The AI Second Brain: Complete System Walkthrough  🔗 **Source:** [The AI Second Brain: Complete System Walkthrough](https://www.youtube.com/watch?v=-TAowrw97-4&t=2149s) Okay. So, as I said, I want you to have a roadmap, a high-level roadmap of what the AI second brain system, the system that we talk about looks like. And how if if assuming you want to learn alongside us, what that might look like, how it works. All right? Um I don't have that many slides. I think I have like 25 or 26. Uh there's going to be plenty of time for us to interact. That's kind of one of the main benefits of this format. Um in the cohort itself, we do breakout rooms, we do coaching, we do a lot of different things. In today's call, just because it's so large, it will be mostly questions that we will interact with via the chat. So, I'll have two separate times for you to to ask questions in the chat. You can put questions anytime and we'll do our best to answer them, but I will specifically turn to questions in the middle after about um 45 minutes or so, and then at the end for the last 15 to 20 or 30 minutes. Okay? So, save your hardest questions for me. But first, let's get on the same page. >> [clears throat] >> So, a few kind of observations and perspectives here uh to kind of set the stage, set the context. I really believe that there's a new bottleneck in modern productivity. There's a new constraint. It's no longer your time. So, just just think about >> [laughter] >> first line. Think about this for a sec. Think about your career. Think about your life, your life experiences, and just imagine for a sec, even not even to do with AI, just set AI aside. Can you even imagine what it means to have your time, the time you have available not be a bottleneck? Just just like try to imagine. Imagine if you had infinite time. If time was not a factor, time was not a limitation. It's almost as if you could pause time for as long as you needed and spend as much time as was needed on whatever you wanted to create or learn or experience. Every anywhere you wanted to travel, anyone you wanted to meet. It's like a really an imagination challenge here. Imagine what it would be like to have your attention not be a bottleneck. You know, your attention, your ability to focus, your attention span, your ability to to pay attention to things that are hard or complicated or boring. What would you do with that mind of yours, with that creativity, if attention was not a bottleneck? And then intelligence. What if your intelligence even was not a bottleneck on what you could create, achieve, experience, the impact you could have? Not your your natural talents that you were born with, your IQ, your EQ even, all those natural traits. What if those were just not a limitation anymore? And imagine or just consider that the bottleneck has moved. The bottleneck has moved to collecting, curating, and providing context, which is really just information, to increasingly powerful generations of artificial intelligence tools. Which is a skill. It's not it's not obvious how to do this. It's a skill. It's a it's a discipline that we're calling PCM, personal context management. A brand new skill in the world that if you can master, you can get around this bottleneck. So, thinking about you as the human in all this. Don't want to forget about that part. Consider that your AI, all your different AI tools can only use, they can only make use of what you give it. What you give it. Your personal curated context, your notes, your knowledge, your expertise, your experience, your memories, your points of view, your perspectives, your relationships, your network, all the stuff that makes you you. Is now not just this, you know, a little weird productivity habit you have. It's it's a treasure trove. It's just an incredibly valuable treasure trove of data that no one else has, no one else can access, no one else can compile, no one else can generate. That context, I believe, is the only way that you escape you escape, you know, the disruptive changes that are coming, that you escape uh competition, that you create a a real competitive advantage that doesn't, you know, get eliminated with the next AI release. Uh I call it the mediocrity trap. Everything with AI, you you may have noticed, kind of pulls you towards the average. The way that AI thinks, the way that it writes, the way that it uh it works through problems. It's constantly sort of homogenizing your thinking. And that's because it's trained on the entire internet, everyone else's ideas and opinions and everything they've ever said. You can't stand out. You can't really have a competitive advantage if you allow yourself to be pulled into that that average, that, you know, that that that average level of quality, that mediocrity. I published a video a few months ago. Um maybe someone on the team could drop that in the chat. Which was exploring uh some research that has been done on something called context rot. Okay? So, imagine Actually, before I go there, there's something called a context window. Okay, we're going to start we're going to start here at the very, very beginning. >> [laughter] >> I'm not going to assume that you know you know anything about how these AI platforms, which are known as LLMs, large language models, work. So, your context window, the AI's context window, is how much information it can work with. You can think of it almost like it's working memory or it's RAM. Right? So, you can give uh an LLM, you know, 10,000 words or tokens, 50,000, 100,000, but at a certain point, it it quits. At a certain point, there's an error. I'm sure you've come across this. You have exceeded the context window. So, without getting too technical here, what you really need to understand is context windows have limits. They are not infinite. Not even close. Even with the latest AI models that say, "Oh, a million token context window, 2 million context window." Those are lies. >> [laughter] >> As this paper uh really proves and explains, the effective context window, how much you can actually give to these AI platforms, is really only maybe 25 to 50% of what they claim. That comes out to something around 30 to 50,000 words. Okay? So, even if they say a million words, 2 million, 5 million words, if you exceed around 30 to 50,000 words or in AI speak tokens, you start having these negative impacts, which is what this paper documents. You start having context poisoning. Context poisoning is when one little error, one little mistake, it poisons the whole interaction with AI. It's like it gets fixated, obsessed with this one error, and it can't let it go. I'm sure you've experienced this. Or this context distraction. If there's too much in the context that you give the AI that is not relevant to the task at hand, it gets distracted, just like humans. Right? It it gets it gets kind of all over the place. It gets fragmented. It's it's paying attention to the wrong things. It's it's getting distracted, just very much like humans do. And then there's context confusion. These are all kind of failure modes that the research has documented. Context confusion is when there's things that conflict. What is the AI supposed to do if you have two pieces of information that are either inconsistent or they're directly contradictory or they're incompatible, which I guarantee you will happen the more context that you try to give it. So, setting aside all this this is the most technical we're going to get right here. >> [laughter] >> So, setting aside all this new terminology and these numbers, that little warning sign down there at the bottom right is what I want you to take away from this. You cannot just dump everything in. I wish you could. I wish you could just say, "Here, here's my hard drives, my computer, my cloud drives, here's all my logins. Just access it all, make sense of it all, organize it all." You really cannot. You have to selectively curate the right I think of them as bundles of context. The minimum amount of context that you need to accomplish the task at hand. And that might seem like just a random, you know, it's kind of technical detail, but it's huge, you guys. It's so important because it means that all the stuff that we that we had to do and that we learned pre-AI, how to organize, how to curate, how to select, how to take notes, how to structure, all those things are still important. They're even more important because you have to do them to take advantage of AI's power. So, zooming out for a second, what is this AI second brain? It's the same as it always was. >> [laughter] >> Going back with my work over 10 years now, and really if you look at the history of what we call PKM, that's personal knowledge management, goes back decades. Uh decades to the early years of the 20th century. It's a system designed to amplify you. It's a system that lives outside your head, outside your body, that is designed to amplify you. To unlock your creative potential. And ultimately, at the grandest scale, to unlock your ability to lead a thriving generative life. So, we're using generative AI to lead a generative life. >> [laughter] >> And this graphic on the right is kind of the the 50,000-ft view of how we're going to do this. It's been amazing to me. It's been so surprising that all the the the techniques and the skills that came pre-AI, not only are still relevant, like I said, they're more important than ever. So, at the bottom there, we have code. That is the core method that I talked about in my book Building a Second Brain. Okay, so that really is centering your creative process, your productive process. And getting information in, which is the C, capture, organizing it, that's the O, distilling it, and then expressing it. That has to be the foundation. Ultimately, you're trying to put something out there. To publish something, communicate something, launch something, sell something. There's an expression at the end. To do that, we build this new layer on top, which is PARA, which is a way to organize your entire digital life that was explained in my book The PARA Method. Because you need certain kinds of information to express whatever you're trying to express. You have projects, that's the P. You have areas of responsibility both at work and in your personal life, that's the A. You have a wide variety of resources, that's the R. And you have archives, that's the second A. Okay. So, those two methodologies, CODE and PARA, at this point are very very very well distributed. Um in fact, we'll send you some links. Like there's the books themselves, but if you don't want to read a book, there's YouTube videos, there's the podcast, there's many blog posts. You can have at it. In whatever format you like to learn, there is a way for you to learn those two methodologies. But we're adding a new one. Right? We're adding this new layer that is building on. It is extending those pre-AI capabilities, but with this new generation of technology that we call AI. All right? So, let's zoom in a bit. Let's get into it. How how does this AI-powered second brain work? So, I always like to think of like a system, like a like almost like a mechanical system. Like if this was a a manufacturing line, or if it was a, you know, a water treatment plant. Like how does the like the actual bits of information flow from one place to another, and how does that add value to my life? So, the four main parts that we're going to talk about in the program that we're teaching, and this is also going to find its way into everything else that we do, is in four parts. So, the first one, as ever, as always, is capture. You need a way to capture information. Right? That's that's how you that that that's where it all starts. Capture notes, capture ideas, capture insights, highlights from your reading. Now, there's new ways to do that with AI. You can have an AI note-taker now, you can do voice transcription. There's a lot of really powerful AI capture tools, but you still need to think about it. There's still some decisions to be made. How do I want to capture information? What is the way of capturing that fits me? Once you've captured it, as before, this part also hasn't changed, is you want to organize it. And that's where PARA comes in. Okay? And the key thing with PARA that I'll point out here, there's there's a lot to say here, but you need an organizational system that makes sense for both humans and AI. This is the key point, you guys. You can have AI create a completely custom, bespoke organizational system that perfectly fits how it thinks, but if it doesn't fit how you think, then you've just created a system that you can't actually make use of. Right? So, so PARA not only is, you know, really well proven and well validated, it's simple enough and it's straightforward enough that AIs can understand it perfectly, and so can humans. That's the key the key criteria. Now, this is where it changes. Okay? Instead of going to distillation, which is a which was quite a manual, you know, labor-intensive process, the information in PARA that you've organized now flows into what we call a master prompt. Okay, I'm going to say a lot more about that in just a minute. But it's basically that curated context that you provide to AI that I was mentioning before. Then the that master prompt, or those master prompts plural, flow into and inform what I think of as a set of AI advisors, like an AI board of advisors. Imagine if you had a coach and a business consultant and a strategic analyst, and then also a relationship coach and a health coach, and, you know, all the all the people that if you had unlimited money, you would hire to help you, you can now have with AI. But it requires some design. Requires a little bit of of uh of, you know, of designing. All right? So, I want to say a little bit of more about the master prompt, because this is really this is really kind of the core thing. What is a master prompt? You can think of a master prompt as your personal operating manual for AI, for all AI. All the different You probably have half a dozen or a dozen different AI tools you work with. So, this is a completely cross-platform, platform-agnostic way of working with AI. It's not limited to any one platform. Okay? So, imagine just a and I'll show you mine in a second, but uh imagine just a document. Like any document, a TXT document, a markdown document, a Word document if you want, a Google Doc. Just a single long document that has some of these little bubbles that you see around the outside. So, as I read each of these, imagine your interactions, whether it's with Claude or Gemini or ChatGPT or Notebook LM or Perplexity or whatever it is. Imagine if that AI knew, say, your basic personal details. Okay, I think this You guys, this is this is this is so fundamental. I feel like this needs to be taught in schools. I I every single person in the world should do this. In fact, this is why we we we published a video on the master prompt uh in the summer. It was one of our most popular videos of the last year. In fact, that became a whole series. Someone in the in the uh from the team, if you could share that in the chat, that would be great. I decided to just give that content away freely to the world, because I think it's just it's like basic fluency for modern life at this point. But imagine if it knew your basic personal details. Who you are? What's your name? How old are you? Where do you live? Who's in your family? Imagine if it had your basic professional info. What's your job? What's the title? What's the role? What team are you on? Who do you report to? Who do who who reports to you? Imagine if it had go just going around clockwise around the circle, your income sources. Do you ever ask AI for any advice or have any questions for it related to money? Related to your finances or related to getting a promotion or related to how you invest or how you save? Well, wouldn't it be useful if it knew how much money you make every year? Or if it knew what your investments are currently? Or if it knew your risk tolerance for your finances? Or if it knew how much savings you have? You have to provide this information. And I'll just go quickly. Like AI needs to know your core values. I'm not talking about company. I mean you as an individual. What are your core values in life? What is your vision? What is your mission? What are your intentions for AI usage? How What are you trying to accomplish in your usage of AI? What are your communication preferences? How do you like to communicate and collaborate? How do you not like to? Your working style, your your tool preferences, your workflows, your rules, your boundaries, your goals and intentions. Goals and intentions are twice, cuz they're so important. Your personal SWOT, your strengths, your weaknesses, your opportunities, your threats, your skills, what quality looks like to you. Okay? I know this might seem like a lot. Like when I talk to people, even people who are very deep in AI, who have very sophisticated systems, I 99% of the time when I ask them if they have this this this kind of information provided to their AI tool of choice, the answer's is I I kind of can't believe that after all this time, we still largely don't do this. All right. So, let me show you. All right. This is my Claude. This is the desktop app for Mac. And what you're looking at, let's just make this very simple. So, I'm clicking over here on the left where it says projects. See that? A project is simply a little self-contained, almost think of it like a folder, that is kind of self-contained. It's limited. Everything that happens within that little container is limited to that container. Okay, so I have one for the book I'm writing, for the upcoming cohort, for the company as a whole, for my writing, for a different program that we run. Each little self-contained box. So, the one I want to go into is Tiago's work master prompt. I have a different one for my personal life cuz I don't want them to bleed over into each other. But if I click into that, this is the project interface. I'll go ahead and close the sidebar. Okay? And the main thing I want you to notice is this little box over here that says files. This is that curated context that I was talking about. They're also known as just project files. Okay? And there's only one file. You can have any number of things. You can see this one document is only using 1% of my project capacity, so that's good to know. I could add lots of other things. But if you click on this, you'll see my work master prompt. All right, so you have basic personal details about me, where I live, company information, our AI strategy, our ideal customer profile, our core products, um that we offer, the company mission, the company vision, the core values of the company, the business strengths. A lot of this is very business-oriented, but I have something similar with my personal master prompt. I have the weaknesses of the business. Uh examples of our brand voice, uh the org chart, uh some of our internal processes, our strategic and operational process architecture, our core value chain, how we serve customers, etc., etc., etc. All right? So, with that master prompt, that's what this is here as context, I can ask it something like, "With everything that you know about me, what is the biggest single gap in our product offerings, and what would you propose in order to address it?" So, the reason I could speak that, by the way, is I use an app called WhisperFlow, which allows me to just hold down a key on my keyboard and speak. Well, that's one of the capture tools that we'll show you how to use. And notice, if you look along the top here, there's three modes that you can use Claude in, chat, co-work, and code. I'm using chat. So, this is the this is the most basic, the most beginner level, the most elementary um version of Claude. If you want more power or you need more capabilities, you can use the others. Okay, interesting. So, it has a strong opinion. Notice that there's no way for it to have a strong opinion or for its strong opinion to be of any use to me if it doesn't have a tremendous amount of context. Think how much context you need to answer this question. You got to be able to holistically see the entire business plus my role in that business. And here's the gap that it sees. You have no scalable high-touch offering that doesn't require Tiago's direct involvement. And I think that I mean, that's exactly right. It's so true. And then it makes a proposal here. Okay, so notice that it knows my product ladder, how people kind of ascend through our ecosystem. It knows that I'm involved, highly involved in pretty much all of them, especially the high-touch ones. Um it can it knows that this is capitalizing on our three biggest strengths. Uh it knows that we previously tried to move into B2B offerings and it didn't work, and it even knows why. Right? And then it has follow-up questions. And they're not just general vague ones, they're really specific. For example, "What's your wife up to?" The fact that it knows I'm married, knows her name, knows what she's up to, knows that she's not currently involved in the business. This isn't a long response. Look, this isn't one of those like mega five, you know, a hundred or a thousand word things that I have to pour through. It's just a very succinct and very targeted kind of observation, the way that a coach would do, pointing out what's missing in my work currently. And I think it's quite insightful and quite accurate. Okay? And the other thing I want to show you before we move on is uh let's see. Notice that this was updated today. See 326? I updated it this morning. And the way that I updated that, I'm not going to get into this now, but every once in a while, every week or two weeks or three weeks or whenever, I give it access to my notes and I say, "Based on all of my latest notes, across all of my current projects, all the areas of responsibility, all the resources, if there's any new ones or any new archives, update my master prompt." And it did that. In a few minutes. I think I told it to do that. I went and heated up my coffee, came back, and it was done. Do you guys understand what is going on here? >> [laughter] >> Like this is so insane. This is so insane that I can just take notes in my casual, free-form, kind of messy way, and then once a week or every two weeks say, "Hey, Claude code." In this case, I used Claude code. "Update my master prompt." And it went ahead and did that. And and that's just like the most basic level. That's just like kind of beginner or what we call the foundational level of what this looks like. All right? I don't know about you, but my my mind is still blown by this. >> [sighs and gasps] >> Okay, I can sense those questions. I can feel the the the tidal wave of doubts and worries and follow-ups, and I want to get to those. Um I think there's a couple more things I want to share with you, and then we'll pause. So, how do I recommend you go about creating this thing called a master prompt? I have a very strong opinion on this. Okay? And this really speaks to what I think I've done so much reflection on the, you know, the decade that we were teaching Building a Second Brain, the the previous, you know, the previous ecosystem, the previous method. Uh we taught it in so many different formats and so many different ways. And just reflecting on all that experience, I think there was a big mistake that I made. There was like there was a variety of mistakes, but this was the biggest one. Which is I sort of imagine the ideal system. What is the ultimate way this looks? Which for me took years and years and many iterations, many versions. And then I said, "Let me teach this ultimate system to everyone." And that had, you know, some benefits. It was it was impressive. It was inspiring. Kind of got you excited. But I think the problem with that approach is that the fully mature system, as cool as it is, is not how you start. That's that that can't be how you start. That's the worst way to start. That's trying to, you know, to swallow something that you're not ready for. It's trying to build something that is, you know, on version 15 when you really need to need to start with version one. So, in this cohort, in this program, I'm going to try to rectify that mistake. And the way we're going to do that is we're going to build the same system three times. Okay? So, week one, we're going to spend week one at the foundational level, just creating the basic master prompt. The the version that I really believe is like the MVP, the minimum viable product, minimum viable prompt. Like what every single professional, no matter what you do, needs to have. We're going to do that in week one. So, if you just do week one and then you get busy or you drop off or that's enough for you, great. You got the the 80/20 of what I have to offer. Okay? And the the other thing that's important here is even for those of you who are more advanced, and many of you are, if you think about it, most of your AI interactions still reside at at kind of a basic level. Right? You don't need to fire up the most advanced system. You don't need to fire up Claude code for probably, I don't know, 50, 60, 70% of your AI interactions. So, even for advanced users, you want almost like a fallback. You want something that is that is small, simple, and minimal, and streamlined that you can fall back to for those kind of simple everyday interactions, and that's the foundational level. Then, we're going to do it again. We're going to sort of rebuild the system in week two at an intermediate level. Because what you're going to find is for many tasks, that foundational level is not enough. And And it's it's funny. I actually want you I want you to run into those barriers yourself. I want you to have the experience of what it's like having a more basic master prompt and then running up against the limits of it, the places where it doesn't work. And there's so many. >> [laughter] >> So then, you feel the need like viscerally, like in your gut, you feel the need for what we're going to do at the intermediate level. Which is basically to break apart your master prompt into little modular bundles. Okay, I know that sounds kind of you know, complicated, but it just basically means imagine your master prompt as a whole whole collection of different documents. And you only load up the ones that you need when you need them. So imagine you have a master prompt just for one project. If you're working on that project, you only load up that master prompt and nothing else. You have a master prompt for your finances. You have a master prompt for your relationship. You have one for your health. You have one for your vacations. You have like for each little part of your life and your work, you have like almost like a little specialized master prompt so that you avoid kind of overloading it and confusing it with too much random context. Okay? Then, in week three, we're going to do it again. Because the intermediate level is also it's not that it's not enough, it's that it has limitations. There's always limitations. So, the important point here is it is only at the advanced level that we're going to layer in all the stuff, the crazy, complicated, impressive, sophisticated stuff that makes up 90% of what you see on social media. Okay, the long-term memory where the the AI can actually build and keep track of its own memory itself, agents and sub-agents, integrations with other platforms, advanced harnesses, all this stuff that's going on. I really strongly believe should only come at the advanced level when you have the the previous layers, the more foundational levels in place. All right. So, I think I'm going to pause here. Okay, that was that was a lot already. >> [laughter] [gasps] >> Um I'm just opening the chat now. Team, do you have any questions or comments you want to surface for me? Yeah, for sure. Definitely seeing a theme around privacy and security when it comes to the master prompt. This is a question that that popped up a lot. So, how do you think about that? Like giving more sort of like sensitive personal data to the LLM or putting it into your master prompt? This is a whole conversation. >> [laughter] [sighs and gasps] >> It's a whole conversation. We're We We're going to have not an entire live session, but a big chunk of one towards the end, I believe, about this because it's very nuanced, you guys. It's very nuanced. Don't don't think there's a single like the single answers that you get these days are very black and white. They're very all or nothing. Give AI everything. It's no problem. You know, YOLO. And the other extreme is no, AI is inherently evil. It's stealing all your data. Pretty sure there's some middle ground there. >> [laughter] >> Um and it it it has implications. Has implications for which tools you use in the first place, for how you use those tools, for what you provide to those tools, for the permissions you give at different levels. There There's This is a world. And what we will talk about it for sure, but it's nuanced. I would say it's If I had If I had to say one answer, it's just a trade-off like everything. It's a trade-off between getting the power and the leverage of AI without getting the risk and the pitfalls and the dangers of of AI. Yeah, I like how Muhammad just put it in the in the chat. Security in the AI era is a calculated risk. Yeah. Like everything. I mean, everything is a risk. Getting in your car, driving down the freeway. Probably, you know, one of the biggest risks you take. They're They're all calculated. They're mitigated. They're They're counterbalanced. Yeah, anything else? Hey, should we get to some questions from the Q&A? Yeah, would you mind surfacing those for me cuz the the chat is pretty crazy right now. >> [gasps and sighs] >> All right. Let's pick this one from from Julie. I'm building my second brain in Notion and Claude. Um I bought the Notion power template. Personally working with Claude directly. Do you have Claude skills you're building or endorsing? How will the cohort maybe cover skills? Yes, we will talk about skills. That's one of those I'd say intermediate to advanced things. So what you're going to notice is that when you build your foundational master prompt, you're going to put stuff in there that later on I'm going to have you look look through it or have your AI look through it, and you're going to notice some of the stuff you're putting in your master prompt shouldn't be there. It should be skills. If it's like something like in in this case, do that. Or in these situations, apply this this lens. Those things that that are sort of triggered. Uh I mean, you can you can create something else that's called a hook. This is This is advanced, but you can create a hook or a skill. It's It's almost like what was originally just the single monolithic master prompt is now being pulled apart into different specialized, purpose-built tools. But I want you to start with the master prompt. Just get it all in one place because AI can do a lot of that for you. It can tell you what things should be and where they go and what format they should be in. Yeah, skill skills are of of the advanced things we're going to look at, I think is So, one of the criteria that I have is just what's mature. I'm only going to teach you guys things that are mature, that are proven. Uh because there's this wild crazy frontier right now, like like open Claude, for example. We're not going to do anything related to open Claude because it is a circus. It is a wild west. I have poured so many hours with zero return on that thing. >> [laughter] >> It's not ready. You know, maybe later it will be ready, but we we're sticking just to Claude code, which has been out for more than a year now. That is mature. And then we'll revisit what's ready to to look at in the in the fall. Let's go to a comment from Andy who is on answering asking from YouTube about your experience on letting Claude update the master prompt on its own. And how it might understand your intentions, update itself. Um how are you making sure that the updates are happening actually happening? Would you like read the whole thing again? Yes, that's that's probably the very first thing that will break in your master prompt. It will go outdated within like 48 hours. >> [laughter] >> Because that's the pace of modern life. That's That's how fast things move. And then we're going to have a conversation cuz there's there's different approaches to this, you guys. There's no This is one of our guiding principles, in fact. There's never just one right way. I I I wish there was. I wish I could just tell you the best way. But even something as simple as updating your master prompt, there's sort of a spectrum, which I think this person was kind of alluding to, from more automatic ways. Like you could really say, just go ahead and update it. I don't even need to know about it. Just do that every hour. But then, there's that that risk trade-off. It could put something in there that is not correct or is not accurate. And then on the other end of the spectrum is full human updating, which again has certain advantages and disadvantages. I tend to be in the middle, which is go ahead and propose a set of changes, flag the most high-stakes one for me so that I can say yes or no or provide input input, and then once I do, go ahead and do them. Uh similar question from Elise and Megan regarding work versus personal. Would you recommend different, for example, Claude accounts for each? Do you put them together? How should How do you think about the separation? Yeah, again, this is this going to be my stock answer for everything, but this is a conversation. I think you need some sort of separation. Some sort of separation, but you can do it. So, we're going to look at something which is the context stack. Imagine a pyramid where there's different layers of context. The ones that are more foundational influence all of your AI interactions. So think just just think for a moment, what is so inherent to you and universal to to everything that you do that you want it to influence every single AI interaction that you have. It's actually not that many things. Right? That's That's quite a low level, but then there's higher levels where it starts to become something that you can turn on or off. Um I typically choose to separate it at the level of the master prompt. I have a master prompt for work and a different one for personal. And that's a pretty clean separation. Um but then I have both of those in the same cloud account which is tied to my work email. So, there's always a little bit of bleeding in and out or some overlap. Okay, I think I'm going to keep going. Um Okay, so that was that was a little bit in the weeds, right? Uh I kind of like to zoom in and out. Always keep keep in mind the big picture and not get lost. And so I want to zoom out. >> [clears throat] >> I want to zoom out because it's sort of like one of the the questions that I I would love for you to answer out of this this this call is whether we're the right people for you to learn from. Right? I don't assume by any means that I am the right person, that our team is the right person for everyone. Right? You You really want to find the teacher or the community or the method or the philosophy that fits you and that you're going to be able to have confidence in. So, to help you do that, I want to just give you I think there's five of them. Like my five most contrarian opinions. They're contrarian in the sense that they're the most different from everything that I see online. Everything I see on X, on Instagram, on LinkedIn, on Substack. Right? So, to the extent that you either agree with these contrarian opinions or not even necessarily agree but are willing to entertain them, willing to consider them, then I'm probably the right teacher for you. All right? So, the first one is this stuff is hard. This is like maybe the most contrarian thing. Every day I see AI influencer after AI influencer just either say or imply that it's easy, it's seamless, it takes seconds, it's it's you know, you could do this if you're brain dead, it takes no effort. And then every time I take what they're telling me and I go and just try it virtually all the time I find in my experience and I'm you know, fairly competent uh it just requires so much more complexity than they say. So much more subtlety is involved in the decisions. There's so much more setup than they, you know, set the expectations for and there's so much more maintenance. So, I just want to be very honest with this that this isn't this like magic button that you press and life becomes easier, your work becomes easy. It's it's hard work and it takes it it's in in a weird way AI takes more cognitive effort. Like like it really burns through your energy to to work with AI because you're making these these kind of like architectural decisions that have a lot of, you know, downstream implications. So, I'm never going to pretend or say that this is easy. Okay? Hm. Number two, um I see a lot of commentary out there that oh, you never need to take notes. Just have your AI note taker do everything for you and just, you know, dump everything on all your drives and all of your your place. No. Note taking is more valuable than ever, you guys. You still it still requires human discernment and human judgment to pick out the signal in the noise. What of all this stuff matters? What is the important factor, the important priority? What's the point of view that I'm taking? At the same time the the value and the purpose of note taking is shifting. So, there's this idea from from finance, from investing called alpha. Alpha is a kind of information that other people don't have. Right? So, if you were a Wall Street investor, you you know, maybe you you travel out there to like Minnesota and you find out that there's like a you know, a pest that is eating the the corn fields and you have alpha. You have this unique piece of information that is not out there in the public and you can use that alpha to invest, to make decisions that give you a better return. That same idea is coming to all knowledge work. There are pieces of information that are not known to AI. Information that is only, you know, in certain places at certain times that is in certain people's heads, that is in old books that have not been digitized, that is in certain formats such as video and audio that are harder for the AI to ingest. There's all and there's hundreds of them, hundreds of little pockets of information of alpha that if you can find them and capture them in your notes, you now actually have kind of a disproportionate advantage over everyone else who is only using what the AI already knows and what it already has in its training data. Okay, so we are not leaving note taking behind. Number three, I I am of the opinion that agents are largely a bunch of BS. >> [laughter] [gasps] >> Um they're so not ready. They're so not ready. I've I've done so many tests and so many experiments and I think basically that the the online hype cycle is putting just far too much attention on automation and execution. Those are the buzz buzzwords right now. AI to automate your life, AI to execute for you, to, you know, do your to-do list for you. And I think that's just so misguided. It's it's not true. They they actually have tons of bugs. They constantly fail. They're constantly making mistakes. And in a way it's it's not even the right place to focus because the simplest bits of execution AI cannot do. The other day I asked it to just look at my calendar. Like the simplest thing. Hey, go and look at my calendar calendar and tell me what I'm doing tomorrow. Well, it immediately deleted a very important meeting that had 30 people invited to it and then it caught it and said, oh, sorry, I deleted that meeting. Let me undo it. And it said, I undid it and it didn't. It's like execution is not the right place for AI to focus. What AI can do, what it's more than ready to do is judgment or rather helping you with your judgment. It's decision-making, making better decisions. It's researching. It's it's synthesizing research. It's finding the gaps in research. Right? That's the realm of pure information. The realm of pure information where it doesn't have to interact with anyone or anything outside of your computer which is where it starts to go wrong. Okay, so we are not going to be talking about any kind of agent. We are talking about a cognitive exoskeleton, AI as an enhancement and as an amplifier to you, the human. Contrarian opinion number four is I really think you know, we talk about the frontier of AI. I really think the true frontier is inside our minds and bodies. Um and we're going to have a series of guest instructors that are all related to this. Uh this is it, you guys. It's not about the tools. It's not about the features. It's not about the technology. It's about do you have self-awareness? Do you know yourself? Do you know how your mind works? Do you have emotional fluidity? Do you have the ability to shift between emotions? The ability to regulate yourself? The ability to rest and recover? Okay, this over the long term, maybe not on the order of weeks and months but on the order of months and years, this is what's going to determine if AI is a force for good in your life or if it's a force or if it's a negative force. >> [clears throat] >> And fifth, this might be the most controversial but I absolutely refuse the urgency. I just think it's so it's so misguided. All this thinking, this apocalyptic thinking that you have 3 months, you have 6 months, you have a year, you have 18 months to, you know, make all the money you can before our world is over and you join the permanent underclass. I've been alive long enough that I have seen multiple technology waves and this is what they always say. Every single new technology wave they say it's all over and you have to do A, B, and C right now. I I think typically when they do that it's it's to get you to do something. Right? It's to get you to panic, give in to fear, buy something, do something, buy into something, an idea and I just won't do it. Okay, this this is going to take decades. This is going to take decades. Um it's going to play out for the rest of our lives. When we are, you know, at the end, on our deathbed, they're still going to be arguing about AI's impact on society. People will still have jobs. We'll still send our kids to school. We'll still read books. I'm not giving in to the panic and the hype. We are being more thoughtful and more present uh in the face of what AI is doing rather than less. Okay. So, we already did that. We're going to have more time at the end but let me just keep going. So, let me transition now from sort of talking in broad strokes about you know, my point of view, my method, my principles, etc. that I'm that I'm following to the program that we're launching. Okay, this this is the next action. This is the concrete thing that you can do like now, like starting today if you have decided you want to keep learning with me and keep learning with us. Okay? It's the first time that we're teaching uh a live cohort. At least we we did one focus on businesses last year but this is the first time we're doing one for individuals, for professionals in 3 years. It's taken 3 years of research and thinking and we've done many, many experiments, many, many, you know, trial and error things and this is what we've come up with as as really the new direction of our entire company and my work. It's an intensive live 3-week program. Okay, so for 3 weeks we are going to meet three times a week. I will be there every minute of it personally to lead you through everything. And what you're going to walk away with here at the bottom is a working AI second brain at some level of capability. I don't know if it's going to be at the foundational level or the intermediate level or the advanced level. That's kind of up to you. That's up to what you're ready for, what you have time for, what you're even interested in. Okay, but what that is is a personalized, organized, context-rich digital exoskeleton. And what it's going to do is make every single conversation and collaboration not just something that anyone else in the world would get from working with AI, but something that's informed by your expertise, your context and your goals and many other things as well. Okay. So, I want to kind of zoom into that. What is the way what what are the kind of the principles that we are using to deliver this? So, the first one is compression. Uh the first assumption that I have is that you don't have time. Okay, I'm assuming you don't have time or at least not as much time as you want or as you need to uh explore the frontier of AI. I mean, I don't have time and it's my full-time job. Takes our entire team spending most of our time, hundreds, really probably thousands hours, thousands of hours of research and experimentation and hands-on trial and error compressed into 3 weeks. That's the main value proposition. That's why you should join. In 3 weeks we're going to take you from wherever you are, even if you've just barely opened ChatGPT, all the way to not completely on the frontier cuz as I said, it's not ready, it's not mature, but pretty close to the frontier. Everything we do in this cohort is community-centric. Okay, so this is hard to understand unless you've experienced it, but the way we do education, it's not like I have all the answers and I am just delivering them on to you. Okay, that that's not how it works. I really see this cohort more as like it's all it's a learning community. It's a community of practice. I really want and I and I expect I'm going to I'm going to ask those of you in the cohort. I I I hesitate to even call you students. I like participants or or peers more because we're going to be constantly sharing what we're figuring out, constantly sharing our experiments, our mistakes, our failures, our wins and successes. I would say from our our past years of doing cohorts that at least 50% of what you learn and a lot of the most impactful things come not from me, but from the other participants. It's a it's a collective, it's a it's a crowdsourced learning experience that we're doing here. Everything we do is platform-agnostic, right? We're So, I should say all the demonstrations will be on Claude. Okay, cuz that's the one I know the best, but everything that we're building, the master prompt, the little context bundles, the AI board of advisors, my this is like a life principle for me. I don't do anything that is limited to one platform. I just don't. That's that's not a wise thing to do. So, everything we're creating is completely platform-agnostic. You take it with you. And I think this is the last one, but and I've I've kind of mentioned it a few times, but I'm really not interested in replacing humans, even if humans can be replaced. Um that's just not my preference. >> [laughter] >> I like humans. I value humans and my time and attention and effort is going to augmenting them, to making them smarter, faster, wiser, more embodied, more connected to their intuition to their intuition, more creative, with better judgment. Right? So, we we are really focused on augmentation, not automation. And this is the price. So, regular price is 3,000 bucks. We have payment plans available via two two different services. Klarna Klarna is one of them and then Afterpay. And there's an early bird uh option. So, this is only for the first 50 people, which is $2,000. It's a $1,000 discount. I would really encourage you if you are interested in that to do it now. Like that will be gone in hours. That will be gone definitely before the end of today. And what do you get for that investment? A few things. First one is the option to rejoin the next cohort. Okay, so the first one, cohort one, the founding cohort is next month in April. The next one will be in the fall. We're not sure exactly when, probably around September. But you're essentially getting two for the price of one. You have the option to join a whole second cohort in the fall which will have a whole new curriculum. Like I'm going to I'm going to update it probably massively with a whole new round of updates with everything that has happened between April and September. Okay. You also get access in the in-between time to our second brain membership. So, this is this is the cool thing is we're not creating a community from scratch. This is a community that has been around for many years. Uh it's called the second brain membership. It's on a platform called Circle. Uh we have our own custom app on iOS and Android, so you can access it on the go. Um there's polls, there's a discussion forum, there's different spaces you can join to kind of get into different niches. You can look up people's profiles. So, you can you can DM them. There's a map. You can see like where in the world do people live? There's a whole world in there that you get access to automatically um when you join the cohort. I think that's like a I believe it's a $650 per year value that you're going to get with that. Uh and then everything, all the course materials, slides, curriculum, everything will be available for 1 year. Not going to get into this too much cuz I want time for questions, but we have so far confirmed four guest instructors. This is something [clears throat] I'm so excited about because this is almost like a it's like a parallel curriculum because I really think these are some of the most important topics in in on the AI landscape. My great friend Chloe is going to talk about attachment, how your attachment style um shapes how you attach, how you relate to AI itself. Uh Joe Hudson, who is I believe one of the most talented coaches in the world. He's the personal coach of Sam Altman, has worked with half a dozen teams at OpenAI uh on the topic of fear, fear when working with and within AI. Uh my friend Raya is going to talk about AI as co-creator. She has some really cool projects and companies that she's started around that. And then these are all my friends. These are just basically my buddies that I the people that I've learned the most from that I am, you know, calling in to teach you as well. Uh Johnny's a dear friend and he's going to talk about nervous system regulation. How do you regulate yourself with the just unbelievable pace of change that AI is unleashing upon the world? And just in case it wasn't clear, this is not really a 3-week arc, it's a year-long arc. Okay, I'm not leaving you to your own devices on May 1st when the 3-week cohort ends. That's really just kind of the kickoff. We have a 3-week kickoff. Then we have five or six months of live events in the membership. Most of those live events are just going to unpack and go deeper on what we covered in the cohort. Right? So, those happen at least weekly, sometimes multiple times a week. We're going to have all the time in the world to just get into examples, get into case studies, get into, you know, step-by-step walk-throughs, answer your questions, do coaching sessions. That all happens within the membership, which is also in the process of pivoting toward AI. Then in the fall we have cohort number two with a updated curriculum and then there's another 6 months. There's a second half of that year membership to then follow up on everything that you learn there. So, what I'm really asking you to do is to go on a learning journey with us. Go on a year-long learning journey. I can't even imagine the things that are going to be unveiled over the next year in the world of AI, but we're going to do it together. That's the bottom line here. That's my concluding thought is when I think about the scale of years and decades, like think about what what is most important if this is something that is going to unfold over many years and even decades. I think the single most important thing for you to decide now is who are you going to learn with? You know, any book, any single book or video or or course is going to pass away within a matter of months. Uh any method, any technique, any set of principles, they're all just being revolutionized on a monthly basis. What will persist, I think, what's going to stand the test of time is your community. The people, the the other human bodies that you decide you want to influence and be influenced by. So, I guess [clears throat] if there's one decision that I would make, you know, today, whether you choose to join us or not, really is you know, that's completely your choice, just really thoughtfully consider who do you want to learn with. Right? Don't make the the feed on Twitter your community. Don't make the feed of endless hype that community. Choose a real community. Choose a community that is that is thoughtful, that is wise, that is diverse, that has a lot of different viewpoints, and really invest in it. Become a member of that community. And if what I've said today resonates with you, if it feels like it fits the way you see the world, then I I invite you to join ours. All right. Okay. Woo, that was a lot of talking. We have 25 minutes left. And I'm here for you. Give me your hardest most complex question. My answer may be it depends, but I'll do my best to give you some clarity. All right. So, why not start with the question from Sherilyn? Can you talk more about how emotional regulation, nervous system, inner awareness are critical for this process? Just want to understand more about how you understand this, and who are some of the guest instructors? Uh We actually saw that, so. >> [laughter] >> Yeah, I would say um I just want to say one thing about that. Uh this is a few weeks ago, about 3 weeks ago, I did a week-long uh course with Joe Hudson, one of the guest instructors, uh in Sonoma in California. I'm going to be writing [clears throat] a blog post on this. It's the the draft is currently 7,000 words, and I think by the time I'm finished will be like 10,000 words. So, I'm sorry for >> [laughter] >> the massive amount of text that I'm about to unleash. Um but the the big breakthrough, the big takeaway was around fear. I would not have said that I was afraid of AI or feeling fear toward AI. I would have said I was excited. Right? That I was optimistic and positive. But through this process, and we're going to we're going to do some of the exercises and some of the practices that we did in my course, I've asked Joe to lead us through those like live on Zoom. Because it goes so deep, I realized that I had so much fear. I had multiple levels. Fear on the personal level, what's going to happen to me, my work, my career, my income. Fear on the family level, what are my kids' futures going to be like? What is the right way to parent? What do my relationships look like at the level of the team? The business, the business model, the industry, all the way to like the fate of the world and the future of civilization. There's no way that all those levels of fear are not really really powerfully shaping the way you think and the decisions you make. And so, the important thing is not to deny that, it's to bring it into the light. To feel through it. Cuz each one of those kinds of fear are telling you something. They have a message. They have a signal that you need to hear, and the key is just to hear them. Which is I'm making it sound like an intellectual process. It's not. It's a somatic, embodied, experiential process. And we will we will try some of that in that guest session. What else? Anything especially that we like we didn't cover on the the website or in the in the emails that I've been sending out, something that has not been addressed elsewhere? Yeah, I'm I'm hearing um that some people are a little bit concerned if they are not really fully up to speed with maybe code or PARA yet, that they might be starting the cohort already on the behind. So, what could you say about that? Yeah, so a couple things. Um the first thing you will see the minute you sign up, like even today, um is we have a little I I believe it's already in there, right Julia? The Claude course? Is that in the curriculum? >> Yeah, yes. We have a beginner's guide to Claude that you will get immediate access to when you sign up. So, we're really not assuming any knowledge. Like it's really helpful if you've opened Chat GPT once or twice, uh or Claude, but um the first thing you will see in the curriculum, like right now when you sign up for the cohort, is a pretty It's it's not extensive. It's maybe like five or six modules or something like that. Just giving you a beginner's introduction to Claude. Right? So, we're giving that to you up front. So, like when I refer to a certain feature or I talk about something that is specific to Claude, you can already know what I'm talking about. That's the first thing. The other thing is we have so much existing content, and I I agree it's almost a problem because, you know, I'm not going to have you go read the PARA book. That would take a long time. Just watch the PARA video. Okay, that's 10 minutes, and you can get most of what you need to know. Uh if you need to know about code, we have, I believe, a video on that. There's practically everything that I'm going to talk about that is sort of like foundational knowledge, there is either an existing piece of content that is quite succinct that you can consume in a matter of minutes or maybe half an hour or something. And if not, then we're going to provide it as part of like the pre-work, the pre-curriculum inside circle. Um My my principle here is I want the floor to be very low. I mean, I'm going to have like my family members, my my parents. >> [laughter] >> Sorry for using you guys as an example. I think they're on the call right now. But my parents are going to be there, okay? They're the ultimate >> [laughter] >> the ultimate judge of whether we've made it, you know, easy to understand. But then I want to make this the the the ceiling very high. I want those of you that are like all into this, that are obsessed, that are just like going full speed ahead by the time the cohort is finished to feel like you've really raised the ceiling of capability. Which does mean we're going to move fast. The only way to have those two things is for there to be a a steep learning curve. And so, we have you know, we have three 90-minute calls a week. It's it's intensive. I put that word intensive in there. It's not an accident. Like you really need to like set aside the time. Honestly. Like set aside the time for it. Question from Megan. How much time will we spend on personal development work versus sort of like this AI and thinking brain training? Yeah, it's a great question. So, >> [clears throat] >> excuse me. Um so, part part of my answer to all these kinds of questions is we are going to very much adapt and flex what we're teaching in response to what people are experiencing. Like like this this is actually a very important kind of disclaimer. Um the whole point of the live cohort is not to like take you on a forced march through this curriculum exactly as designed. It's to feel you out. It's to feel you out. I have so many ways of doing that. I have the little feedback surveys, I have your circle comments, I have the expression on your face on Zoom, because we'll be in in meeting mode, so I'll be able to see the gallery of all your faces. I have your comments in the chat. If I sense that people are struggling or that we're moving too fast or that a you know, a a previous concept didn't land, then we stop. We don't we don't just like charge ahead. We flex, we adapt, we move faster, we slower move slower. We often like will create sessions like brand new sessions. We'll be like, "Hey, we need a breakout call, a whole other call to just talk about that thing." cuz there's like say a small sub small subset of people who are interested in that. It's a it's an interactive experience. Okay? Um I always say that each and every person in the cohort very like very much shapes the cohort. Like individual people change. They have an impact on how we go and where we go, and that's so important, right? Um and so, it's it partially depends on the the interest in that personal development side that I sense. If we have like five people interested in it, I'll kind of be like, uh let's just kind of like move that conversation to the the guest sessions, which is almost like a parallel curriculum. If there's a lot of interest in it, we may we may emphasize it quite a bit. Depends. All right. What else? Um I I just want to mention that we have already sold out of of our 50 seats at the $2,000 level. Okay. So, that that wasn't planned. That wasn't like one of these like crazy urgency-creating tactics. That was much faster than I expected, but uh early bird is over. Early bird is finished. All right. Okay, I want to ask ask a question from Preston. How do you find your alpha with AI? >> [clears throat] >> Yes, such a great one. Such a great one. Oh my gosh, we're going to talk about this. We have a whole session dedicated to note-taking and capture. Because it's subtle, you guys. It's so subtle. Like I'll just give you [clears throat] like one random example. Um I'm I'm really getting into local history. This is this is the last thing I ever thought I would be interested in, but uh we live in this Mexican town right now. It's a it's a small town. I mean, smallish, 100,000 people. Small compared to Mexico City, right? And I'm noticing that it has a really rich history that goes back almost 500 years. And none of it is digital. You can't find it online. I've tried asking every AI platform, they're all like, "We know nothing about this town." right? And at first I was like annoyed. I'm like, "I just want to, you know, I want a quick, easy, convenient, seamless way of learning this. But as I thought about it, I'm like, oh my god, this is an incredible opportunity. And I'm now like I'm kind of like in the Indiana Jones. I'm like going to the local library and taking out old books and literally like blowing on them with like the dust, you know? >> [laughter] >> And it's like I get to go on this little adventure of finding these these rare physical printed documents and like reading it reading through them in some cases and like old Spanish, using AI to translate the old Spanish into English. Um I'm working on a blog post where I'm going to talk about the 500-year history of this town. And so that's one example that I never would have imagined, local history. Think about the the local history that exists all over the world. Most of it is not digitized. Most of it is is not in the AI training data and therefore that's alpha. Now, how you take advantage of that alpha, that's a separate question. You know, maybe there's not like a direct way to say make money off that. But like in my case, I'm using it for community building. I'm starting a nonprofit with a friend uh to promote like sustainability and innovation in this town and I'm going to like share this research with this little community that we're building as a way of saying like you guys, there's a really rich uh tradition here. There's a rich legacy. And so like the the return on investment for me is not dollars. It's like connection, interestingness, satisfying my curiosity, having conversation fodder for, you know, these local friends that I have in my town. So you you got to think beyond finances. Think beyond money. Um but there's so many examples. Like things that happen in conversation are alpha. Conversation with friends, things that uh happened in the past like during your childhood. I'm doing another project now to digitize all my home videos from my childhood. Cuz I realized, holy crap, those grainy, low-resolution home videos from when I was five, AI can will soon is pretty close to be able extract tremendous meaning from that or at least just edit it into like a highlight reel. Uh it's everywhere. Alpha's everywhere. Uh but you got to you got to you got to think, you got to pay attention, you got to think like what kinds of alpha are most relevant to you. And then you have to find an efficient means of capture for getting that alpha into your own context. Okay, so this is a question from a little earlier and I don't remember who asked it, but it was around like specific like use cases. Like how have you specifically seen this sort of like help you? Like you know, the master prompt, what you will be teaching, what what results? Talking about the results you've gotten. Yeah, sometimes we nerd out on the the the process so much that we forget, you know, the results. Um there was another comment too I saw in the chat like is this just for business? Or even just for work? And I would say absolutely not. Uh those tend to be I tend to use work-related examples cuz the return on investment the investment of your time is so clear. But I would say the impacts have been just as big in my personal life. I'll give you a couple examples and this is what we're going to tackle in the AI board of advisors. Those those advisors are not just for work life. I have actually found them more useful in my personal life because in my personal life I don't have as good of advice. I I I like can't justify, you know, the the consulting and the coaching in my personal life. So one example the two examples are my health and my finances. So with my health, I'm going to write [clears throat] this up uh soon, but you guys, I just I've just started a basically assembling all the context I can find about my health, providing it to my AI health coach, my health advisor. And I I would say I've learned more about health and my own personal health in the past couple months than than I ever have before. Like the its ability to cross-reference, oh, you're taking that supplement, but you're also do you're also having that protein after your workouts. Well, that this ingredient in that protein, which I shared with it, is counteracting and making it so you can't absorb that supplement. Or oh, you're trying to get more protein in your diet, but you're you eating too much steak. That's too much red meat, which is increasing your cholesterol, which I know you're trying to keep an eye on. So substitute 50% of that that red meat intake with fish and chicken. Like things like you would need a team of not even doctors cuz doctors aren't good at nutrition. You would need a team of nutritionists around the table, you know, going through your health documents and which are of course are in a dozen different formats. It's crazy. The number of formats you have to work with with health. And I talk to it almost every day. Uh and now I'm doing the same for my family. I'm creating health advisors for different members of my family because I'm just like my parents, you know, they're they're getting old and they don't have anywhere near this good of advice for their health. Um the other one is um finances. Um we've worked with a financial advisor before, but do you know what financial advisors charge? Like they charge a percentage of fees under management. Have you seen the math on like if you work with a financial advisor like over 5, 10, 20 years, you're paying them like a sizeable percentage of all the money that you make from your investing. It's absurd. Right? Even the the advisors that you can pay like by the hour are expensive. Um and so I've given it uh our financial context and there's just all these all these like mistaken assumptions I was making about my finances. There were some things I just flat out did not understand about how retirement account works accounts work, how 529 education accounts work. Like I had certain ideas of what risk is or even means that were actually completely misguided. Uh and we've significantly changed how we save, how we invest, how we give, how we how we uh donate uh based on our work with our AI financial advisor. Those are a couple examples. So the reason you need your uh we have 10 minutes left. Your board of advisors is So this is another example of where the master prompt fails. Your master prompt is very like hor Think of it as horizontal. Right? It's across, like I said, everything. It's across every AI interaction. Right? But if you have a certain domain of your work or life, like health, like finances, at work it might be like looking at your HR policies or looking at your insurance needs or looking at your marketing strategy, like one vertical slice, your master prompt won't have anywhere near enough context. Right? How could it? How could it? So for So for those vertical slices, you have to go really deep on just that slice. Where is the context that you'll need? And often like you got to you got to go spelunking. You got to go log into random platforms, download things, convert them from one format to We're going to talk all about this, but convert them in into a format that is AI friendly such as markdown. You have to um you have to do a little dedicated like curation effort to get that context in one place because it tends to either not exist at all or not exist in digital form or not exist in a digital form that AI can make use of. Um if you folks have asked if this is suited for people with ADHD and maybe the broader question is who is really best uh would best benefit from the course? >> [gasps and sighs] >> Yeah, there's a few I think we have this on the website, but there's a few people that come to mind. Um I mean the the the main one as I said is if time is a constraint. Because if time is not a constraint, if you can afford to spend I I feel like realistically it takes at least one or two hours a day to kind of tread water. Like that's just that's like maintenance. That's like basic maintenance. It it really does, you guys. Um like those one or two hours would just be spent sort of like maintaining what you already have. You know, as I said before, it takes maintenance. Don't let anyone convince you that no maintenance is required. Uh and then I think you would need at least another one or two hours to do anything new. To learn anything new, try anything new, adopt anything new. So like three to four hours I feel like is what it really takes. If you have three to four hours a day, go for it. Like do trial and error. There's no there's nothing like direct experience. Right? Um but if you don't, then allow us to compress. You know what I noticed that was funny? I I went through months or even like years of of notes and Notion docs and experiments and different things designing this curriculum. There was like a six-month window. Only things about six months old. So uh up to like the beginning of the fourth quarter of last year were relevant and then it like dropped off. Everything that was more than six months older was like zero relevant, zero usage. It was actually like the wrong thing to pay attention to. So I kind of think in AI right now there's like a moving six-month window of relevance. And so this cohort, this three-week cohort, we're getting really the last six months and we're compressing it into I think about 15 hours is what we have in terms of live sessions. So six months of time compressed into 15 hours. That's the main value. And then besides that, I would say professionals. There will there will be I would say more of an emphasis on work. That's tends to be the arena where people use AI more. Uh people who um are neurodivergent and have ADHD. I kind of think that this is a golden age. This This is AI is ushering in a golden age for people with ADHD and people who are neurodivergent. Because finally multitasking >> [laughter] >> such as between multiple cloud code sessions that are all happening at the same time or multiple agents that are all working. That's that's now going to become one of the most valuable skills. It's going to become so incredibly important to be able to do that and it is a skill. It's a skill. It's like the skill of middle management. Those of you who are are middle managers and have, you know, eight direct reports. That's people talk about, "Oh, middle management is going away. That's going to be the first people to lose their jobs." Maybe so, but you're just we're all going to become middle managers now. >> [laughter] >> We're all middle managers of our own team of AI agents. And as any manager will tell you, I mean people people go through an incredible like transformation to become managers. To be able to lead, to be able to delegate, to be able to coach, to be able to guide, to see things from different perspectives and let go of your perspective to take on someone else's. It's like a whole skill set that we kind of need to learn now and people with ADHD I I I've seen some examples that they tend to thrive in that environment. Who else? Um any Anyone else come to mind, Julia, as a as a good fit for this? I was answering questions and not listening to you. >> [laughter] >> Perfect example. >> [gasps] >> Okay. Uh question from Maria. She's in the middle of reading second building building a second brain. What's your advice on starting to capture at this point? I think we've already talked quite a bit about capture. I would just say it continues to be important as important as ever. But the way it happens and what it's focused on needs to change. Needs to change. Needs to become more about just more about finding whatever is not in AI's training data or what AI cannot find through a web search. It's as simple as that. Anything else? 5 minutes left. I wish I could see you all. I can I can get a sense of you from the chat over here on the right, but it's kind of it's a lot going on, but I love I love that we do meeting mode in the cohort because it's it's it's almost like we're just like it's like a work meeting. We're getting on with our colleagues, our collaborators, our peers and we are like yes, I'm teaching, but we're also kind of knowledge sharing or giving feedback on different things. We're sharing things we've tried. No No one No single person has enough time to try everything. It's impossible. So I I really in in a funny way I'm trying I'm >> [laughter] >> I'm very much trying to assemble the group of people that I personally want to learn with. Honestly, like that's it. I'm trying to bring together a little crew uh that, you know, shares some principles, but then has other, you know, divergent and diverse points of view because I want to spend the next few years learning learning with those people and I can't do it all myself. Even our team of six cannot do it all ourselves. Oh, the t-shirt. Yeah, this is These are the previous t-shirts. I guess they still kind of apply. Um I've long wanted to make the t-shirts available on the website. Maybe we'll do that. Uh there's no attendance >> make an attempt. There's no attendance limit. This is something that I that has always been important to me. Um that to me feels like an artificial constraint. Like why as long as Zoom can support it, why put a cap on it? Uh which also means we don't actually we really have no idea how many people are going to are going to end up in this. My goal was at least 50. 50's kind of a nice number. Seems like it's going to be more than that, but um we don't know for sure how many people will be in there. And I just want to point out if anyone has questions, um you can reach out to us at [email protected]. We'll be right there answering your questions. Thanks, everyone. >> probably many still have some. Yes, [clears throat] please send us all your questions. We want to hear them all. And >> And enrollment is open until April 14th. That's one day before the first live session, which is on April 15th. Awesome. Thank you. Thank you all so much for being here. I appreciate you. And I hope to see you soon somewhere. >> [clears throat] >> Bye, everyone. Thank you, everyone. Adios., The AI Second Brain: Complete System Walkthrough, YouTube, 01kpkzc3mfzpf36prt4chsa13h.