we can add maybe there's a new rule that we can add maybe there's a new rule that we can add in our claw.md or there's a new document in our claw.md or there's a new document in our claw.md or there's a new document that we can that we can that we can give it when we're in our planning give it when we're in our planning give it when we're in our planning process, or there's maybe an update to process, or there's maybe an update to process, or there's maybe an update to our skill that we can make. And I'm our skill that we can make. And I'm our skill that we can make. And I'm being kind of general on purpose here being kind of general on purpose here being kind of general on purpose here because there's a million different ways because there's a million different ways because there's a million different ways that we can improve our system. And so, that we can improve our system. And so, that we can improve our system. And so, this is kind of like the example that this is kind of like the example that this is kind of like the example that you gave, Nate, where you had that email you gave, Nate, where you had that email you gave, Nate, where you had that email go out, or at least it went out to way go out, or at least it went out to way go out, or at least it went out to way more people than it should have. And so, more people than it should have. And so, more people than it should have. And so, you wrote up that report of like, here's you wrote up that report of like, here's you wrote up that report of like, here's what happened, here's what we can do what happened, here's what we can do what happened, here's what we can do better. And so, it's kind of doing that, better. And so, it's kind of doing that, better. And so, it's kind of doing that, but like for the agent, so that going but like for the agent, so that going but like for the agent, so that going forward, it has that rule so it it forward, it has that rule so it it forward, it has that rule so it it doesn't do that thing anymore. Like doesn't do that thing anymore. Like doesn't do that thing anymore. Like maybe it didn't run all the validation maybe it didn't run all the validation maybe it didn't run all the validation you wanted it to. So, now you just like you wanted it to. So, now you just like you wanted it to. So, now you just like make sure that like that's a part of the make sure that like that's a part of the make sure that like that's a part of the rule where it's like, this you make sure rule where it's like, this you make sure rule where it's like, this you make sure you don't forget this validation, kind

you don't forget this validation, kind you don't forget this validation, kind of as a silly example. of as a silly example. of as a silly example. But, that way every bug becomes a But, that way every bug becomes a But, that way every bug becomes a permanent upgrade. So, once you have permanent upgrade. So, once you have permanent upgrade. So, once you have this kind of system in place, you this kind of system in place, you this kind of system in place, you actually almost welcome bugs. Like I actually almost welcome bugs. Like I actually almost welcome bugs. Like I want something to go wrong because then want something to go wrong because then want something to go wrong because then I can make sure it never happens again. I can make sure it never happens again. I can make sure it never happens again. Right? Like I almost have I almost feel Right? Like I almost have I almost feel Right? Like I almost have I almost feel kind of nervous when everything is going kind of nervous when everything is going kind of nervous when everything is going too well cuz then it's like, oh shoot, I too well cuz then it's like, oh shoot, I too well cuz then it's like, oh shoot, I have no way to like make my agent better have no way to like make my agent better have no way to like make my agent better right now. So, it's it can kind of right now. So, it's it can kind of right now. So, it's it can kind of become nice. become nice. become nice. >> Yeah, absolutely. >> Yeah, absolutely. >> Yeah, absolutely. >> Yeah, so it can get better over time. >> Yeah, so it can get better over time. >> Yeah, so it can get better over time. >> I've got an interesting question for >> I've got an interesting question for >> I've got an interesting question for you. So, I completely agree. Every you. So, I completely agree. Every you. So, I completely agree. Every single time that you have a failure, you single time that you have a failure, you single time that you have a failure, you should look at that as data and an should look at that as data and an should look at that as data and an opportunity to improve the system. opportunity to improve the system. opportunity to improve the system. Now, what what about before you get Now, what what about before you get Now, what what about before you get those failures? How do you think about, those failures? How do you think about, those failures? How do you think about, to your best to the best of your to your best to the best of your to your best to the best of your ability, ability, ability, finding those edge cases or predicting finding those edge cases or predicting finding those edge cases or predicting what edge cases might happen and trying what edge cases might happen and trying what edge cases might happen and trying to build in guardrails before to build in guardrails before to build in guardrails before the whole testing part? the whole testing part? the whole testing part? >> Well, it can never be perfect, which is >> Well, it can never be perfect, which is >> Well, it can never be perfect, which is why I lean on this so much, but why I lean on this so much, but why I lean on this so much, but generally, when you're looking out for generally, when you're looking out for generally, when you're looking out for edge cases, edge cases, edge cases, Um I mean, Cloud Code is actually pretty Um I mean, Cloud Code is actually pretty Um I mean, Cloud Code is actually pretty good at it. It's not going to cover like good at it. It's not going to cover like good at it. It's not going to cover like nearly all the edge cases, but even just nearly all the edge cases, but even just nearly all the edge cases, but even just asking it like, "How could this go asking it like, "How could this go asking it like, "How could this go wrong?" is a question that sometimes wrong?" is a question that sometimes wrong?" is a question that sometimes people are are honestly like nervous to people are are honestly like nervous to people are are honestly like nervous to even ask. But, it's a a really good even ask. But, it's a a really good even ask. But, it's a a really good question. Once you're done with the question. Once you're done with the question. Once you're done with the implementation, and like this is a part implementation, and like this is a part implementation, and like this is a part of like my code review skill that I have of like my code review skill that I have of like my code review skill that I have built in where it's like, "Ask yourself, built in where it's like, "Ask yourself, built in where it's like, "Ask yourself, what could go wrong here?" And then try what could go wrong here?" And then try what could go wrong here?" And then try to engineer a scenario where you're to engineer a scenario where you're to engineer a scenario where you're really testing that. Like, if I'm really testing that. Like, if I'm really testing that. Like, if I'm building an automation where I think building an automation where I think building an automation where I think there might be an edge case where it there might be an edge case where it there might be an edge case where it doesn't handle this kind of input doesn't handle this kind of input doesn't handle this kind of input correctly, I'm going to as a part of my correctly, I'm going to as a part of my correctly, I'm going to as a part of my agent's code review have it like create

agent's code review have it like create agent's code review have it like create that like it'll invoke the application that like it'll invoke the application that like it'll invoke the application with that input, like a webhook or with that input, like a webhook or with that input, like a webhook or whatever, and try to break it and see whatever, and try to break it and see whatever, and try to break it and see what happens. And if it does break, then what happens. And if it does break, then what happens. And if it does break, then I mean, that's obviously going to be I mean, that's obviously going to be I mean, that's obviously going to be like going back here a part of our like going back here a part of our like going back here a part of our verification where um it'll then uh verification where um it'll then uh verification where um it'll then uh address that thing and then do the test address that thing and then do the test address that thing and then do the test again, right? Like, iterate. Like, you again, right? Like, iterate. Like, you again, right? Like, iterate. Like, you find a problem, fix it, and then also find a problem, fix it, and then also find a problem, fix it, and then also retest, right? Don't forget the retest retest, right? Don't forget the retest retest, right? Don't forget the retest cuz maybe your fix didn't actually cuz maybe your fix didn't actually cuz maybe your fix didn't actually address the problem. address the problem. address the problem. >> Mhm. Yeah. Well, I think, you know, >> Mhm. Yeah. Well, I think, you know, >> Mhm. Yeah. Well, I think, you know, something that I've realized after something that I've realized after something that I've realized after responding to YouTube comments, responding to YouTube comments, responding to YouTube comments, Q&As in the community, chatting to you, Q&As in the community, chatting to you, Q&As in the community, chatting to you, and and just seeing what's going on when and and just seeing what's going on when and and just seeing what's going on when people are learning these kinds of tools people are learning these kinds of tools people are learning these kinds of tools is that is that is that you really at you know, at the simplest you really at you know, at the simplest you really at you know, at the simplest way to describe it, you just have to way to describe it, you just have to way to describe it, you just have to treat it like treat it like treat it like your best friend who is your best friend who is your best friend who is the smartest person in the world. the smartest person in the world. the smartest person in the world. Meaning, you know, treat it like a Meaning, you know, treat it like a Meaning, you know, treat it like a mentor. It's not going to laugh at you mentor. It's not going to laugh at you mentor. It's not going to laugh at you if you ask it something stupid. if you ask it something stupid. if you ask it something stupid. >> Yeah. >> Yeah. >> Yeah. >> need to be curious and you need to ask >> need to be curious and you need to ask >> need to be curious and you need to ask ask the questions that you are wondering ask the questions that you are wondering ask the questions that you are wondering in your head. And I think when you kind in your head. And I think when you kind in your head. And I think when you kind of get over that that idea that it can of get over that that idea that it can of get over that that idea that it can teach you anything, and it can for the teach you anything, and it can for the teach you anything, and it can for the most part, especially if you ask it most part, especially if you ask it most part, especially if you ask it right, it can help you figure out the right, it can help you figure out the right, it can help you figure out the majority of your problems when you have, majority of your problems when you have, majority of your problems when you have, you know, that that sort of you know, that that sort of you know, that that sort of uneasiness because maybe you don't uneasiness because maybe you don't uneasiness because maybe you don't understand what it did. So, that's like understand what it did. So, that's like understand what it did. So, that's like a huge mindset shift for a huge mindset shift for a huge mindset shift for anyone I've talked to that is like anyone I've talked to that is like anyone I've talked to that is like trying to get into it and doesn't trying to get into it and doesn't trying to get into it and doesn't understand it. If they, you know, maybe understand it. If they, you know, maybe understand it. If they, you know, maybe they text me a question or they drop a they text me a question or they drop a they text me a question or they drop a question, question, question, it's just like the response can a lot of it's just like the response can a lot of it's just like the response can a lot of times be times be times be "Have you asked Claude code that?"

"Have you asked Claude code that?" "Have you asked Claude code that?" >> [laughter] >> [laughter] >> [laughter] >> I know. Yeah, I feel bad saying that, >> I know. Yeah, I feel bad saying that, >> I know. Yeah, I feel bad saying that, but like yeah, it comes it comes to that but like yeah, it comes it comes to that but like yeah, it comes it comes to that a lot. a lot. a lot. Um yeah, where it's like now you should Um yeah, where it's like now you should Um yeah, where it's like now you should have just I mean you usually how I can have just I mean you usually how I can have just I mean you usually how I can be more helpful is like telling them be more helpful is like telling them be more helpful is like telling them what to ask exactly. Like give it give what to ask exactly. Like give it give what to ask exactly. Like give it give [clears throat] it this link, give it [clears throat] it this link, give it [clears throat] it this link, give it that thing, and then here's how I'd ask that thing, and then here's how I'd ask that thing, and then here's how I'd ask it. But yeah, a lot of times it does it. But yeah, a lot of times it does it. But yeah, a lot of times it does come down to that. And I mean you can't come down to that. And I mean you can't come down to that. And I mean you can't you can't just ask Claude for everything you can't just ask Claude for everything you can't just ask Claude for everything cuz of like the sycophancy you mentioned cuz of like the sycophancy you mentioned cuz of like the sycophancy you mentioned earlier. Sometimes if you're asking it earlier. Sometimes if you're asking it earlier. Sometimes if you're asking it for its opinion, like asking a large for its opinion, like asking a large for its opinion, like asking a large English model for its opinion is a English model for its opinion is a English model for its opinion is a really slippery slope. really slippery slope. really slippery slope. >> Yeah. >> Yeah. >> Yeah. >> But but what you can [laughter] what you >> But but what you can [laughter] what you >> But but what you can [laughter] what you can ask it for is to like understand how can ask it for is to like understand how can ask it for is to like understand how something works. Like that's when it can something works. Like that's when it can something works. Like that's when it can do a really good job. So like going back do a really good job. So like going back do a really good job. So like going back to the example earlier, if you're not to the example earlier, if you're not to the example earlier, if you're not technical, but you want to try to technical, but you want to try to technical, but you want to try to actually be able to understand the actually be able to understand the actually be able to understand the automations and things that it's automations and things that it's automations and things that it's building for you, like that's a really building for you, like that's a really building for you, like that's a really good thing to ask it cuz it's not going good thing to ask it cuz it's not going good thing to ask it cuz it's not going to like there's no sycophancy there, to like there's no sycophancy there, to like there's no sycophancy there, right? It's not just trying to appease right? It's not just trying to appease right? It's not just trying to appease you. It's it's just helping you you. It's it's just helping you you. It's it's just helping you understand. The way to appease you is to understand. The way to appease you is to understand. The way to appease you is to explain the thing, right? explain the thing, right? explain the thing, right? >> Yeah. >> Yeah. >> Yeah. >> So like that that's a really good case, >> So like that that's a really good case, >> So like that that's a really good case, just trying to understand anything.

just trying to understand anything. just trying to understand anything. And then like what we were talking about And then like what we were talking about And then like what we were talking about just here with verification, like trying just here with verification, like trying just here with verification, like trying to find edge cases, if there's anything to find edge cases, if there's anything to find edge cases, if there's anything where there's like actual empirical where there's like actual empirical where there's like actual empirical data, like there is a way to verify that data, like there is a way to verify that data, like there is a way to verify that like this this automation doesn't handle like this this automation doesn't handle like this this automation doesn't handle this input well. I mean there's no room this input well. I mean there's no room this input well. I mean there's no room for sycophancy there. It's like it it for sycophancy there. It's like it it for sycophancy there. It's like it it either works or it doesn't, and there's either works or it doesn't, and there's either works or it doesn't, and there's not really like any kind of gray area or not really like any kind of gray area or not really like any kind of gray area or opinion. opinion. opinion. >> Right. >> Right. >> Right. >> So if you think there might be an edge >> So if you think there might be an edge >> So if you think there might be an edge case, or it thinks there might be, it case, or it thinks there might be, it case, or it thinks there might be, it can test it, and then it's it's black or can test it, and then it's it's black or can test it, and then it's it's black or white. white. white. >> Right. >> Right. >> Right. So I want to hear what you think about So I want to hear what you think about So I want to hear what you think about this because this because this because you briefly mentioned the agent teams you briefly mentioned the agent teams you briefly mentioned the agent teams earlier, and earlier, and earlier, and >> Yeah. >> Yeah. >> Yeah. >> I actually find myself using them quite >> I actually find myself using them quite >> I actually find myself using them quite a bit for mainly one specific use case, a bit for mainly one specific use case, a bit for mainly one specific use case, and I want to hear what you think about and I want to hear what you think about and I want to hear what you think about it. So it. So it. So really the time when I reach for agent really the time when I reach for agent really the time when I reach for agent teams is when teams is when teams is when I am trying to help, you know, I'm I am trying to help, you know, I'm I am trying to help, you know, I'm trying to decide something, but I don't trying to decide something, but I don't trying to decide something, but I don't want to just ask for want to just ask for want to just ask for Claude code's opinion, like you just Claude code's opinion, like you just Claude code's opinion, like you just said. said. said. >> Yeah. >> Yeah. >> Yeah. >> And so what I'll do a lot is I'll spin >> And so what I'll do a lot is I'll spin >> And so what I'll do a lot is I'll spin up like a debate panel or like a war up like a debate panel or like a war up like a debate panel or like a war room. room. room. >> Nice. >> Nice. >> Nice. >> And I will say, you know, like one of >> And I will say, you know, like one of >> And I will say, you know, like one of you guys is a CEO, one is a beginner, you guys is a CEO, one is a beginner, you guys is a CEO, one is a beginner, one is a college student, and just like one is a college student, and just like one is a college student, and just like a bunch of different personas, sometimes a bunch of different personas, sometimes a bunch of different personas, sometimes even like seven.

even like seven. even like seven. And I will just have them all do And I will just have them all do And I will just have them all do independent research, form their own independent research, form their own independent research, form their own opinions, and then I'll have them opinions, and then I'll have them opinions, and then I'll have them debate. debate. debate. And then I'll just be able to read the And then I'll just be able to read the And then I'll just be able to read the debate, and I'll be able to debate, and I'll be able to debate, and I'll be able to sometimes I'll say like keep debating sometimes I'll say like keep debating sometimes I'll say like keep debating until you all come to some sort of until you all come to some sort of until you all come to some sort of consensus. consensus. consensus. >> Nice. >> Nice. >> Nice. >> do that quite a bit, and that doesn't >> do that quite a bit, and that doesn't >> do that quite a bit, and that doesn't mean whatever the agent team spits out I mean whatever the agent team spits out I mean whatever the agent team spits out I do, do, do, but sometimes it's just really great for but sometimes it's just really great for but sometimes it's just really great for me to read through all those opinions. me to read through all those opinions. me to read through all those opinions. But I want to see do you But I want to see do you But I want to see do you do you like that? Do you think that's a do you like that? Do you think that's a do you like that? Do you think that's a major flaw? Like what what thoughts do major flaw? Like what what thoughts do major flaw? Like what what thoughts do you have about that? you have about that? you have about that? >> I do actually like that. Uh I've I've >> I do actually like that. Uh I've I've >> I do actually like that. Uh I've I've never done that before. never done that before. never done that before. >> done that. You should definitely try it. >> done that. You should definitely try it. >> done that. You should definitely try it. >> I No, I yeah, I feel like tonight I >> I No, I yeah, I feel like tonight I >> I No, I yeah, I feel like tonight I literally got to try that. That's really literally got to try that. That's really literally got to try that. That's really cool. cool. cool. >> Yeah, I like that idea a lot. Cuz so >> Yeah, I like that idea a lot. Cuz so >> Yeah, I like that idea a lot. Cuz so something that I have done something that I have done something that I have done experimentation with that's sort of experimentation with that's sort of experimentation with that's sort of similar, I call it adversarial similar, I call it adversarial similar, I call it adversarial development. Where basically after a development. Where basically after a development. Where basically after a Claude code finishes building something, Claude code finishes building something, Claude code finishes building something, I'll have a separate Claude code session I'll have a separate Claude code session I'll have a separate Claude code session um where I prompt it specifically to um where I prompt it specifically to um where I prompt it specifically to play the devil's advocate. Like I want play the devil's advocate. Like I want play the devil's advocate. Like I want you to be mean to the other Claude code you to be mean to the other Claude code you to be mean to the other Claude code session to like really make sure that session to like really make sure that session to like really make sure that it's not just being happy-go-lucky when it's not just being happy-go-lucky when it's not just being happy-go-lucky when there are actually some some problems there are actually some some problems there are actually some some problems that need to be surfaced. And like that that need to be surfaced. And like that that need to be surfaced. And like that works really well. So just generally works really well. So just generally works really well. So just generally like pitting large language models like pitting large language models like pitting large language models against each other against each other against each other >> Mhm.

>> Mhm. >> Mhm. >> is a good idea. Um I wish I had tried >> is a good idea. Um I wish I had tried >> is a good idea. Um I wish I had tried that before. So yeah, I'll I'll give that before. So yeah, I'll I'll give that before. So yeah, I'll I'll give that a shot. I think that that's that's that a shot. I think that that's that's that a shot. I think that that's that's a really good use for agent teams. Cuz a really good use for agent teams. Cuz a really good use for agent teams. Cuz at that point at at that point it's like at that point at at that point it's like at that point at at that point it's like you're not relying on it getting the you're not relying on it getting the you're not relying on it getting the perfect answer. perfect answer. perfect answer. Like it it's very token heavy, and the Like it it's very token heavy, and the Like it it's very token heavy, and the communications aren't really perfect, so communications aren't really perfect, so communications aren't really perfect, so that's why I don't really recommend that's why I don't really recommend that's why I don't really recommend agent teams when you're trying to do agent teams when you're trying to do agent teams when you're trying to do like deep development or like building like deep development or like building like deep development or like building any kinds of like complex automations. any kinds of like complex automations. any kinds of like complex automations. But when it's more like research and But when it's more like research and But when it's more like research and just like forming a consensus, I I think just like forming a consensus, I I think just like forming a consensus, I I think that it does really it would do really that it does really it would do really that it does really it would do really well for that. I'll try it out. well for that. I'll try it out. well for that. I'll try it out. >> Cool. Yeah, let me know if you try it >> Cool. Yeah, let me know if you try it >> Cool. Yeah, let me know if you try it out and what you think, but I've never out and what you think, but I've never out and what you think, but I've never >> Yeah. >> Yeah. >> Yeah. >> really talked about that or made a video >> really talked about that or made a video >> really talked about that or made a video because I know people would go do it and because I know people would go do it and because I know people would go do it and then be like, "You just killed my 5-hour then be like, "You just killed my 5-hour then be like, "You just killed my 5-hour limit." limit." limit." >> [laughter] >> [laughter] >> [laughter] >> Right. Yeah. >> Right. Yeah. >> Right. Yeah. >> Fortunately. >> Fortunately. >> Fortunately. >> So, um >> So, um >> So, um >> How much of your limit does it use when >> How much of your limit does it use when >> How much of your limit does it use when you typically do it? you typically do it? you typically do it? >> on the 200 buck >> on the 200 buck >> on the 200 buck 200 bucks a month plan, anywhere from, 200 bucks a month plan, anywhere from, 200 bucks a month plan, anywhere from, you know, 4% to to 10 sometimes, like, you know, 4% to to 10 sometimes, like, you know, 4% to to 10 sometimes, like, you know, you know, you know, >> It's not too bad. >> It's not too bad. >> It's not too bad. >> It's not too bad, but, you know, if if >> It's not too bad, but, you know, if if >> It's not too bad, but, you know, if if you if you say something like a you if you say something like a you if you say something like a "Don't stop until everyone agrees" and "Don't stop until everyone agrees" and "Don't stop until everyone agrees" and they just keep going, then it you could they just keep going, then it you could they just keep going, then it you could you could run into some some trouble, you could run into some some trouble, you could run into some some trouble, but but but to close this off here, I have to ask, to close this off here, I have to ask, to close this off here, I have to ask, I just did a video about my favorite I just did a video about my favorite I just did a video about my favorite features in Cloud Code, and I prefaced features in Cloud Code, and I prefaced features in Cloud Code, and I prefaced that whole video and basically said, that whole video and basically said, that whole video and basically said, "This is not a list of the best features "This is not a list of the best features "This is not a list of the best features or, you know, the most used or the the or, you know, the most used or the the or, you know, the most used or the the most useful. These are basically the way most useful. These are basically the way most useful. These are basically the way that I use Cloud Code on my day-to-day, that I use Cloud Code on my day-to-day, that I use Cloud Code on my day-to-day, the ones that I like the most." And I I the ones that I like the most." And I I the ones that I like the most." And I I had like a a numbered list of 12 at the had like a a numbered list of 12 at the had like a a numbered list of 12 at the top. But, I would love to hear from you top. But, I would love to hear from you top. But, I would love to hear from you to put you on the spot. If you had like to put you on the spot. If you had like to put you on the spot. If you had like a top three based on cuz I I'm assuming

a top three based on cuz I I'm assuming a top three based on cuz I I'm assuming we use Cloud Code very differently. What we use Cloud Code very differently. What we use Cloud Code very differently. What would you say are like your top three would you say are like your top three would you say are like your top three favorites? favorites? favorites? >> Hm. >> Hm. >> Hm. Yeah, so, uh hooks is definitely Maybe Yeah, so, uh hooks is definitely Maybe Yeah, so, uh hooks is definitely Maybe not like my favorite favorite, but not like my favorite favorite, but not like my favorite favorite, but probably the one that like most people probably the one that like most people probably the one that like most people wouldn't put in their top three. And wouldn't put in their top three. And wouldn't put in their top three. And that's because of what I've been doing that's because of what I've been doing that's because of what I've been doing with it for security and then the whole with it for security and then the whole with it for security and then the whole um integration with the second brain. um integration with the second brain. um integration with the second brain. So, it's able to basically like extract So, it's able to basically like extract So, it's able to basically like extract summaries and like remember things over summaries and like remember things over summaries and like remember things over time. time. time. >> definitely need a hooks cool video. >> definitely need a hooks cool video. >> definitely need a hooks cool video. >> Yeah, I honestly, I should just do that >> Yeah, I honestly, I should just do that >> Yeah, I honestly, I should just do that next week. next week. next week. >> Yeah, we definitely need it. >> Yeah, we definitely need it. >> Yeah, we definitely need it. >> Yeah. Okay. Yeah, thanks, Nate. Yeah, >> Yeah. Okay. Yeah, thanks, Nate. Yeah, >> Yeah. Okay. Yeah, thanks, Nate. Yeah, so, yeah, hooks hooks is definitely so, yeah, hooks hooks is definitely so, yeah, hooks hooks is definitely number one. number one. number one. >> Okay. >> Okay. >> Okay. >> And then, uh here, I'll cuz I I >> And then, uh here, I'll cuz I I >> And then, uh here, I'll cuz I I mentioned some of the things here. Like, mentioned some of the things here. Like, mentioned some of the things here. Like, I mean, really, when I I mean, really, when I I mean, really, when I there's kind of two different sorts of there's kind of two different sorts of there's kind of two different sorts of Cloud Code features. You have like the Cloud Code features. You have like the Cloud Code features. You have like the components of the AI layer, like rule components of the AI layer, like rule components of the AI layer, like rule skills, hooks, and then you just have skills, hooks, and then you just have skills, hooks, and then you just have like general capabilities of the like general capabilities of the like general capabilities of the harness, like, um harness, like, um harness, like, um agent teams and slash by the way and and agent teams and slash by the way and and agent teams and slash by the way and and um dispatch or like dynamic workflows, um dispatch or like dynamic workflows, um dispatch or like dynamic workflows, things like that, right? So, either like things like that, right? So, either like things like that, right? So, either like it's something that you use or it's it's something that you use or it's it's something that you use or it's something that you build on top of. something that you build on top of. something that you build on top of. Um sub-agents would be probably like Um sub-agents would be probably like Um sub-agents would be probably like number two.

number two. number two. Um just because like I said, there's Um just because like I said, there's Um just because like I said, there's dangers to using sub-agents. dangers to using sub-agents. dangers to using sub-agents. But just using them to like sprawl out But just using them to like sprawl out But just using them to like sprawl out and research a ton of different things, and research a ton of different things, and research a ton of different things, I use it for that all of the time. And I use it for that all of the time. And I use it for that all of the time. And especially when I'm working on more especially when I'm working on more especially when I'm working on more complex code bases or building out complex code bases or building out complex code bases or building out larger automations, I'm using sub-agents larger automations, I'm using sub-agents larger automations, I'm using sub-agents to basically like extract context from to basically like extract context from to basically like extract context from certain parts of my system. Right? Like certain parts of my system. Right? Like certain parts of my system. Right? Like you're responsible for getting a you're responsible for getting a you're responsible for getting a grounding here of like how we're going grounding here of like how we're going grounding here of like how we're going to have to mess with the front end in to have to mess with the front end in to have to mess with the front end in this application, how we're going to this application, how we're going to this application, how we're going to have to mess with the back end. have to mess with the back end. have to mess with the back end. Um and then Um and then Um and then I honestly probably like my number of I honestly probably like my number of I honestly probably like my number of one. So I guess like hooks would be two one. So I guess like hooks would be two one. So I guess like hooks would be two and sub-agents would be three. Probably and sub-agents would be three. Probably and sub-agents would be three. Probably my my number one is skills, even though my my number one is skills, even though my my number one is skills, even though it's like super super cliche. it's like super super cliche. it's like super super cliche. >> That was my pick. >> That was my pick. >> That was my pick. >> it Yeah, it's got to be skills. Yeah. >> it Yeah, it's got to be skills. Yeah. >> it Yeah, it's got to be skills. Yeah. >> Yeah, like skills skills dictate >> Yeah, like skills skills dictate >> Yeah, like skills skills dictate everything. Skill I have a skill for everything. Skill I have a skill for everything. Skill I have a skill for making this diagram. I have a skill for making this diagram. I have a skill for making this diagram. I have a skill for scripting my YouTube videos. I have a scripting my YouTube videos. I have a scripting my YouTube videos. I have a skill for building PowerPoints. I have a skill for building PowerPoints. I have a skill for building PowerPoints. I have a skill for skill for skill for um I mean if you could literally name um I mean if you could literally name um I mean if you could literally name anything. anything. anything. >> Yeah. >> Yeah. >> Yeah. >> Yeah, it's just any kind of reusable >> Yeah, it's just any kind of reusable >> Yeah, it's just any kind of reusable prompt, you just make it as a skill.

prompt, you just make it as a skill. prompt, you just make it as a skill. >> Mhm. >> Mhm. >> Mhm. >> And Claude Code has done a really good >> And Claude Code has done a really good >> And Claude Code has done a really good job continuing to evolve just like the job continuing to evolve just like the job continuing to evolve just like the way you can parameterize things. Like way you can parameterize things. Like way you can parameterize things. Like they have like um path scope skills now they have like um path scope skills now they have like um path scope skills now and you can like set if this one is to and you can like set if this one is to and you can like set if this one is to be invoked only by you or if the agent be invoked only by you or if the agent be invoked only by you or if the agent can decide to do it as well. can decide to do it as well. can decide to do it as well. Um and then like talking about like Um and then like talking about like Um and then like talking about like verification verification verification like getting back to here, like having like getting back to here, like having like getting back to here, like having that browser automation skill so it that browser automation skill so it that browser automation skill so it knows how to use a CLI. Um like that's a knows how to use a CLI. Um like that's a knows how to use a CLI. Um like that's a whole 'nother thing is like that the whole 'nother thing is like that the whole 'nother thing is like that the skill plus CLI combination is just skill plus CLI combination is just skill plus CLI combination is just really really powerful. Cuz basically really really powerful. Cuz basically really really powerful. Cuz basically any platform or tool you want your any platform or tool you want your any platform or tool you want your coding agent to be able to use, it's coding agent to be able to use, it's coding agent to be able to use, it's either going to be an MCP server and either going to be an MCP server and either going to be an MCP server and like those are still good, but honestly like those are still good, but honestly like those are still good, but honestly I would have think is even better, like I would have think is even better, like I would have think is even better, like more token efficient, is having a CLI so more token efficient, is having a CLI so more token efficient, is having a CLI so it has access to your CRM or GitHub or it has access to your CRM or GitHub or it has access to your CRM or GitHub or whatever through the CLI. And then the whatever through the CLI. And then the whatever through the CLI. And then the skill it tells it how to use that CLI skill it tells it how to use that CLI skill it tells it how to use that CLI and then more it more specifically like and then more it more specifically like and then more it more specifically like how you want it to use that like what how you want it to use that like what how you want it to use that like what how did you want to this CLI to be how did you want to this CLI to be how did you want to this CLI to be integrated in your workflow. So like integrated in your workflow. So like integrated in your workflow. So like that combination I'm leaning on that for that combination I'm leaning on that for that combination I'm leaning on that for everything. It's like my Archon tool I everything. It's like my Archon tool I everything. It's like my Archon tool I was talking about earlier like it is a was talking about earlier like it is a was talking about earlier like it is a CLI that has a skill that comes with it.

CLI that has a skill that comes with it. CLI that has a skill that comes with it. So like if you want those more So like if you want those more So like if you want those more deterministic workflows where you get to deterministic workflows where you get to deterministic workflows where you get to pick like when do we have the LLM when pick like when do we have the LLM when pick like when do we have the LLM when are we just running code then like you are we just running code then like you are we just running code then like you build that as a workflow and then now build that as a workflow and then now build that as a workflow and then now Archon with its skill and its CLI Archon with its skill and its CLI Archon with its skill and its CLI becomes a tool that my second brain can becomes a tool that my second brain can becomes a tool that my second brain can call upon whenever it wants to dispatch call upon whenever it wants to dispatch call upon whenever it wants to dispatch one of those workflows to go handle a one of those workflows to go handle a one of those workflows to go handle a GitHub issue or run this automation GitHub issue or run this automation GitHub issue or run this automation whatever it is. whatever it is. whatever it is. >> Very cool. I love it. Yeah, I love the >> Very cool. I love it. Yeah, I love the >> Very cool. I love it. Yeah, I love the list. My top three list. My top three list. My top three were skills as number one. were skills as number one. were skills as number one. >> Okay. >> Okay. >> Okay. >> Number two I had status line. >> Number two I had status line. >> Number two I had status line. >> [laughter] >> [laughter] >> [laughter] >> Oh, nice. >> Oh, nice. >> Oh, nice. I respect that. I respect that. I respect that. >> of life thing, you know, just seeing the >> of life thing, you know, just seeing the >> of life thing, you know, just seeing the model, the effort, the window. I love model, the effort, the window. I love model, the effort, the window. I love that. And then my number three was that. And then my number three was that. And then my number three was routines. routines. routines. I love the I love the I love the the cloud routines. I I just think it's the cloud routines. I I just think it's the cloud routines. I I just think it's so cool that you know, I know I know so cool that you know, I know I know so cool that you know, I know I know we've got the SDK and whatnot, but it's we've got the SDK and whatnot, but it's we've got the SDK and whatnot, but it's just nice to be able to schedule just nice to be able to schedule just nice to be able to schedule something that is just my cloud code something that is just my cloud code something that is just my cloud code going and yeah, I think those are my top going and yeah, I think those are my top going and yeah, I think those are my top three and I'm sure they'll they'll move three and I'm sure they'll they'll move three and I'm sure they'll they'll move around, but yeah, I appreciate you around, but yeah, I appreciate you around, but yeah, I appreciate you sharing yours. It was interesting to sharing yours. It was interesting to sharing yours. It was interesting to hear. I'm glad that hooks made the list. hear. I'm glad that hooks made the list. hear. I'm glad that hooks made the list. So I'll definitely be keeping my eye out So I'll definitely be keeping my eye out So I'll definitely be keeping my eye out for that video though. for that video though. for that video though. >> Sounds good. Yeah, all right. What do >> Sounds good. Yeah, all right. What do >> Sounds good. Yeah, all right. What do you use routines for?

you use routines for? you use routines for? >> Um well, I've got one going now that is >> Um well, I've got one going now that is >> Um well, I've got one going now that is a a trading bot. I had that originally a a trading bot. I had that originally a a trading bot. I had that originally going with an open claw agent, but I going with an open claw agent, but I going with an open claw agent, but I switched it over to routines just to see switched it over to routines just to see switched it over to routines just to see how how it would do there. how how it would do there. how how it would do there. But then other things just like it's But then other things just like it's But then other things just like it's actually doing worse there. actually doing worse there. actually doing worse there. Yeah, it's doing worse there right now, Yeah, it's doing worse there right now, Yeah, it's doing worse there right now, but I don't know if it's I mean the but I don't know if it's I mean the but I don't know if it's I mean the market and everything as well, but market and everything as well, but market and everything as well, but I think open claw had I think open claw had I think open claw had just out of the box it had better just out of the box it had better just out of the box it had better memory capabilities for that sort of memory capabilities for that sort of memory capabilities for that sort of thing. So thing. So thing. So >> Yeah, makes sense. >> Yeah, makes sense. >> Yeah, makes sense. >> Um but then >> Um but then >> Um but then you know, just your other standard stuff you know, just your other standard stuff you know, just your other standard stuff like checking in on the team and giving like checking in on the team and giving like checking in on the team and giving me updates throughout the week and um me updates throughout the week and um me updates throughout the week and um end of week reports. Just very, very end of week reports. Just very, very end of week reports. Just very, very simple things, but nice to throw the simple things, but nice to throw the simple things, but nice to throw the routines in there. So, routines in there. So, routines in there. So, >> [snorts] >> [snorts] >> [snorts] >> yeah, I really appreciate you walking us >> yeah, I really appreciate you walking us >> yeah, I really appreciate you walking us through all this stuff today. Is there through all this stuff today. Is there through all this stuff today. Is there anything else that you want to leave anything else that you want to leave anything else that you want to leave everyone with? everyone with? everyone with? >> Uh that's a good question. Yeah, I I >> Uh that's a good question. Yeah, I I >> Uh that's a good question. Yeah, I I would I would say that no matter how would I would say that no matter how would I would say that no matter how technical you are, really what it comes technical you are, really what it comes technical you are, really what it comes down to is you can think of yourself down to is you can think of yourself down to is you can think of yourself like the product manager for Claude like the product manager for Claude like the product manager for Claude Code. Code. Code. So, you don't necessarily have to So, you don't necessarily have to So, you don't necessarily have to describe how to build something, but describe how to build something, but describe how to build something, but it's important for you to shape the it's important for you to shape the it's important for you to shape the vision, right? Like what are we going to vision, right? Like what are we going to vision, right? Like what are we going to build? And then uh a lot of people are build? And then uh a lot of people are build? And then uh a lot of people are calling this intent engineering now. I calling this intent engineering now. I calling this intent engineering now. I mean, it's kind of another buzzword.

mean, it's kind of another buzzword. mean, it's kind of another buzzword. It's basically like you want to you want It's basically like you want to you want It's basically like you want to you want to give like the why. Like Claude Code, to give like the why. Like Claude Code, to give like the why. Like Claude Code, this is why we're building this thing this is why we're building this thing this is why we're building this thing cuz that really actually ends up shaping cuz that really actually ends up shaping cuz that really actually ends up shaping the how quite well. So, if like that's a the how quite well. So, if like that's a the how quite well. So, if like that's a big part of your planning process, big part of your planning process, big part of your planning process, that's going to take you far. And like that's going to take you far. And like that's going to take you far. And like it it it seems kind of silly cuz you it it it seems kind of silly cuz you it it it seems kind of silly cuz you really start to get into the sort of really start to get into the sort of really start to get into the sort of like the personification of Claude Code like the personification of Claude Code like the personification of Claude Code when you're you're telling it why you're when you're you're telling it why you're when you're you're telling it why you're doing things, but like it actually makes doing things, but like it actually makes doing things, but like it actually makes a difference. You kind of have to like a difference. You kind of have to like a difference. You kind of have to like get over yourself and be like it's kind get over yourself and be like it's kind get over yourself and be like it's kind of cringe to treat it like a person, but of cringe to treat it like a person, but of cringe to treat it like a person, but like that actually is how you get the like that actually is how you get the like that actually is how you get the best results. So, just just do it. It best results. So, just just do it. It best results. So, just just do it. It actually helps a lot and make good plans actually helps a lot and make good plans actually helps a lot and make good plans and good specs going into whatever and good specs going into whatever and good specs going into whatever you're building with Claude or you're building with Claude or you're building with Claude or automating. automating. automating. >> Great tip. Great tip. I actually did >> Great tip. Great tip. I actually did >> Great tip. Great tip. I actually did just yesterday read in the Claude docs just yesterday read in the Claude docs just yesterday read in the Claude docs on how to prompt 4.8 that it said that. on how to prompt 4.8 that it said that. on how to prompt 4.8 that it said that. It said to give it the context for why It said to give it the context for why It said to give it the context for why you're doing something and it will you're doing something and it will you're doing something and it will probably do a better job. So, that's probably do a better job. So, that's probably do a better job. So, that's awesome. Cole, where can people find you awesome. Cole, where can people find you awesome. Cole, where can people find you if they want to watch more of your stuff if they want to watch more of your stuff if they want to watch more of your stuff or get in touch? or get in touch? or get in touch? >> Yeah, so YouTube channel is the main >> Yeah, so YouTube channel is the main >> Yeah, so YouTube channel is the main place for me to put all my content. So, place for me to put all my content. So, place for me to put all my content. So, you can just search my name, Cole Medin.

you can just search my name, Cole Medin. you can just search my name, Cole Medin. Uh it is not spelled as you think. It's Uh it is not spelled as you think. It's Uh it is not spelled as you think. It's m e d i n. Sounds like Medin. Everyone m e d i n. Sounds like Medin. Everyone m e d i n. Sounds like Medin. Everyone says it wrong. Um but yeah, that's says it wrong. Um but yeah, that's says it wrong. Um but yeah, that's that's my YouTube channel and then uh that's my YouTube channel and then uh that's my YouTube channel and then uh also doing a lot of posting on LinkedIn also doing a lot of posting on LinkedIn also doing a lot of posting on LinkedIn as well. as well. as well. Same name, obviously. Same name, obviously. Same name, obviously. >> There we go. Yeah, I think for the first >> There we go. Yeah, I think for the first >> There we go. Yeah, I think for the first multiple months I knew you, I thought it multiple months I knew you, I thought it multiple months I knew you, I thought it was Cole Medin and I was saying I was was Cole Medin and I was saying I was was Cole Medin and I was saying I was saying Medin all the time. saying Medin all the time. saying Medin all the time. >> Nice. Yeah. >> Nice. Yeah. >> Nice. Yeah. >> Good to know everyone cleared up it's >> Good to know everyone cleared up it's >> Good to know everyone cleared up it's Cole Medin. Cole Medin. Cole Medin. >> That's right. Yeah, it's a Swedish last >> That's right. Yeah, it's a Swedish last >> That's right. Yeah, it's a Swedish last name. And yeah, Nate, there's there's name. And yeah, Nate, there's there's name. And yeah, Nate, there's there's people that said it way worse than you. people that said it way worse than you. people that said it way worse than you. Like someone called me Melden Like someone called me Melden Like someone called me Melden live on stage at a chess tournament in live on stage at a chess tournament in live on stage at a chess tournament in high school. Like it's it's been worse. high school. Like it's it's been worse. high school. Like it's it's been worse. >> Oh man, yeah. I don't know a lot of >> Oh man, yeah. I don't know a lot of >> Oh man, yeah. I don't know a lot of people have hallucinated the L in there. people have hallucinated the L in there. people have hallucinated the L in there. I've noticed that. I'm not sure why. I've noticed that. I'm not sure why. I've noticed that. I'm not sure why. >> Yeah. Yeah, I've had a lot of people >> Yeah. Yeah, I've had a lot of people >> Yeah. Yeah, I've had a lot of people spell it to me as Melden. Or Medlin. spell it to me as Melden. Or Medlin. spell it to me as Melden. Or Medlin. >> Oh, wow. Okay, cuz I that's actually a >> Oh, wow. Okay, cuz I that's actually a >> Oh, wow. Okay, cuz I that's actually a one-time thing for me. That's one-time thing for me. That's one-time thing for me. That's surprising. surprising. surprising. >> No, I've gotten that a lot for some >> No, I've gotten that a lot for some >> No, I've gotten that a lot for some reason, but reason, but reason, but Anyways, yeah, thank you so much for Anyways, yeah, thank you so much for Anyways, yeah, thank you so much for hopping on, Cole. hopping on, Cole. hopping on, Cole. I was here to I was here to I was here to not only chat with you, but I also not only chat with you, but I also not only chat with you, but I also learned a lot as well. So, thank you so learned a lot as well. So, thank you so learned a lot as well. So, thank you so much as always. It's a pleasure to get much as always. It's a pleasure to get much as always. It's a pleasure to get to speak with you, and hopefully we can to speak with you, and hopefully we can to speak with you, and hopefully we can do it again soon.

do it again soon. do it again soon. >> Yeah, sounds good. I appreciate it. >> Yeah, sounds good. I appreciate it. >> Yeah, sounds good. I appreciate it. Thank you as well, Nate. This was Thank you as well, Nate. This was Thank you as well, Nate. This was awesome. awesome. awesome. >> Absolutely. >> Absolutely. >> Absolutely. >> chatting with you. >> chatting with you. >> chatting with you. >> Awesome, there we go. All right, take it >> Awesome, there we go. All right, take it >> Awesome, there we go. All right, take it easy, Cole. easy, Cole. easy, Cole. >> Have a good one. >> Have a good one. >> Have a good one. >> Thanks so much for watching today's >> Thanks so much for watching today's >> Thanks so much for watching today's episode. I hope that you guys enjoyed. episode. I hope that you guys enjoyed. episode. I hope that you guys enjoyed. Don't forget that I broke all of this Don't forget that I broke all of this Don't forget that I broke all of this down into a free resource guide that you down into a free resource guide that you down into a free resource guide that you can access for completely free using the can access for completely free using the can access for completely free using the link in the description to join our free link in the description to join our free link in the description to join our free school community. I'll see you guys in school community. I'll see you guys in school community. I'll see you guys in there. Thanks so much.