Every Level of a Claude Second Brain Explained

Today, I'm going to explain the Today, I'm going to explain the different levels of building your own AI different levels of building your own AI different levels of building your own AI second brain. You can see here we have a second brain. You can see here we have a second brain. You can see here we have a visual of three very different types of visual of three very different types of visual of three very different types of data. This one is where we have our data. This one is where we have our data. This one is where we have our context really starting to form and context really starting to form and context really starting to form and we're starting to see some relationships we're starting to see some relationships we're starting to see some relationships and we're starting to see some different and we're starting to see some different and we're starting to see some different nodes and entities form. And then as we nodes and entities form. And then as we nodes and entities form. And then as we continue to scale this up, add more continue to scale this up, add more continue to scale this up, add more knowledge, more knowledge, more knowledge, more knowledge, more knowledge, more knowledge, more relationships, we start to get something relationships, we start to get something relationships, we start to get something that looks a little bit more like this that looks a little bit more like this that looks a little bit more like this where we have clearly different clusters where we have clearly different clusters where we have clearly different clusters and inside of all of these nodes we can and inside of all of these nodes we can and inside of all of these nodes we can see how they relate to each other. And see how they relate to each other. And see how they relate to each other. And then over here we're taking all of those then over here we're taking all of those then over here we're taking all of those relationships a step farther and we're relationships a step farther and we're relationships a step farther and we're able to then start to see how everything able to then start to see how everything able to then start to see how everything really pieces together rather than just really pieces together rather than just really pieces together rather than just having files that sort of link back to having files that sort of link back to having files that sort of link back to each other. This is relationship each other. This is relationship each other. This is relationship mapping. And so really the idea of an AI mapping. And so really the idea of an AI mapping. And so really the idea of an AI second brain has blown up because we're second brain has blown up because we're second brain has blown up because we're all trying to get as much information all trying to get as much information all trying to get as much information out of our heads into our systems as out of our heads into our systems as out of our heads into our systems as possible. That's the true value. Your possible. That's the true value. Your possible. That's the true value. Your moat is your data, it's your IP. But the moat is your data, it's your IP. But the moat is your data, it's your IP. But the process of organizing that into a system process of organizing that into a system process of organizing that into a system so that you can use it with a bunch of so that you can use it with a bunch of so that you can use it with a bunch of different AI models and so that it can different AI models and so that it can different AI models and so that it can actually recall things in a way that actually recall things in a way that actually recall things in a way that makes sense rather than just makes sense rather than just makes sense rather than just hallucinating or spending a bunch of hallucinating or spending a bunch of hallucinating or spending a bunch of your time and tokens trying to look your time and tokens trying to look your time and tokens trying to look through everything. That's the issue. So through everything. That's the issue. So through everything. That's the issue. So clearly all of this is my real data and clearly all of this is my real data and clearly all of this is my real data and this is what the actual project looks this is what the actual project looks this is what the actual project looks like. It is my Hercule project. I have a like. It is my Hercule project. I have a like. It is my Hercule project. I have a bunch of folders and files here and at bunch of folders and files here and at bunch of folders and files here and at the end of the day that's basically all the end of the day that's basically all the end of the day that's basically all it is. It is markdown files that are it is. It is markdown files that are it is. It is markdown files that are organized in a way that I understand and organized in a way that I understand and organized in a way that I understand and that my agents understand. And so yes, that my agents understand. And so yes, that my agents understand. And so yes, I'm going to walk you guys through what I'm going to walk you guys through what I'm going to walk you guys through what I have here and how it works, but I also I have here and how it works, but I also I have here and how it works, but I also have this other project where I'm going have this other project where I'm going have this other project where I'm going to show you if you're starting from to show you if you're starting from to show you if you're starting from scratch or if you feel like maybe you're scratch or if you feel like maybe you're scratch or if you feel like maybe you're in between level two and three, how we in between level two and three, how we in between level two and three, how we can actually look at the differences and can actually look at the differences and can actually look at the differences and what it might look like to scale up your what it might look like to scale up your what it might look like to scale up your own systems and start to add context in own systems and start to add context in own systems and start to add context in different ways. So super excited to dig

different ways. So super excited to dig different ways. So super excited to dig into this today and I don't want to into this today and I don't want to into this today and I don't want to waste any of you guys' time, so let's waste any of you guys' time, so let's waste any of you guys' time, so let's just start looking at these five levels just start looking at these five levels just start looking at these five levels and how they differ. All right, so every and how they differ. All right, so every and how they differ. All right, so every level of a Claude Code second brain and level of a Claude Code second brain and level of a Claude Code second brain and I'm going to be obviously kind of I'm going to be obviously kind of I'm going to be obviously kind of referring to Claude Code a lot, but keep referring to Claude Code a lot, but keep referring to Claude Code a lot, but keep in mind this can be used with any AI in mind this can be used with any AI in mind this can be used with any AI model. I use my second brain all the model. I use my second brain all the model. I use my second brain all the time with Codex as well. I use it with time with Codex as well. I use it with time with Codex as well. I use it with Hermes Agent. This can be used by Hermes Agent. This can be used by Hermes Agent. This can be used by different agent harnesses because it's different agent harnesses because it's different agent harnesses because it's just files and folders. So, what is the just files and folders. So, what is the just files and folders. So, what is the actual job of a second brain? A lot of actual job of a second brain? A lot of actual job of a second brain? A lot of people probably define this differently, people probably define this differently, people probably define this differently, but the way that I think about it is but the way that I think about it is but the way that I think about it is that it's a place for me to save notes, that it's a place for me to save notes, that it's a place for me to save notes, meeting recordings, ClickUp threads, meeting recordings, ClickUp threads, meeting recordings, ClickUp threads, stuff like that. I can save it there, stuff like that. I can save it there, stuff like that. I can save it there, and then it helps me basically ingest it and then it helps me basically ingest it and then it helps me basically ingest it and get it into the right spots so that and get it into the right spots so that and get it into the right spots so that it can actually find it later. And so it can actually find it later. And so it can actually find it later. And so that's really the thing to think about that's really the thing to think about that's really the thing to think about is can your agent find it again, and is can your agent find it again, and is can your agent find it again, and could you find it again? Because if the could you find it again? Because if the could you find it again? Because if the answer is no, then you probably don't answer is no, then you probably don't answer is no, then you probably don't have the right routing or folder have the right routing or folder have the right routing or folder architecture set up, which is what I'm architecture set up, which is what I'm architecture set up, which is what I'm here to talk about today. And one other here to talk about today. And one other here to talk about today. And one other sort of mindset thing that I want to get sort of mindset thing that I want to get sort of mindset thing that I want to get out there before we dive into these five out there before we dive into these five out there before we dive into these five levels is that levels is that levels is that you kind of have to work backwards. You you kind of have to work backwards. You you kind of have to work backwards. You want to reverse engineer based on the want to reverse engineer based on the want to reverse engineer based on the question. So this will start to make question. So this will start to make question. So this will start to make more sense as we get into it, but really more sense as we get into it, but really more sense as we get into it, but really what you should be thinking about is how what you should be thinking about is how what you should be thinking about is how do I want to use this data in the do I want to use this data in the do I want to use this data in the future? Because how it's going to be future? Because how it's going to be future? Because how it's going to be accessed and recalled determines the way accessed and recalled determines the way accessed and recalled determines the way that you put it in in the first place.

that you put it in in the first place. that you put it in in the first place. For example, a basketball hoop and a For example, a basketball hoop and a For example, a basketball hoop and a basketball. We know what shape the hoop basketball. We know what shape the hoop basketball. We know what shape the hoop is, and we know that the ball needs to is, and we know that the ball needs to is, and we know that the ball needs to go through. So why would we ever design go through. So why would we ever design go through. So why would we ever design the ball to be a giant square? Because the ball to be a giant square? Because the ball to be a giant square? Because it just wouldn't fit through the hoop, it just wouldn't fit through the hoop, it just wouldn't fit through the hoop, so that would make no sense. So you need so that would make no sense. So you need so that would make no sense. So you need to start with the end in mind a little to start with the end in mind a little to start with the end in mind a little bit. Once again, I will show you exactly bit. Once again, I will show you exactly bit. Once again, I will show you exactly what I mean by that as we continue on. what I mean by that as we continue on. what I mean by that as we continue on. Because remember, we're trying to get to Because remember, we're trying to get to Because remember, we're trying to get to the point where your second brain knows the point where your second brain knows the point where your second brain knows everything about your business, about everything about your business, about everything about your business, about you, your relationships. It knows you, your relationships. It knows you, your relationships. It knows everything to the point where everything to the point where everything to the point where it probably can recall stuff better than it probably can recall stuff better than it probably can recall stuff better than you can because it has a better memory, you can because it has a better memory, you can because it has a better memory, and it can search through things way and it can search through things way and it can search through things way faster than you can. So we've got five faster than you can. So we've got five faster than you can. So we've got five different levels to talk about, and they different levels to talk about, and they different levels to talk about, and they each kind of have different questions. each kind of have different questions. each kind of have different questions. So level one is, can you find the file So level one is, can you find the file So level one is, can you find the file or the info by looking for an exact word or the info by looking for an exact word or the info by looking for an exact word or name? Level two is, can you pull or name? Level two is, can you pull or name? Level two is, can you pull everything on a certain topic together? everything on a certain topic together? everything on a certain topic together? Level three is, I search for different Level three is, I search for different Level three is, I search for different words than I wrote, so semantic search, words than I wrote, so semantic search, words than I wrote, so semantic search, you're searching for meaning rather than you're searching for meaning rather than you're searching for meaning rather than an exact word match. And then trace an exact word match. And then trace an exact word match. And then trace relationship chains. Can you ask about relationship chains. Can you ask about relationship chains. Can you ask about topic X, and then trace that all the way topic X, and then trace that all the way topic X, and then trace that all the way back to topic A? And then level five is back to topic A? And then level five is back to topic A? And then level five is just kind of making this whole second just kind of making this whole second just kind of making this whole second brain thing super autonomous to the brain thing super autonomous to the brain thing super autonomous to the point that you don't even have to think point that you don't even have to think point that you don't even have to think about it. And by the way, this isn't me about it. And by the way, this isn't me about it. And by the way, this isn't me saying that number five is best. I have saying that number five is best. I have saying that number five is best. I have some arguments about why I do not some arguments about why I do not some arguments about why I do not currently sit on level five. The point currently sit on level five. The point currently sit on level five. The point I'm trying to make here is each level is I'm trying to make here is each level is I'm trying to make here is each level is different and you want to find the different and you want to find the different and you want to find the simplest level or the lowest level that simplest level or the lowest level that simplest level or the lowest level that actually fits your needs. If you don't actually fits your needs. If you don't actually fits your needs. If you don't have a pain point in your system, then I have a pain point in your system, then I have a pain point in your system, then I don't really think there's a need to go don't really think there's a need to go don't really think there's a need to go experiment or develop a new sort of, you experiment or develop a new sort of, you experiment or develop a new sort of, you know, architecture. If there's not pain,

know, architecture. If there's not pain, know, architecture. If there's not pain, then why create more? Okay, so level one then why create more? Okay, so level one then why create more? Okay, so level one is pretty simple and this is where you is pretty simple and this is where you is pretty simple and this is where you always start. So you start with a always start. So you start with a always start. So you start with a claw.md or if you're using codex or claw.md or if you're using codex or claw.md or if you're using codex or something, you would start with an something, you would start with an something, you would start with an agents.md. agents.md. agents.md. But you start with a claw.md which is But you start with a claw.md which is But you start with a claw.md which is kind of, you know, that gets loaded up. kind of, you know, that gets loaded up. kind of, you know, that gets loaded up. That's almost like the system prompt for That's almost like the system prompt for That's almost like the system prompt for that session for that project. And then that session for that project. And then that session for that project. And then you've just got a bunch of folders and you've just got a bunch of folders and you've just got a bunch of folders and files. But the key part there is the files. But the key part there is the files. But the key part there is the claw.md is kind of treated as a router. claw.md is kind of treated as a router. claw.md is kind of treated as a router. So yes, you've got some, hey, this is So yes, you've got some, hey, this is So yes, you've got some, hey, this is your role, here is what's important, but your role, here is what's important, but your role, here is what's important, but you also have routing rules. If you ever you also have routing rules. If you ever you also have routing rules. If you ever need to find information about me need to find information about me need to find information about me personally, look in this folder. If you personally, look in this folder. If you personally, look in this folder. If you need information about our quarter one need information about our quarter one need information about our quarter one priorities, look in this folder. Because priorities, look in this folder. Because priorities, look in this folder. Because if you've ever had a point where you ask if you've ever had a point where you ask if you've ever had a point where you ask Claude to do something and then it asks Claude to do something and then it asks Claude to do something and then it asks you, hey, can you give me more info? I you, hey, can you give me more info? I you, hey, can you give me more info? I don't know what you're talking about, don't know what you're talking about, don't know what you're talking about, but you know there's files and folders but you know there's files and folders but you know there's files and folders in your project, then you probably just in your project, then you probably just in your project, then you probably just didn't give Claude the knowledge to go didn't give Claude the knowledge to go didn't give Claude the knowledge to go look there. It's not just going to go look there. It's not just going to go look there. It's not just going to go search your entire code base search your entire code base search your entire code base automatically. I mean, you wouldn't want automatically. I mean, you wouldn't want automatically. I mean, you wouldn't want it to do that cuz it's going to waste it to do that cuz it's going to waste it to do that cuz it's going to waste your time and your tokens. So if it your time and your tokens. So if it your time and your tokens. So if it doesn't know if something lives doesn't know if something lives doesn't know if something lives somewhere, then it's probably not going somewhere, then it's probably not going somewhere, then it's probably not going to be able to find it. So when this is to be able to find it. So when this is to be able to find it. So when this is properly set up, you will stop having to properly set up, you will stop having to properly set up, you will stop having to re-explain things, you will talk to it re-explain things, you will talk to it re-explain things, you will talk to it and it will just know where to go look and it will just know where to go look and it will just know where to go look and why. But the problems with this is and why. But the problems with this is and why. But the problems with this is that if it grows too big, it can start that if it grows too big, it can start that if it grows too big, it can start to get messy and feel ignored. And this to get messy and feel ignored. And this to get messy and feel ignored. And this is typically more of like an exact words is typically more of like an exact words is typically more of like an exact words type of search depending on the way that type of search depending on the way that type of search depending on the way that you route. So if I open up my um example you route. So if I open up my um example you route. So if I open up my um example project here, let's open up level one.

project here, let's open up level one. project here, let's open up level one. So in level one, what you can see, So in level one, what you can see, So in level one, what you can see, pretend this is its own Claude project, pretend this is its own Claude project, pretend this is its own Claude project, we've got a claw.md. So let me click we've got a claw.md. So let me click we've got a claw.md. So let me click into that. We can see here it says, this into that. We can see here it says, this into that. We can see here it says, this file loads automatically every time you file loads automatically every time you file loads automatically every time you open Claude Code in this folder. It is open Claude Code in this folder. It is open Claude Code in this folder. It is the one file that tells the AI who you the one file that tells the AI who you the one file that tells the AI who you are, how you work, and where things are, how you work, and where things are, how you work, and where things live. At level one, this file plus a few live. At level one, this file plus a few live. At level one, this file plus a few folders is your entire second brain. So, folders is your entire second brain. So, folders is your entire second brain. So, here's kind of like that basic here's kind of like that basic here's kind of like that basic knowledge, and then right here, it's knowledge, and then right here, it's knowledge, and then right here, it's this simple, where things live. In the this simple, where things live. In the this simple, where things live. In the context folder, always true background context folder, always true background context folder, always true background about you and how you work, read this about you and how you work, read this about you and how you work, read this first. Projects, decision log, and first. Projects, decision log, and first. Projects, decision log, and that's basically it. So, right here you that's basically it. So, right here you that's basically it. So, right here you can see there's a context folder, we can see there's a context folder, we can see there's a context folder, we have an about me file, which you could have an about me file, which you could have an about me file, which you could grow. We have stack and conversations grow. We have stack and conversations grow. We have stack and conversations file. We have decisions, so this is a file. We have decisions, so this is a file. We have decisions, so this is a decision log where you can have your decision log where you can have your decision log where you can have your Claude at MD always append new decisions Claude at MD always append new decisions Claude at MD always append new decisions and dates whenever you make a big change and dates whenever you make a big change and dates whenever you make a big change to your project or to your life or to to your project or to your life or to to your project or to your life or to your business. And then we have your business. And then we have your business. And then we have projects, so this is where you could projects, so this is where you could projects, so this is where you could have a markdown file or even folders have a markdown file or even folders have a markdown file or even folders within the projects for all of your within the projects for all of your within the projects for all of your ongoing projects, all of your ongoing ongoing projects, all of your ongoing ongoing projects, all of your ongoing clients, whatever it is, however you clients, whatever it is, however you clients, whatever it is, however you want to organize it, that's where you want to organize it, that's where you want to organize it, that's where you can have some projects. And you can even can have some projects. And you can even can have some projects. And you can even start to organize these things by dates start to organize these things by dates start to organize these things by dates if you want. So, if you want to just if you want. So, if you want to just if you want. So, if you want to just have one that's for like May, and then have one that's for like May, and then have one that's for like May, and then you have all of those stuff, and you you have all of those stuff, and you you have all of those stuff, and you have one for June. The thing that I have one for June. The thing that I have one for June. The thing that I really want to stress here with level really want to stress here with level really want to stress here with level one, and the thing that I answer a lot one, and the thing that I answer a lot one, and the thing that I answer a lot in my community in the comments, is that in my community in the comments, is that in my community in the comments, is that there is not yet a standard way that has there is not yet a standard way that has there is not yet a standard way that has been proven the best way to set up your been proven the best way to set up your been proven the best way to set up your projects or your second brain besides projects or your second brain besides projects or your second brain besides some of the most common things like your some of the most common things like your some of the most common things like your contexts and your Claude at MD and your, contexts and your Claude at MD and your, contexts and your Claude at MD and your, you know, whatnot. But, the point I'm you know, whatnot. But, the point I'm you know, whatnot. But, the point I'm trying to make there is trying to make there is trying to make there is don't see what I do and think that don't see what I do and think that don't see what I do and think that that's the right way, or see what that's the right way, or see what that's the right way, or see what someone else you watch does and think someone else you watch does and think someone else you watch does and think that that's the only right way.

that that's the only right way. that that's the only right way. All that matters is All that matters is All that matters is do you have proper routing in place, and do you have proper routing in place, and do you have proper routing in place, and does it make sense to you, and does it does it make sense to you, and does it does it make sense to you, and does it make sense to your AI? Okay, so let's make sense to your AI? Okay, so let's make sense to your AI? Okay, so let's say I have my Hercule project right say I have my Hercule project right say I have my Hercule project right here, and I need to find something in here, and I need to find something in here, and I need to find something in here, but I can't ask AI for some here, but I can't ask AI for some here, but I can't ask AI for some reason. What I need to find is easy reason. What I need to find is easy reason. What I need to find is easy because I understand the drill downs. because I understand the drill downs. because I understand the drill downs. You know, I understand my base folders, You know, I understand my base folders, You know, I understand my base folders, and let's say I'm looking for the HTML and let's say I'm looking for the HTML and let's say I'm looking for the HTML slide deck I built for my slide deck I built for my slide deck I built for my ranking Claude code features video. I ranking Claude code features video. I ranking Claude code features video. I would come into here and I say, okay, I would come into here and I say, okay, I would come into here and I say, okay, I know that's a project, so I'll go there. know that's a project, so I'll go there. know that's a project, so I'll go there. Within my projects, I've got another Within my projects, I've got another Within my projects, I've got another project for YouTube videos, I'll open project for YouTube videos, I'll open project for YouTube videos, I'll open that up. And now I know I made this that up. And now I know I made this that up. And now I know I made this video right here, May 30th Claude code video right here, May 30th Claude code video right here, May 30th Claude code top 50 features. In here, I have the top 50 features. In here, I have the top 50 features. In here, I have the actual tier list deck, and when I open actual tier list deck, and when I open actual tier list deck, and when I open that up, now I have the slide deck, and that up, now I have the slide deck, and that up, now I have the slide deck, and not only can I find it easily, but my not only can I find it easily, but my not only can I find it easily, but my agent can find it because it all makes agent can find it because it all makes agent can find it because it all makes sense and I have routing rules. Real sense and I have routing rules. Real sense and I have routing rules. Real quick, guys, if you're watching this quick, guys, if you're watching this quick, guys, if you're watching this video, you're probably interested in video, you're probably interested in video, you're probably interested in building your own AI operating system. building your own AI operating system. building your own AI operating system. Lucky for you, I have a full free course Lucky for you, I have a full free course Lucky for you, I have a full free course on that in my free school community. The on that in my free school community. The on that in my free school community. The link for that is down in the link for that is down in the link for that is down in the description. Join the free school description. Join the free school description. Join the free school community, hop in here, take the 7-day community, hop in here, take the 7-day community, hop in here, take the 7-day challenge, build your own AI operating challenge, build your own AI operating challenge, build your own AI operating system, and apply these principles into system, and apply these principles into system, and apply these principles into building your second brain, which will building your second brain, which will building your second brain, which will make your AI operating system even more make your AI operating system even more make your AI operating system even more powerful. So, link's in the description.

powerful. So, link's in the description. powerful. So, link's in the description. Let's get back to the video. Awesome. Let's get back to the video. Awesome. Let's get back to the video. Awesome. Okay, so that is how you start. Now, as Okay, so that is how you start. Now, as Okay, so that is how you start. Now, as you move up to level two, you might be you move up to level two, you might be you move up to level two, you might be able to start to work in some things able to start to work in some things able to start to work in some things like the LLM Wiki, which is what I've like the LLM Wiki, which is what I've like the LLM Wiki, which is what I've got set up for a few different things. got set up for a few different things. got set up for a few different things. This is the whole Karpathy LLM Wiki, This is the whole Karpathy LLM Wiki, This is the whole Karpathy LLM Wiki, which I did make a full video about if which I did make a full video about if which I did make a full video about if you want to check that out. I'll tag you want to check that out. I'll tag you want to check that out. I'll tag that right up here. But, this is when that right up here. But, this is when that right up here. But, this is when you start to have more files and and you start to have more files and and you start to have more files and and they start to take a bit of a different they start to take a bit of a different they start to take a bit of a different shape, and you want to organize them shape, and you want to organize them shape, and you want to organize them together in a bit of a different way. together in a bit of a different way. together in a bit of a different way. So, it could be really good for So, it could be really good for So, it could be really good for researching all on a certain project. It researching all on a certain project. It researching all on a certain project. It could be really good for, you know, a could be really good for, you know, a could be really good for, you know, a few of the ones that I've got set up is few of the ones that I've got set up is few of the ones that I've got set up is my YouTube transcripts all live in their my YouTube transcripts all live in their my YouTube transcripts all live in their own Wiki. I've got all of like my own Wiki. I've got all of like my own Wiki. I've got all of like my meeting transcripts that live in their meeting transcripts that live in their meeting transcripts that live in their own Wiki. So, for example, this is the own Wiki. So, for example, this is the own Wiki. So, for example, this is the Obsidian view of my Wiki for all of my Obsidian view of my Wiki for all of my Obsidian view of my Wiki for all of my YouTube video transcripts. You can see YouTube video transcripts. You can see YouTube video transcripts. You can see here if I go to Wiki, you can see here if I go to Wiki, you can see here if I go to Wiki, you can see there's main concepts like agentic there's main concepts like agentic there's main concepts like agentic workflows, AI coding market, context workflows, AI coding market, context workflows, AI coding market, context window. And all of these in here start window. And all of these in here start window. And all of these in here start to relate back to other tools and to relate back to other tools and to relate back to other tools and concepts and videos and stuff like that. concepts and videos and stuff like that. concepts and videos and stuff like that. So, we've got the sources, we've got So, we've got the sources, we've got So, we've got the sources, we've got platforms, we've got um context platforms, we've got um context platforms, we've got um context management techniques. And all of this management techniques. And all of this management techniques. And all of this was auto-created by our Claude code when was auto-created by our Claude code when was auto-created by our Claude code when I told it to ingest this YouTube I told it to ingest this YouTube I told it to ingest this YouTube transcript into our Wiki. So, I'm not transcript into our Wiki. So, I'm not transcript into our Wiki. So, I'm not going to dive super super deep into all going to dive super super deep into all going to dive super super deep into all of this right now, but definitely check of this right now, but definitely check of this right now, but definitely check out that YouTube video I linked. Now, out that YouTube video I linked. Now, out that YouTube video I linked. Now, what else is cool about this is this what else is cool about this is this what else is cool about this is this transcript Wiki actually lives within my transcript Wiki actually lives within my transcript Wiki actually lives within my main Herc 2 project. So, here's Herc 2.

main Herc 2 project. So, here's Herc 2. main Herc 2 project. So, here's Herc 2. If I go right here to Other Worlds, and If I go right here to Other Worlds, and If I go right here to Other Worlds, and then I go down to YouTube OS, and I then I go down to YouTube OS, and I then I go down to YouTube OS, and I click into the transcript Wiki right click into the transcript Wiki right click into the transcript Wiki right here, this is what we were just looking here, this is what we were just looking here, this is what we were just looking at in Obsidian. We could see the at in Obsidian. We could see the at in Obsidian. We could see the concepts, we could see the comparisons, concepts, we could see the comparisons, concepts, we could see the comparisons, we could see the sources, techniques. we could see the sources, techniques. we could see the sources, techniques. This is what we were looking at in This is what we were looking at in This is what we were looking at in Obsidian. So, all Obsidian is is it Obsidian. So, all Obsidian is is it Obsidian. So, all Obsidian is is it basically just visualizes your markdown basically just visualizes your markdown basically just visualizes your markdown files. You see here, wiki, concepts, files. You see here, wiki, concepts, files. You see here, wiki, concepts, comparisons, techniques. This is what we comparisons, techniques. This is what we comparisons, techniques. This is what we were just looking at. All we get now is were just looking at. All we get now is were just looking at. All we get now is we just get a visual view of all that. we just get a visual view of all that. we just get a visual view of all that. And so, the reason I wanted to bring And so, the reason I wanted to bring And so, the reason I wanted to bring that up as well is because I think a lot that up as well is because I think a lot that up as well is because I think a lot of people obviously get pretty of people obviously get pretty of people obviously get pretty infatuated by that visual view. And infatuated by that visual view. And infatuated by that visual view. And obviously, I started the video with that obviously, I started the video with that obviously, I started the video with that because I think that's what hooks a lot because I think that's what hooks a lot because I think that's what hooks a lot of people in. But, all that really of people in. But, all that really of people in. But, all that really matters is can your system grab that and matters is can your system grab that and matters is can your system grab that and give it to you? If you are a visual give it to you? If you are a visual give it to you? If you are a visual person and you really want that view, person and you really want that view, person and you really want that view, then by all means, install Obsidian and then by all means, install Obsidian and then by all means, install Obsidian and set it up. It's super easy. But, I'm set it up. It's super easy. But, I'm set it up. It's super easy. But, I'm saying that you don't always need that saying that you don't always need that saying that you don't always need that visual layer if it's not beneficial to visual layer if it's not beneficial to visual layer if it's not beneficial to you. I hardly ever open Obsidian, just you. I hardly ever open Obsidian, just you. I hardly ever open Obsidian, just to be honest, because I know that it all to be honest, because I know that it all to be honest, because I know that it all lives here and I know that my second lives here and I know that my second lives here and I know that my second brain and my OS can find all of that. brain and my OS can find all of that. brain and my OS can find all of that. So, anyways, in level two here, let's So, anyways, in level two here, let's So, anyways, in level two here, let's look at this. It's very similar in shape look at this. It's very similar in shape look at this. It's very similar in shape to level one. It's just building on top to level one. It's just building on top to level one. It's just building on top of it because now we have our claw.md, of it because now we have our claw.md, of it because now we have our claw.md, which starts to route to some other which starts to route to some other which starts to route to some other things because it routes to the wiki and things because it routes to the wiki and things because it routes to the wiki and it still routes to contexts, projects, it still routes to contexts, projects, it still routes to contexts, projects, decisions, but it's also routing to decisions, but it's also routing to decisions, but it's also routing to references and memory.md. So, we're just references and memory.md. So, we're just references and memory.md. So, we're just starting to add a bit more of these starting to add a bit more of these starting to add a bit more of these routing rules inside of the claw.md.

routing rules inside of the claw.md. routing rules inside of the claw.md. We can grow the context, we can grow the We can grow the context, we can grow the We can grow the context, we can grow the decisions, we can grow projects and decisions, we can grow projects and decisions, we can grow projects and references, and we can also start to get references, and we can also start to get references, and we can also start to get this idea of memory. And what's really this idea of memory. And what's really this idea of memory. And what's really cool about this is you can turn on auto cool about this is you can turn on auto cool about this is you can turn on auto memory in Claude Code. And the AI will memory in Claude Code. And the AI will memory in Claude Code. And the AI will basically start to write this file and basically start to write this file and basically start to write this file and update it on its own. So, you don't have update it on its own. So, you don't have update it on its own. So, you don't have to think about it. If you come in here to think about it. If you come in here to think about it. If you come in here and you do {slash} memory, it'll say and you do {slash} memory, it'll say and you do {slash} memory, it'll say auto memory on or off. And if it's off, auto memory on or off. And if it's off, auto memory on or off. And if it's off, if you want to turn that on, just turn if you want to turn that on, just turn if you want to turn that on, just turn it on. And now, one thing to think about it on. And now, one thing to think about it on. And now, one thing to think about is I mentioned earlier that we want to is I mentioned earlier that we want to is I mentioned earlier that we want to make our second brains tool agnostic. make our second brains tool agnostic. make our second brains tool agnostic. And this is one thing that's pretty And this is one thing that's pretty And this is one thing that's pretty specific about Claude Code is it uses specific about Claude Code is it uses specific about Claude Code is it uses claw.md and it uses this memory.md and claw.md and it uses this memory.md and claw.md and it uses this memory.md and it keeps that updated on its own. So, if it keeps that updated on its own. So, if it keeps that updated on its own. So, if you wanted to move this over to Codex, you wanted to move this over to Codex, you wanted to move this over to Codex, what you would do is you would first of what you would do is you would first of what you would do is you would first of all transition your claw.md. You'd make all transition your claw.md. You'd make all transition your claw.md. You'd make a copy of it called agents.md. As you a copy of it called agents.md. As you a copy of it called agents.md. As you can see here in my Herc 2, I've got my, can see here in my Herc 2, I've got my, can see here in my Herc 2, I've got my, if I scroll down, claw.md right here, if I scroll down, claw.md right here, if I scroll down, claw.md right here, and then I've got agents.md right here. and then I've got agents.md right here. and then I've got agents.md right here. And they're essentially the exact same And they're essentially the exact same And they're essentially the exact same file. Just so Codex can read this one file. Just so Codex can read this one file. Just so Codex can read this one and Claude code can read this one. But and Claude code can read this one. But and Claude code can read this one. But because Claude code keeps that auto because Claude code keeps that auto because Claude code keeps that auto memory, all you need to do is make sure memory, all you need to do is make sure memory, all you need to do is make sure you have that memory.md file and just you have that memory.md file and just you have that memory.md file and just tell Codex, "Hey, by the way, for tell Codex, "Hey, by the way, for tell Codex, "Hey, by the way, for memories, look in our memory.md file."

memories, look in our memory.md file." memories, look in our memory.md file." It's all about the routing there. It's all about the routing there. It's all about the routing there. Anyways, just felt like that was Anyways, just felt like that was Anyways, just felt like that was important to throw out. But at a certain important to throw out. But at a certain important to throw out. But at a certain point, when you have these, you know, point, when you have these, you know, point, when you have these, you know, wikis, they do start to degrade a little wikis, they do start to degrade a little wikis, they do start to degrade a little bit. Because what's what's great about bit. Because what's what's great about bit. Because what's what's great about them is that they have indexes, right? them is that they have indexes, right? them is that they have indexes, right? So, when your AI starts to look in the So, when your AI starts to look in the So, when your AI starts to look in the wiki, it knows, "Okay, if the user's wiki, it knows, "Okay, if the user's wiki, it knows, "Okay, if the user's asking about a genetic workflow, I'm asking about a genetic workflow, I'm asking about a genetic workflow, I'm probably going to start here. And then probably going to start here. And then probably going to start here. And then from here, I'm going to drill down and from here, I'm going to drill down and from here, I'm going to drill down and read this to see what else is important read this to see what else is important read this to see what else is important to them." Maybe they're asking about the to them." Maybe they're asking about the to them." Maybe they're asking about the WATC framework, and then I can drill WATC framework, and then I can drill WATC framework, and then I can drill into that. And maybe from there, I need into that. And maybe from there, I need into that. And maybe from there, I need to learn a little bit more about the to learn a little bit more about the to learn a little bit more about the Claude at MD system prompt, and then I Claude at MD system prompt, and then I Claude at MD system prompt, and then I will drill into that. So, there are will drill into that. So, there are will drill into that. So, there are relationships here a little bit, but relationships here a little bit, but relationships here a little bit, but this isn't the same as like semantic this isn't the same as like semantic this isn't the same as like semantic relationships or knowledge graph relationships or knowledge graph relationships or knowledge graph relationships that have more meaning. relationships that have more meaning. relationships that have more meaning. This is more about just actually This is more about just actually This is more about just actually following a trail and reading the page following a trail and reading the page following a trail and reading the page in its entirety. And I'll be fully in its entirety. And I'll be fully in its entirety. And I'll be fully honest with you guys, honest with you guys, honest with you guys, I pretty much sit my entire PERC 2 I pretty much sit my entire PERC 2 I pretty much sit my entire PERC 2 project in this level, in level two. project in this level, in level two. project in this level, in level two. Because this has been working really Because this has been working really Because this has been working really well for me. Like I mentioned earlier, I well for me. Like I mentioned earlier, I well for me. Like I mentioned earlier, I haven't felt a pain yet big enough to haven't felt a pain yet big enough to haven't felt a pain yet big enough to switch over to level two. And here's switch over to level two. And here's switch over to level two. And here's what I meant by that. My wiki has links, what I meant by that. My wiki has links, what I meant by that. My wiki has links, isn't that a knowledge graph? Not isn't that a knowledge graph? Not isn't that a knowledge graph? Not exactly. Because this doesn't have exactly. Because this doesn't have exactly. Because this doesn't have connections of how they are related, connections of how they are related, connections of how they are related, like this is endorsed by this or this like this is endorsed by this or this like this is endorsed by this or this has cron to here. These just have has cron to here. These just have has cron to here. These just have connections because it's like a a see connections because it's like a a see connections because it's like a a see also. It's like backlinks. So, they're also. It's like backlinks. So, they're also. It's like backlinks. So, they're very similar, and yes, they can achieve very similar, and yes, they can achieve very similar, and yes, they can achieve a similar effect, but it's still a a similar effect, but it's still a a similar effect, but it's still a little bit different. Anyways, let's little bit different. Anyways, let's little bit different. Anyways, let's take a look at level three, which is take a look at level three, which is take a look at level three, which is where you start to do things like where you start to do things like where you start to do things like semantic search. Whether you do that in semantic search. Whether you do that in semantic search. Whether you do that in Obsidian, whether you do that with Pine Obsidian, whether you do that with Pine Obsidian, whether you do that with Pine Cone or Supabase, however you start to Cone or Supabase, however you start to Cone or Supabase, however you start to grab the actual semantic search,

grab the actual semantic search, grab the actual semantic search, that is what level three is. And so, that is what level three is. And so, that is what level three is. And so, just as a quick visual for you guys, just as a quick visual for you guys, just as a quick visual for you guys, let's take a look at this quadrant let's take a look at this quadrant let's take a look at this quadrant cluster of images. So, every one of cluster of images. So, every one of cluster of images. So, every one of these vector points is an image. And these vector points is an image. And these vector points is an image. And what we see in here is the payload is what we see in here is the payload is what we see in here is the payload is stuff like the file name, the URL, the stuff like the file name, the URL, the stuff like the file name, the URL, the name of the author or the artist, and name of the author or the artist, and name of the author or the artist, and the URL. But, we don't actually see like the URL. But, we don't actually see like the URL. But, we don't actually see like what's in the image. We don't get a what's in the image. We don't get a what's in the image. We don't get a description. So, what we have to do is description. So, what we have to do is description. So, what we have to do is we have to organize these images by we have to organize these images by we have to organize these images by meaning or by similarity. So, when I meaning or by similarity. So, when I meaning or by similarity. So, when I open up this graph and we start to open up this graph and we start to open up this graph and we start to visualize the stuff here, what you see visualize the stuff here, what you see visualize the stuff here, what you see is that we have this main image, these is that we have this main image, these is that we have this main image, these owls, these kind of like I don't even owls, these kind of like I don't even owls, these kind of like I don't even know. Um it's a very trippy style, like know. Um it's a very trippy style, like know. Um it's a very trippy style, like hallucinogenic style. Anyways, then this hallucinogenic style. Anyways, then this hallucinogenic style. Anyways, then this one is kind of similar, right? It's got one is kind of similar, right? It's got one is kind of similar, right? It's got those colors, it's got the paints. This those colors, it's got the paints. This those colors, it's got the paints. This one is also similar, but they're not the one is also similar, but they're not the one is also similar, but they're not the same. They just share similarities. And same. They just share similarities. And same. They just share similarities. And as we start to expand these more and as we start to expand these more and as we start to expand these more and more, we can start to get into different more, we can start to get into different more, we can start to get into different styles. So, this one has like some styles. So, this one has like some styles. So, this one has like some creepy eyes and mushrooms or whatever. creepy eyes and mushrooms or whatever. creepy eyes and mushrooms or whatever. This one is kind of more down that This one is kind of more down that This one is kind of more down that fantasy lane. And as we start to build fantasy lane. And as we start to build fantasy lane. And as we start to build out more of these relationships and out more of these relationships and out more of these relationships and meanings, we can expand and grow away meanings, we can expand and grow away meanings, we can expand and grow away from them. And so, Quadrant really just from them. And so, Quadrant really just from them. And so, Quadrant really just gives you a visualization here. I mean, gives you a visualization here. I mean, gives you a visualization here. I mean, it's a it has clusters and vector store.

it's a it has clusters and vector store. it's a it has clusters and vector store. But, [snorts] the reason I pulled this But, [snorts] the reason I pulled this But, [snorts] the reason I pulled this up as a demo is just because we start to up as a demo is just because we start to up as a demo is just because we start to see the actual relationships form here see the actual relationships form here see the actual relationships form here based on meaning. And that's what's based on meaning. And that's what's based on meaning. And that's what's important about semantic search is that important about semantic search is that important about semantic search is that we're no longer doing keyword matching, we're no longer doing keyword matching, we're no longer doing keyword matching, we're searching based on meaning. So, we're searching based on meaning. So, we're searching based on meaning. So, here in my YouTube transcript second here in my YouTube transcript second here in my YouTube transcript second brain, if I go to the smart lookup over brain, if I go to the smart lookup over brain, if I go to the smart lookup over here, this is very different from just here, this is very different from just here, this is very different from just the regular search. So, for example, if the regular search. So, for example, if the regular search. So, for example, if I search here for um I search here for um I search here for um feedback, let's say. We're actually feedback, let's say. We're actually feedback, let's say. We're actually doing a match on the word feedback, and doing a match on the word feedback, and doing a match on the word feedback, and it's only showing me where that word it's only showing me where that word it's only showing me where that word actually appears inside of our second actually appears inside of our second actually appears inside of our second brain. But, if I come over here in the brain. But, if I come over here in the brain. But, if I come over here in the smart lookup and I search for feedback, smart lookup and I search for feedback, smart lookup and I search for feedback, we are getting matches that have things we are getting matches that have things we are getting matches that have things in here that mean feedback. So, live in here that mean feedback. So, live in here that mean feedback. So, live test results, cloud code skills, which test results, cloud code skills, which test results, cloud code skills, which was uh talking about evaluations and was uh talking about evaluations and was uh talking about evaluations and stuff. So, there's a big difference stuff. So, there's a big difference stuff. So, there's a big difference between keyword matching and semantic between keyword matching and semantic between keyword matching and semantic search, you know, similarity matching. search, you know, similarity matching. search, you know, similarity matching. This one over here is saying X equals X, This one over here is saying X equals X, This one over here is saying X equals X, and this one is saying X is similar to and this one is saying X is similar to and this one is saying X is similar to X, Y, and Z. And so, this all just goes X, Y, and Z. And so, this all just goes X, Y, and Z. And so, this all just goes back to vector databases. I've talked back to vector databases. I've talked back to vector databases. I've talked so, so much about vector databases, so so, so much about vector databases, so so, so much about vector databases, so I'm not going to dive super deep in.

I'm not going to dive super deep in. I'm not going to dive super deep in. I've got so many resources on my I've got so many resources on my I've got so many resources on my channel. But basically, what it is is we channel. But basically, what it is is we channel. But basically, what it is is we take a document, so let's just say take a document, so let's just say take a document, so let's just say YouTube transcript, we chunk it up, and YouTube transcript, we chunk it up, and YouTube transcript, we chunk it up, and then each chunk is ran through an then each chunk is ran through an then each chunk is ran through an embeddings model. And the embeddings embeddings model. And the embeddings embeddings model. And the embeddings model puts that chunk of text onto like model puts that chunk of text onto like model puts that chunk of text onto like a three-dimensional space where space is a three-dimensional space where space is a three-dimensional space where space is related to meaning. And so it decides, related to meaning. And so it decides, related to meaning. And so it decides, okay, this chunk is about a company, so okay, this chunk is about a company, so okay, this chunk is about a company, so we're going to put it up here. This we're going to put it up here. This we're going to put it up here. This chunk is about finances, so it's going chunk is about finances, so it's going chunk is about finances, so it's going to go here. And we start to see these to go here. And we start to see these to go here. And we start to see these vectors form near other similar vectors. vectors form near other similar vectors. vectors form near other similar vectors. Now, do you guys remember how I said Now, do you guys remember how I said Now, do you guys remember how I said earlier, like you want to think about earlier, like you want to think about earlier, like you want to think about how is the data going to be used? What how is the data going to be used? What how is the data going to be used? What type of questions are you going to ask? type of questions are you going to ask? type of questions are you going to ask? This is a reason why that's so This is a reason why that's so This is a reason why that's so important. So think about this. Let's important. So think about this. Let's important. So think about this. Let's say I put my meeting transcript of March say I put my meeting transcript of March say I put my meeting transcript of March 5th meeting into my second brain. And I 5th meeting into my second brain. And I 5th meeting into my second brain. And I put those in as, you know, vectorized put those in as, you know, vectorized put those in as, you know, vectorized chunks. So let's say when I vectorize chunks. So let's say when I vectorize chunks. So let's say when I vectorize that meeting, we actually get, you know, that meeting, we actually get, you know, that meeting, we actually get, you know, like like like 20 chunks. It actually creates 20 20 chunks. It actually creates 20 20 chunks. It actually creates 20 chunks, or however many that is. And chunks, or however many that is. And chunks, or however many that is. And then when I say, "Hey, Mr. AI agent, can then when I say, "Hey, Mr. AI agent, can then when I say, "Hey, Mr. AI agent, can you summarize the meeting on March 5th?" you summarize the meeting on March 5th?" you summarize the meeting on March 5th?" It will basically search for March 5th It will basically search for March 5th It will basically search for March 5th meeting summary, and it will pull chunks meeting summary, and it will pull chunks meeting summary, and it will pull chunks that are similar to March 5th meeting that are similar to March 5th meeting that are similar to March 5th meeting summary. And then even if it gets the summary. And then even if it gets the summary. And then even if it gets the right chunks, it's going to only right chunks, it's going to only right chunks, it's going to only summarize those five chunks. It's not summarize those five chunks. It's not summarize those five chunks. It's not able to look at the entire meeting able to look at the entire meeting able to look at the entire meeting summary, or sorry, like meeting summary, or sorry, like meeting summary, or sorry, like meeting transcript in entirety. So it doesn't transcript in entirety. So it doesn't transcript in entirety. So it doesn't really know a summary. It might be really know a summary. It might be really know a summary. It might be missing a lot of key information. Now missing a lot of key information. Now missing a lot of key information. Now yes, there are things you can start to yes, there are things you can start to yes, there are things you can start to play with there like metadata and other play with there like metadata and other play with there like metadata and other things like that to make these results things like that to make these results things like that to make these results better, but at the end of the day, better, but at the end of the day, better, but at the end of the day, people kind of assumed that a vector people kind of assumed that a vector people kind of assumed that a vector database was some magic solution where database was some magic solution where database was some magic solution where it could always pull back what you need, it could always pull back what you need, it could always pull back what you need, but that is very false. And I mean,

but that is very false. And I mean, but that is very false. And I mean, think about it like this. Let's say we think about it like this. Let's say we think about it like this. Let's say we have a table, and we say, "Hey, which have a table, and we say, "Hey, which have a table, and we say, "Hey, which week did we have the highest sales?" week did we have the highest sales?" week did we have the highest sales?" Okay, the agent looks for highest sales, Okay, the agent looks for highest sales, Okay, the agent looks for highest sales, it maybe grabs this chunk outlined in it maybe grabs this chunk outlined in it maybe grabs this chunk outlined in gray of data, and then it looks at, gray of data, and then it looks at, gray of data, and then it looks at, "Okay, week six here was the highest "Okay, week six here was the highest "Okay, week six here was the highest sales, so that must be the answer." But sales, so that must be the answer." But sales, so that must be the answer." But in reality, you can see week 14 was in reality, you can see week 14 was in reality, you can see week 14 was higher, week 19 was higher. So when you higher, week 19 was higher. So when you higher, week 19 was higher. So when you need something that has actual full need something that has actual full need something that has actual full context, context, context, then you can't do the vector database then you can't do the vector database then you can't do the vector database chunking. That's where you'd rather just chunking. That's where you'd rather just chunking. That's where you'd rather just have a markdown file of March 5th, and have a markdown file of March 5th, and have a markdown file of March 5th, and then all this agent would have to do is then all this agent would have to do is then all this agent would have to do is read that entire markdown file and then read that entire markdown file and then read that entire markdown file and then give you a summary. And that's just give you a summary. And that's just give you a summary. And that's just going to be more accurate. So, in this going to be more accurate. So, in this going to be more accurate. So, in this project, if we open up level three, you project, if we open up level three, you project, if we open up level three, you can see it's very similar because you can see it's very similar because you can see it's very similar because you can still have context files, decision can still have context files, decision can still have context files, decision files, you can still have all that, and files, you can still have all that, and files, you can still have all that, and then you might identify, "Okay, then you might identify, "Okay, then you might identify, "Okay, actually, this one specific unit of my actually, this one specific unit of my actually, this one specific unit of my business, maybe my YouTube transcripts, business, maybe my YouTube transcripts, business, maybe my YouTube transcripts, maybe I want just that to be a vector maybe I want just that to be a vector maybe I want just that to be a vector database, but I still want my context database, but I still want my context database, but I still want my context and my projects and my decisions to be and my projects and my decisions to be and my projects and my decisions to be markdown files." markdown files." markdown files." So, another point I'm trying to make So, another point I'm trying to make So, another point I'm trying to make here is here is here is just because you have a second brain, just because you have a second brain, just because you have a second brain, and just because you have a massive, you and just because you have a massive, you and just because you have a massive, you know, folder here with a bunch of know, folder here with a bunch of know, folder here with a bunch of folders and files, doesn't mean that the folders and files, doesn't mean that the folders and files, doesn't mean that the whole folder needs to be one style. It whole folder needs to be one style. It whole folder needs to be one style. It doesn't mean that everything needs graph doesn't mean that everything needs graph doesn't mean that everything needs graph rack. It doesn't mean that everything is rack. It doesn't mean that everything is rack. It doesn't mean that everything is just LLM Wiki. It means that you're able just LLM Wiki. It means that you're able just LLM Wiki. It means that you're able to decide, based on the type of data and to decide, based on the type of data and to decide, based on the type of data and the way you use it, how can you the way you use it, how can you the way you use it, how can you structure this specific folder in the structure this specific folder in the structure this specific folder in the way you want it. So, here we have a way you want it. So, here we have a way you want it. So, here we have a vector index folder, and we click on the vector index folder, and we click on the vector index folder, and we click on the house search works. It works by house search works. It works by house search works. It works by chunking, embedding, search, hybrid, chunking, embedding, search, hybrid, chunking, embedding, search, hybrid, re-ranking. There's some things you can re-ranking. There's some things you can re-ranking. There's some things you can get really, really nitty-gritty on when get really, really nitty-gritty on when get really, really nitty-gritty on when it comes to semantic search. But what

it comes to semantic search. But what it comes to semantic search. But what vector retrieval is really, really good vector retrieval is really, really good vector retrieval is really, really good at is looking at tons and tons of data, at is looking at tons and tons of data, at is looking at tons and tons of data, typically just like a lot of text, and typically just like a lot of text, and typically just like a lot of text, and when you need a very specific answer, when you need a very specific answer, when you need a very specific answer, something that's very similar. So, if something that's very similar. So, if something that's very similar. So, if you had a thousand rules that you needed you had a thousand rules that you needed you had a thousand rules that you needed to store, and you basically said, "Hey, to store, and you basically said, "Hey, to store, and you basically said, "Hey, um can you remind me what rule 17 was?" um can you remind me what rule 17 was?" um can you remind me what rule 17 was?" That might be a really good use case for That might be a really good use case for That might be a really good use case for vector search because it's able to vector search because it's able to vector search because it's able to search for rule 17, pull in those search for rule 17, pull in those search for rule 17, pull in those chunks, and just give you a little chunks, and just give you a little chunks, and just give you a little snippet because it would be a waste of snippet because it would be a waste of snippet because it would be a waste of time and tokens for your agent to read time and tokens for your agent to read time and tokens for your agent to read the entire markdown file of all 1,000 the entire markdown file of all 1,000 the entire markdown file of all 1,000 rules if you just needed rule 17. So, rules if you just needed rule 17. So, rules if you just needed rule 17. So, that's kind of the difference there. that's kind of the difference there. that's kind of the difference there. Like I said, I've got so many videos on Like I said, I've got so many videos on Like I said, I've got so many videos on vector stuff on my channel, but really vector stuff on my channel, but really vector stuff on my channel, but really you could say, "Hey, you could say, "Hey, you could say, "Hey, to your cloud code agent, I have this to your cloud code agent, I have this to your cloud code agent, I have this data. Here's how I want to use it. Do data. Here's how I want to use it. Do data. Here's how I want to use it. Do you think this would be better for now you think this would be better for now you think this would be better for now as markdown files, or should I do as markdown files, or should I do as markdown files, or should I do semantic search? Like what would semantic search? Like what would semantic search? Like what would actually make more sense here?" And it actually make more sense here?" And it actually make more sense here?" And it will help walk you through the way that will help walk you through the way that will help walk you through the way that you should actually set that up. So, now you should actually set that up. So, now you should actually set that up. So, now I hope you guys are starting to I hope you guys are starting to I hope you guys are starting to understand why I said, you know, moving understand why I said, you know, moving understand why I said, you know, moving up on or I'm sorry, like moving up on up on or I'm sorry, like moving up on up on or I'm sorry, like moving up on levels, moving down doesn't necessarily levels, moving down doesn't necessarily levels, moving down doesn't necessarily mean better. It's all about figuring out mean better. It's all about figuring out mean better. It's all about figuring out what is the pain point with what you're what is the pain point with what you're what is the pain point with what you're currently doing and where would a currently doing and where would a currently doing and where would a different level help you out and fix different level help you out and fix different level help you out and fix that pain point. Okay, so now let's take that pain point. Okay, so now let's take that pain point. Okay, so now let's take a look at level four. This is where we a look at level four. This is where we a look at level four. This is where we start to get into like knowledge graphs start to get into like knowledge graphs start to get into like knowledge graphs and relationship graphs, which typically and relationship graphs, which typically and relationship graphs, which typically are going to be the most complex and are going to be the most complex and are going to be the most complex and sometimes the most expensive as well. If sometimes the most expensive as well. If sometimes the most expensive as well. If you're doing it on a certain platform, you're doing it on a certain platform, you're doing it on a certain platform, you could always use open source you could always use open source you could always use open source software, but anyways, knowledge graphs.

software, but anyways, knowledge graphs. software, but anyways, knowledge graphs. And I also want to be up front. I've And I also want to be up front. I've And I also want to be up front. I've played with these a lot, but I do not played with these a lot, but I do not played with these a lot, but I do not actually use these on the day-to-day actually use these on the day-to-day actually use these on the day-to-day because I found out just other ways to because I found out just other ways to because I found out just other ways to use routing files and wikis that fit my use routing files and wikis that fit my use routing files and wikis that fit my needs. Now, my work is very different needs. Now, my work is very different needs. Now, my work is very different than what a lot of you guys' work may than what a lot of you guys' work may than what a lot of you guys' work may be. Mine is very project-based and it is be. Mine is very project-based and it is be. Mine is very project-based and it is very, you know, content-heavy. I don't very, you know, content-heavy. I don't very, you know, content-heavy. I don't have a massive CRM to manage with a have a massive CRM to manage with a have a massive CRM to manage with a bunch of different businesses and bunch of different businesses and bunch of different businesses and clients, you know? And if I did, maybe a clients, you know? And if I did, maybe a clients, you know? And if I did, maybe a knowledge graph would make a lot more knowledge graph would make a lot more knowledge graph would make a lot more sense and it probably would. But sense and it probably would. But sense and it probably would. But typically, the cool part about that is typically, the cool part about that is typically, the cool part about that is if you identify that you needed a if you identify that you needed a if you identify that you needed a knowledge graph, let's say for all your knowledge graph, let's say for all your knowledge graph, let's say for all your projects, you needed you wanted to put projects, you needed you wanted to put projects, you needed you wanted to put all of this in a knowledge graph, all of this in a knowledge graph, all of this in a knowledge graph, the data probably already exists here. the data probably already exists here. the data probably already exists here. And that's the thing about building out And that's the thing about building out And that's the thing about building out these relationships in your knowledge these relationships in your knowledge these relationships in your knowledge graph is that the system, whatever graph is that the system, whatever graph is that the system, whatever software you use, is typically going to software you use, is typically going to software you use, is typically going to be pretty good at embedding that and be pretty good at embedding that and be pretty good at embedding that and creating that. But the problem that you creating that. But the problem that you creating that. But the problem that you have to solve is you have to give it have to solve is you have to give it have to solve is you have to give it enough data. And so, one thing that I enough data. And so, one thing that I enough data. And so, one thing that I really like to do is I like to have really like to do is I like to have really like to do is I like to have these brainstorm sessions, as you can these brainstorm sessions, as you can these brainstorm sessions, as you can see. And what I do with these brainstorm see. And what I do with these brainstorm see. And what I do with these brainstorm sessions is I use a skill called Grill sessions is I use a skill called Grill sessions is I use a skill called Grill Me. So, if you see here, I have a skill Me. So, if you see here, I have a skill Me. So, if you see here, I have a skill called Grill Me, which I originally got called Grill Me, which I originally got called Grill Me, which I originally got from Matt Pocock. I customize it a from Matt Pocock. I customize it a from Matt Pocock. I customize it a little bit. I'll leave the skill for little bit. I'll leave the skill for little bit. I'll leave the skill for Grill Me in my free school community.

Grill Me in my free school community. Grill Me in my 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. All you have to do is hop description. All you have to do is hop description. All you have to do is hop in here, go to classroom, click on all in here, go to classroom, click on all in here, go to classroom, click on all YouTube resources, and you can find all YouTube resources, and you can find all YouTube resources, and you can find all the skills and everything like that. But the skills and everything like that. But the skills and everything like that. But the skill, what that does, is it the skill, what that does, is it the skill, what that does, is it basically just grills me. It interviews basically just grills me. It interviews basically just grills me. It interviews me relentlessly about a certain topic me relentlessly about a certain topic me relentlessly about a certain topic and it creates a brainstorm file here. and it creates a brainstorm file here. and it creates a brainstorm file here. It only stops when it knows everything It only stops when it knows everything It only stops when it knows everything about it. So, if you wanted to start about it. So, if you wanted to start about it. So, if you wanted to start building up a knowledge graph for all building up a knowledge graph for all building up a knowledge graph for all your clients and businesses, just say your clients and businesses, just say your clients and businesses, just say "Grill me about client A. Grill me about "Grill me about client A. Grill me about "Grill me about client A. Grill me about client B. Grill me about business A." client B. Grill me about business A." client B. Grill me about business A." And it would just ask you questions and And it would just ask you questions and And it would just ask you questions and you can feed it files. You can give it you can feed it files. You can give it you can feed it files. You can give it stuff. You can feed it in transcripts. stuff. You can feed it in transcripts. stuff. You can feed it in transcripts. You can feed it in, you know, contracts, You can feed it in, you know, contracts, You can feed it in, you know, contracts, whatever it is. And that's how you can whatever it is. And that's how you can whatever it is. And that's how you can start to form a lot of data. start to form a lot of data. start to form a lot of data. Hey guys, me again. Real quick, I'm Hey guys, me again. Real quick, I'm Hey guys, me again. Real quick, I'm editing this video and I realized that I editing this video and I realized that I editing this video and I realized that I needed to throw out one thing here, needed to throw out one thing here, needed to throw out one thing here, which is that obviously, if you're which is that obviously, if you're which is that obviously, if you're putting all of this data and you're putting all of this data and you're putting all of this data and you're sending it all to Anthropic, to Claude sending it all to Anthropic, to Claude sending it all to Anthropic, to Claude models, then models, then models, then that's not private. So, if you feel that's not private. So, if you feel that's not private. So, if you feel comfortable with that, that's fine. I am comfortable with that, that's fine. I am comfortable with that, that's fine. I am putting a lot of my data in there and it putting a lot of my data in there and it putting a lot of my data in there and it is my business stuff and is my business stuff and is my business stuff and that's what I'm doing. But, if you don't that's what I'm doing. But, if you don't that's what I'm doing. But, if you don't feel comfortable with that or you, you feel comfortable with that or you, you feel comfortable with that or you, you know, don't want to send client data, of know, don't want to send client data, of know, don't want to send client data, of course you don't, then maybe you want to course you don't, then maybe you want to course you don't, then maybe you want to do that through open-source models and do that through open-source models and do that through open-source models and maybe Claude code isn't where you have maybe Claude code isn't where you have maybe Claude code isn't where you have the second brain that has every single the second brain that has every single the second brain that has every single piece of information about you and your piece of information about you and your piece of information about you and your business and your client's business. So, business and your client's business. So, business and your client's business. So, the point I'm trying to make here is the point I'm trying to make here is the point I'm trying to make here is just this is what I'm doing. I'm just this is what I'm doing. I'm just this is what I'm doing. I'm obviously aware of the fact that my data obviously aware of the fact that my data obviously aware of the fact that my data goes to Anthropic when I process it goes to Anthropic when I process it goes to Anthropic when I process it through Claude. And if you guys are through Claude. And if you guys are through Claude. And if you guys are doing that, then you should also be doing that, then you should also be doing that, then you should also be aware of that. But, there are other aware of that. But, there are other aware of that. But, there are other options if you can't do that. So, I options if you can't do that. So, I options if you can't do that. So, I wanted to throw that out there. I am wanted to throw that out there. I am wanted to throw that out there. I am planning to make a ton of videos here planning to make a ton of videos here planning to make a ton of videos here soon about local AI and open-source soon about local AI and open-source soon about local AI and open-source models and all this stuff cuz it's a models and all this stuff cuz it's a models and all this stuff cuz it's a really, really exciting space that I really, really exciting space that I really, really exciting space that I think is going to start becoming bigger

think is going to start becoming bigger think is going to start becoming bigger and bigger. So, yeah, keep that in mind. and bigger. So, yeah, keep that in mind. and bigger. So, yeah, keep that in mind. Back to the video. I think sometimes Back to the video. I think sometimes Back to the video. I think sometimes that's a misconception about how I got that's a misconception about how I got that's a misconception about how I got here and how people build their own AI here and how people build their own AI here and how people build their own AI OS or second brain is that OS or second brain is that OS or second brain is that they think the problem is the system not they think the problem is the system not they think the problem is the system not retrieving it great, which sometimes it retrieving it great, which sometimes it retrieving it great, which sometimes it is, but sometimes it seems like the is, but sometimes it seems like the is, but sometimes it seems like the bigger problem is getting everything out bigger problem is getting everything out bigger problem is getting everything out of your brain into the system. So, of your brain into the system. So, of your brain into the system. So, before you blame AI, take a look at your before you blame AI, take a look at your before you blame AI, take a look at your folders and files and say, "Is this folders and files and say, "Is this folders and files and say, "Is this actually holistic? Is this Does this actually holistic? Is this Does this actually holistic? Is this Does this have all the nuance that I have in my have all the nuance that I have in my have all the nuance that I have in my brain?" Anyways, from there, when you brain?" Anyways, from there, when you brain?" Anyways, from there, when you open up level four, you can see that open up level four, you can see that open up level four, you can see that it's it's, you know, very similar still. it's it's, you know, very similar still. it's it's, you know, very similar still. We're just adding on a few things. You We're just adding on a few things. You We're just adding on a few things. You can see here we've added an agents.md, can see here we've added an agents.md, can see here we've added an agents.md, which is the exact same as the which is the exact same as the which is the exact same as the claude.md. And what else is cool is you claude.md. And what else is cool is you claude.md. And what else is cool is you can literally just reference inside of can literally just reference inside of can literally just reference inside of your claude.md at agents.md and then you your claude.md at agents.md and then you your claude.md at agents.md and then you can delete all this because this can delete all this because this can delete all this because this basically just like injects that file basically just like injects that file basically just like injects that file into here. But I just wanted to show into here. But I just wanted to show into here. But I just wanted to show that. But anyways, you can see we're that. But anyways, you can see we're that. But anyways, you can see we're still following the same principles. We still following the same principles. We still following the same principles. We have a wiki. We've also added a have a wiki. We've also added a have a wiki. We've also added a knowledge graph layer. We've still got knowledge graph layer. We've still got knowledge graph layer. We've still got the same where things live with the the same where things live with the the same where things live with the routing with all these just regular routing with all these just regular routing with all these just regular folders and boring markdown, but boring folders and boring markdown, but boring folders and boring markdown, but boring is beautiful. You can see that our is beautiful. You can see that our is beautiful. You can see that our memory is still here. It's starting to memory is still here. It's starting to memory is still here. It's starting to grow, and we just keep building on top grow, and we just keep building on top grow, and we just keep building on top of this. So what one thing we added here of this. So what one thing we added here of this. So what one thing we added here as you can see was our knowledge graph as you can see was our knowledge graph as you can see was our knowledge graph folder. And so what happens here is we folder. And so what happens here is we folder. And so what happens here is we get different entities, right? So like get different entities, right? So like get different entities, right? So like we can see okay Jordan is a person. Acme we can see okay Jordan is a person. Acme we can see okay Jordan is a person. Acme is a company. And then we can start to is a company. And then we can start to is a company. And then we can start to form relationships between all these form relationships between all these form relationships between all these things. So Jordan works at Acme. Acme is things. So Jordan works at Acme. Acme is things. So Jordan works at Acme. Acme is endorsed by Postpilot. Postpilot is a endorsed by Postpilot. Postpilot is a endorsed by Postpilot. Postpilot is a competitor of Cadently. And it starts to competitor of Cadently. And it starts to competitor of Cadently. And it starts to build out not only these entities, but build out not only these entities, but build out not only these entities, but it shows you how they're all related.

it shows you how they're all related. it shows you how they're all related. And so that's why when I said that I And so that's why when I said that I And so that's why when I said that I really like using, you know, this um really like using, you know, this um really like using, you know, this um what's it called? LLM Wiki is because I what's it called? LLM Wiki is because I what's it called? LLM Wiki is because I have enough of that feel of all these have enough of that feel of all these have enough of that feel of all these relationships because I've put so much relationships because I've put so much relationships because I've put so much time and effort into ingesting these in time and effort into ingesting these in time and effort into ingesting these in the right way and giving it context. The the right way and giving it context. The the right way and giving it context. The thing about this one is that it has to thing about this one is that it has to thing about this one is that it has to read every single file it wants. Maybe read every single file it wants. Maybe read every single file it wants. Maybe it was looking at AI video production it was looking at AI video production it was looking at AI video production and all it needed to know was and all it needed to know was and all it needed to know was ElevenLabs, it still would have read ElevenLabs, it still would have read ElevenLabs, it still would have read this entire file first. And so that's this entire file first. And so that's this entire file first. And so that's where sometimes the knowledge graph is where sometimes the knowledge graph is where sometimes the knowledge graph is actually more lightweight in that sense. actually more lightweight in that sense. actually more lightweight in that sense. And this is the example I showed at the And this is the example I showed at the And this is the example I showed at the beginning of the video where we have beginning of the video where we have beginning of the video where we have Lightrag. And forgive me, I'm going to Lightrag. And forgive me, I'm going to Lightrag. And forgive me, I'm going to have to blur some of this stuff out have to blur some of this stuff out have to blur some of this stuff out because this is like legitimately my because this is like legitimately my because this is like legitimately my entire second brain in our business. But entire second brain in our business. But entire second brain in our business. But as I really zoom in here and this kind as I really zoom in here and this kind as I really zoom in here and this kind of slows down my computer because of slows down my computer because of slows down my computer because there's so much. But what you'll notice there's so much. But what you'll notice there's so much. But what you'll notice is that we actually start to get is that we actually start to get is that we actually start to get relationships. I probably shouldn't have relationships. I probably shouldn't have relationships. I probably shouldn't have done this with so much data, but you can done this with so much data, but you can done this with so much data, but you can see like we have this collaborates with see like we have this collaborates with see like we have this collaborates with that. We have this builds that. And so that. We have this builds that. And so that. We have this builds that. And so if I really started to open up all of if I really started to open up all of if I really started to open up all of these little these little these little you know, circles, we could see what was you know, circles, we could see what was you know, circles, we could see what was going on and how they're all related. We going on and how they're all related. We going on and how they're all related. We could see that our 7-day AI challenge it could see that our 7-day AI challenge it could see that our 7-day AI challenge it was provided from YouTube. It connects was provided from YouTube. It connects was provided from YouTube. It connects to the onboarding process of AIS Plus.

to the onboarding process of AIS Plus. to the onboarding process of AIS Plus. It was developed by Aiden. And so we can It was developed by Aiden. And so we can It was developed by Aiden. And so we can basically follow around these basically follow around these basically follow around these relationships, as you see. And even relationships, as you see. And even relationships, as you see. And even though it's pretty much the same data though it's pretty much the same data though it's pretty much the same data that you see here in Obsidian, we're not that you see here in Obsidian, we're not that you see here in Obsidian, we're not getting that same level of relationships getting that same level of relationships getting that same level of relationships between these different entities. So, between these different entities. So, between these different entities. So, anyways, if you guys want to see, you anyways, if you guys want to see, you anyways, if you guys want to see, you know, a full breakdown video on know, a full breakdown video on know, a full breakdown video on something like Logseq or um Graphir or something like Logseq or um Graphir or something like Logseq or um Graphir or all the other solutions that there are all the other solutions that there are all the other solutions that there are out there for more of a knowledge graph out there for more of a knowledge graph out there for more of a knowledge graph relationship graph, then let me know. relationship graph, then let me know. relationship graph, then let me know. But, that is kind of the difference But, that is kind of the difference But, that is kind of the difference there. So, if you don't need those sort there. So, if you don't need those sort there. So, if you don't need those sort of relationship chains, and you're not of relationship chains, and you're not of relationship chains, and you're not worried about that semantic type of worried about that semantic type of worried about that semantic type of relationships, then you probably don't relationships, then you probably don't relationships, then you probably don't need to use something like a knowledge need to use something like a knowledge need to use something like a knowledge graph. And then, level five, we have graph. And then, level five, we have graph. And then, level five, we have more of the always-on Brain OS, and more of the always-on Brain OS, and more of the always-on Brain OS, and something like Gbrain. Garry Tan, CEO of something like Gbrain. Garry Tan, CEO of something like Gbrain. Garry Tan, CEO of Y Combinator, he created this thing Y Combinator, he created this thing Y Combinator, he created this thing called Gbrain, which pairs really well called Gbrain, which pairs really well called Gbrain, which pairs really well with G stack. But, Gbrain is kind of the with G stack. But, Gbrain is kind of the with G stack. But, Gbrain is kind of the idea of everything we've talked about idea of everything we've talked about idea of everything we've talked about here. Wikis, routing, relationships, here. Wikis, routing, relationships, here. Wikis, routing, relationships, tools. But, Gbrain has kind of that tools. But, Gbrain has kind of that tools. But, Gbrain has kind of that always-on element, because it is like always-on element, because it is like always-on element, because it is like constantly syncing and refreshing constantly syncing and refreshing constantly syncing and refreshing memories and adding more stuff. So, memories and adding more stuff. So, memories and adding more stuff. So, adding in Gbrain to something like a adding in Gbrain to something like a adding in Gbrain to something like a Hermes agent would be really, really Hermes agent would be really, really Hermes agent would be really, really good. You could still do it in cloud good. You could still do it in cloud good. You could still do it in cloud code, but you'd have to handle those code, but you'd have to handle those code, but you'd have to handle those crons and get all that stuff set up, crons and get all that stuff set up, crons and get all that stuff set up, which is why I don't currently run which is why I don't currently run which is why I don't currently run Gbrain at the moment, but I have been Gbrain at the moment, but I have been Gbrain at the moment, but I have been playing around with it with my Hermes playing around with it with my Hermes playing around with it with my Hermes agent. So, anyways, the point here is agent. So, anyways, the point here is agent. So, anyways, the point here is that it's very similar to everything that it's very similar to everything that it's very similar to everything else we've just talked about. It's just else we've just talked about. It's just else we've just talked about. It's just having that auto-updating feel, more of having that auto-updating feel, more of having that auto-updating feel, more of the autonomous, always-on feel.

the autonomous, always-on feel. the autonomous, always-on feel. But, I will say, another thing that I But, I will say, another thing that I But, I will say, another thing that I kind of that kind of scares me about kind of that kind of scares me about kind of that kind of scares me about that is you have this whole dilemma of, that is you have this whole dilemma of, that is you have this whole dilemma of, you know, you know, you know, when do you have too much context? And when do you have too much context? And when do you have too much context? And when does it get to the point where it's when does it get to the point where it's when does it get to the point where it's actually doing more damage than it's actually doing more damage than it's actually doing more damage than it's doing good? And the reason I bring that doing good? And the reason I bring that doing good? And the reason I bring that up is because I am in complete control up is because I am in complete control up is because I am in complete control of what my second brain ingests. I will of what my second brain ingests. I will of what my second brain ingests. I will run a skill to go grab all of my meeting run a skill to go grab all of my meeting run a skill to go grab all of my meeting transcripts from the week. I will say, transcripts from the week. I will say, transcripts from the week. I will say, "Hey, here's something. Help me figure "Hey, here's something. Help me figure "Hey, here's something. Help me figure out like how many brains are about this, out like how many brains are about this, out like how many brains are about this, and then let's ingest it together." And and then let's ingest it together." And and then let's ingest it together." And for me, I really like being in that for me, I really like being in that for me, I really like being in that control, because in my mind, there's a control, because in my mind, there's a control, because in my mind, there's a big difference between a few types of big difference between a few types of big difference between a few types of data. If you guys remember in my like AI data. If you guys remember in my like AI data. If you guys remember in my like AI OS videos, I've talked about the four OS videos, I've talked about the four OS videos, I've talked about the four C's. So, context, connections, C's. So, context, connections, C's. So, context, connections, capabilities, and cadence. And for the capabilities, and cadence. And for the capabilities, and cadence. And for the second brain, I mainly think about it as second brain, I mainly think about it as second brain, I mainly think about it as just these first two. So, context and just these first two. So, context and just these first two. So, context and connections. And so, when I think of connections. And so, when I think of connections. And so, when I think of context, that's stuff like, you know, context, that's stuff like, you know, context, that's stuff like, you know, what my business has done. So, if I come what my business has done. So, if I come what my business has done. So, if I come into here, into my my second brain, and into here, into my my second brain, and into here, into my my second brain, and you can see here if I go to you can see here if I go to you can see here if I go to um up at OTAs. So, OTAs are basically um up at OTAs. So, OTAs are basically um up at OTAs. So, OTAs are basically just our projects for the quarter. And just our projects for the quarter. And just our projects for the quarter. And so, here I can see all the Q1 ones, so, here I can see all the Q1 ones, so, here I can see all the Q1 ones, right? I can look at all those and I can right? I can look at all those and I can right? I can look at all those and I can click at them and see decisions that click at them and see decisions that click at them and see decisions that we've made in the statuses. And I can we've made in the statuses. And I can we've made in the statuses. And I can also see Q2 OTAs. So, I can see what's also see Q2 OTAs. So, I can see what's also see Q2 OTAs. So, I can see what's going on here. And my second brain's going on here. And my second brain's going on here. And my second brain's able to see that because that has been able to see that because that has been able to see that because that has been basically those are locked in decisions.

basically those are locked in decisions. basically those are locked in decisions. This is what we're doing this quarter, This is what we're doing this quarter, This is what we're doing this quarter, and then I'm updating the statuses of and then I'm updating the statuses of and then I'm updating the statuses of that stuff. So, that's like context. that stuff. So, that's like context. that stuff. So, that's like context. That's what's going on in the business. That's what's going on in the business. That's what's going on in the business. But when it comes to connections, if I But when it comes to connections, if I But when it comes to connections, if I go back to this, this is more of like go back to this, this is more of like go back to this, this is more of like the real data that isn't as evergreen. the real data that isn't as evergreen. the real data that isn't as evergreen. This is stuff that changes. This is like This is stuff that changes. This is like This is stuff that changes. This is like Slack threads. This is emails. This is a Slack threads. This is emails. This is a Slack threads. This is emails. This is a customer data. And that type of data you customer data. And that type of data you customer data. And that type of data you don't want to ingest into a second brain don't want to ingest into a second brain don't want to ingest into a second brain because that's just noise then. Then you because that's just noise then. Then you because that's just noise then. Then you have to go back every month and like have to go back every month and like have to go back every month and like delete old stuff. So, the way that I delete old stuff. So, the way that I delete old stuff. So, the way that I like to think about my actual second like to think about my actual second like to think about my actual second brain is stuff that I'm not going to brain is stuff that I'm not going to brain is stuff that I'm not going to delete. This is stuff that is like, delete. This is stuff that is like, delete. This is stuff that is like, okay, in a year, will it be good for me okay, in a year, will it be good for me okay, in a year, will it be good for me to have this memory in here? Yes. to have this memory in here? Yes. to have this memory in here? Yes. Otherwise, it's just adding noise. So, Otherwise, it's just adding noise. So, Otherwise, it's just adding noise. So, when you're adding data into your when you're adding data into your when you're adding data into your project, think about it like the context project, think about it like the context project, think about it like the context and connections. Think about if this is and connections. Think about if this is and connections. Think about if this is kind of like more evergreen, holistic kind of like more evergreen, holistic kind of like more evergreen, holistic data, or if this is more things that are data, or if this is more things that are data, or if this is more things that are going to change next week. So, you going to change next week. So, you going to change next week. So, you probably shouldn't pull it in, but you probably shouldn't pull it in, but you probably shouldn't pull it in, but you should make sure that your second brain should make sure that your second brain should make sure that your second brain has access to go grab it. So, that way has access to go grab it. So, that way has access to go grab it. So, that way if I said to my second brain, "Hey, can if I said to my second brain, "Hey, can if I said to my second brain, "Hey, can you just take a look real quick at what you just take a look real quick at what you just take a look real quick at what John and I were talking about last week John and I were talking about last week John and I were talking about last week about, you know, OTA number seven?" It about, you know, OTA number seven?" It about, you know, OTA number seven?" It would first go to our OTA file, and it would first go to our OTA file, and it would first go to our OTA file, and it would search through there and it it would search through there and it it would search through there and it it would try to find it there. If it would try to find it there. If it would try to find it there. If it couldn't find it there, it would look couldn't find it there, it would look couldn't find it there, it would look through the Wiki and it would look through the Wiki and it would look through the Wiki and it would look through meeting transcripts and see what through meeting transcripts and see what through meeting transcripts and see what we talked about there. And if it we talked about there. And if it we talked about there. And if it couldn't find it there, it would finally couldn't find it there, it would finally couldn't find it there, it would finally go to ClickUp itself, pull real data in go to ClickUp itself, pull real data in go to ClickUp itself, pull real data in from me and John's conversations, and from me and John's conversations, and from me and John's conversations, and see if the answer lived there. And so, see if the answer lived there. And so, see if the answer lived there. And so, that in my mind is still a second brain that in my mind is still a second brain that in my mind is still a second brain because I'm able to ask a vague because I'm able to ask a vague because I'm able to ask a vague question, and the second brain knows question, and the second brain knows question, and the second brain knows exactly where to look in what order to exactly where to look in what order to exactly where to look in what order to find that real-time data, and then give find that real-time data, and then give find that real-time data, and then give me back the answer that I need. That's me back the answer that I need. That's me back the answer that I need. That's the question I ask myself is, "Does this the question I ask myself is, "Does this the question I ask myself is, "Does this thing understand where my data lives and thing understand where my data lives and thing understand where my data lives and where to look, and can to give me where to look, and can to give me where to look, and can to give me accurate answers. So, as far as finding

accurate answers. So, as far as finding accurate answers. So, as far as finding your level, remember your whole project your level, remember your whole project your level, remember your whole project doesn't fit into one level. Maybe this doesn't fit into one level. Maybe this doesn't fit into one level. Maybe this folder's level two, maybe this folder's folder's level two, maybe this folder's folder's level two, maybe this folder's level four, maybe this folder's level level four, maybe this folder's level level four, maybe this folder's level three. Here's some things to think three. Here's some things to think three. Here's some things to think about. If you were re-explaining your about. If you were re-explaining your about. If you were re-explaining your setup and you need to find things by setup and you need to find things by setup and you need to find things by exact words or files, look at level one. exact words or files, look at level one. exact words or files, look at level one. If you have 30 plus notes and you keep If you have 30 plus notes and you keep If you have 30 plus notes and you keep forgetting what's in them, look at level forgetting what's in them, look at level forgetting what's in them, look at level two. That's where you sort of like two. That's where you sort of like two. That's where you sort of like ingest them and get that wiki with ingest them and get that wiki with ingest them and get that wiki with relationships. If your project is just relationships. If your project is just relationships. If your project is just completely whiffing on notes that you completely whiffing on notes that you completely whiffing on notes that you know exist and your routing isn't know exist and your routing isn't know exist and your routing isn't working, then maybe you want to look for working, then maybe you want to look for working, then maybe you want to look for something more like a semantic search something more like a semantic search something more like a semantic search that doesn't rely on an exact word level that doesn't rely on an exact word level that doesn't rely on an exact word level match. If you're looking for match. If you're looking for match. If you're looking for relationships and to be able to follow relationships and to be able to follow relationships and to be able to follow chains of questions and thoughts, then chains of questions and thoughts, then chains of questions and thoughts, then you probably want to look for something you probably want to look for something you probably want to look for something like a knowledge graph. you're running like a knowledge graph. you're running like a knowledge graph. you're running agents offline and you've got so much agents offline and you've got so much agents offline and you've got so much data and you want to sync up a bunch of data and you want to sync up a bunch of data and you want to sync up a bunch of Hermes agents together, then you Hermes agents together, then you Hermes agents together, then you probably are looking for something like probably are looking for something like probably are looking for something like level five, something like G brain. And level five, something like G brain. And level five, something like G brain. And another topic that I get some questions another topic that I get some questions another topic that I get some questions about, which I'm not going to fully about, which I'm not going to fully about, which I'm not going to fully address in this video, but I will address in this video, but I will address in this video, but I will briefly bring up is the fact that you briefly bring up is the fact that you briefly bring up is the fact that you are building your own second brain OS. are building your own second brain OS. are building your own second brain OS. So are other people on your team. The So are other people on your team. The So are other people on your team. The next question is, how do you actually next question is, how do you actually next question is, how do you actually make sure that everyone's data is make sure that everyone's data is make sure that everyone's data is syncing together and how do you have syncing together and how do you have syncing together and how do you have more of like your team second brain?

more of like your team second brain? more of like your team second brain? There's a lot of different ways to solve There's a lot of different ways to solve There's a lot of different ways to solve that. I think once again, it's not an that. I think once again, it's not an that. I think once again, it's not an issue of, oh, do we use Google Drive or issue of, oh, do we use Google Drive or issue of, oh, do we use Google Drive or Notion or GitHub or cloud plugins? I Notion or GitHub or cloud plugins? I Notion or GitHub or cloud plugins? I think the issue to figure out with your think the issue to figure out with your think the issue to figure out with your team is how do we actually make sure team is how do we actually make sure team is how do we actually make sure that we all have it shift so that this that we all have it shift so that this that we all have it shift so that this stuff is actually useful and not just stuff is actually useful and not just stuff is actually useful and not just noise. How do we make sure that process noise. How do we make sure that process noise. How do we make sure that process owners are updating their docs and owners are updating their docs and owners are updating their docs and syncing their stuff there? How do we syncing their stuff there? How do we syncing their stuff there? How do we make sure that other people are pulling make sure that other people are pulling make sure that other people are pulling from that rather than always just from that rather than always just from that rather than always just pinging the same people for questions pinging the same people for questions pinging the same people for questions and answers all the time? I think the and answers all the time? I think the and answers all the time? I think the adoption and the change management adoption and the change management adoption and the change management question is the bigger one. The tech and question is the bigger one. The tech and question is the bigger one. The tech and the way it actually functionally rolls the way it actually functionally rolls the way it actually functionally rolls out is a little bit less. But what I do out is a little bit less. But what I do out is a little bit less. But what I do know is that you getting set up with know is that you getting set up with know is that you getting set up with your own first and understanding how it your own first and understanding how it your own first and understanding how it works, how you should route, how you works, how you should route, how you works, how you should route, how you should make the decisions of where the should make the decisions of where the should make the decisions of where the data should live, that's the first data should live, that's the first data should live, that's the first hurdle. You can only solve the team-wide hurdle. You can only solve the team-wide hurdle. You can only solve the team-wide problem once you feel comfortable about problem once you feel comfortable about problem once you feel comfortable about the way you run it every single day and the way you run it every single day and the way you run it every single day and then it works for you. That is going to then it works for you. That is going to then it works for you. That is going to do it for today. Like I said, you guys do it for today. Like I said, you guys do it for today. Like I said, you guys can grab all the skills and everything can grab all the skills and everything can grab all the skills and everything that you need from this free community. that you need from this free community. that you need from this free 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. I will also include the description. I will also include the description. I will also include the slide deck if you guys are interested in slide deck if you guys are interested in slide deck if you guys are interested in flipping through. So, if you guys flipping through. So, if you guys flipping through. So, if you guys enjoyed the video or you learned enjoyed the video or you learned enjoyed the video or you learned something new, please give it a like. It something new, please give it a like. It something new, please give it a like. It helps me out a ton. And as always, I helps me out a ton. And as always, I helps me out a ton. And as always, I appreciate you guys making it to the end appreciate you guys making it to the end appreciate you guys making it to the end of the video, and I will see you all in of the video, and I will see you all in of the video, and I will see you all in the next one.

the next one. the next one. Thanks, guys.