Transcription
So, this week, the big news was that Andre Karpathy, the AI Godfather, the guy who created the term "vibe coding," who was pushing forward knowledge graphs, and also created the auto research system. And all these things have gone super viral and have really been like the trendsetting for a lot of the industry. He's now joined Claude. So, what does this mean and why does it matter for you?
I think what this means is that what AI, OpenAI, and Claude are starting to realize is that a lot of the power of AI is actually not hidden in the models. It's actually hidden in the layer on top. So, what all these AI companies have realized is that the model is just not enough to really bring true value to people's lives. And what Andre Karpathy, and what everybody else that I'm seeing, has found is that you really need like an operating system that's customized to you on top of the AI. And the cool thing is, this can be free. You know, this can be something that maybe you work with a Claude Max subscription, maybe you work with other tools, but this isn't something that you have to pay a whole monthly subscription for. It's really something that you use to really define and structure the way that AI is getting information to you.
And the cool thing, too, is that I think that there everything is changing. Like, every week there's new news, there's new tools, there's new models, everything else. But I do think that the AI OS operating system is likely, it is starting to solidify. And I think that that's something that's very important when you're working in like a fast-moving field like this. If you can figure out what is not going to change, that's really what you want to invest in and focus on. So, I think that with AI, this is where you want to focus. You don't want to try and learn some like random tool, even though I spend a lot of time with Claude Code and Code X and things like that. I think they're super valid. But you really want to understand how you can build your own operating system on top of it of that.
And something that I've started to notice working as like an AI architect for the clients that we work with, I feel like you can break the data that you need to give to LLMs into two big categories. One of which is quantitative data. Um, and this is like SQL stuff, business intelligence. It's just numbers. And so, that's pretty straightforward. Um, there are some unique things that with my analytics company we do differently for AI, and I'm also going to share that in a future video. But what I want to talk about today is qualitative data. So, this is like, you know, written content or like strategies that you've written or brand guidelines or even like visuals or images or different things like that. And that I think is becoming more and more clear exactly how qualitative data needs to be stored for AI. Um, and there are a couple other um sections as well. Um, like being able to store the run-time states and also having canonical knowledge, but really the quantitative and the qualitative is probably what you should spend most of your time on.
So, let me go into what is a knowledge graph? So, I spent a lot of time trying to explain knowledge graphs to people, and I think I found the the best way to explain it. So, when you're on your computer, most people are used to a traditional file system with a hierarchy. And so, let's say you have a Memorial Day Klaviyo email that needs to be sent on May of 2026, and it's tied to the marketing department, it's tied to the seasonal promotion library, and then you're having to decide where to store like this file, maybe. Let's, you know, it's a draft. It's a draft that you have. And so, what most people are used to is you have to just pick something. Like you might have a file system that's like, "All right, we have the company folder, and then the marketing department, and then maybe there's a Klaviyo folder." Um, and you just have to pick. I mean, it may tie to multiple different things, but you just have to find some hierarchy that makes sense um, and it just forces that uh situation. It's what we would call like in data like a one-to-many relationship. Like there's one parent folder to many subfolders.
But when you have a knowledge graph, all that breaks. You can actually just say, "Here is my Klaviyo draft, and by the way, this ties to the project of Memorial Day, it ties to the tool of email, it ties to the workspace uh marketing department, it's a part of our seasonal offer, and also this is it ties to our company voice." So, you then can just have the file, and then it can have six references, and it's more like a much more like flattened, broad like node brain instead of like a traditional file hierarchy. Um, and I'll just tell you this, AIs love this kind of data. They can like fly through and analyze it all and see connections that we can't even see as humans. Um, but on the traditional file path, they get very limited. And so, if you're trying, even if you give it access to the files, it just spends way more time like going through, finding things. It's harder for it to find connections and do its own self-exploration across files. So, these knowledge graphs are going to be really, really key for AI.
And to be honest, it doesn't matter if you use OpenAI, it doesn't matter if you use Claude, it doesn't matter if 3 years from now they create a super AI. Like, the AI is going to need knowledge, and it's going to need your company's knowledge, your personal knowledge. That's going to be something. So, I think this is something that you definitely want to spend some time focusing on is starting to build these knowledge graphs now.
But, a recent video I did is I actually have not liked a lot of this second brain type content. Um, I went super into that a few years ago, but too much of the the second brain type content was focused for human readers. But, I'm never going to open my knowledge graph. Um, I'm going to have AI open it and explain things to me and write details for me. To be honest, it really sucks copying all this and doing it manually. So, it's like one of the perfect things for AI to do for you. It can actually build the brain, it can track things, you can ask it to make changes. Um, but because it's going to be AI, I've actually found that there's several things that you should change with them. So, I released a video, if you'd like to see, on my infinite brain system, and I'm planning to open source it in the next 2 weeks. So, subscribe to the channel or look at our other videos to learn more about the infinite brain system.
But, the key things you want to do is you you definitely want to like the most important part, I would say, is indexing. And with indexing, you want to be able to have like, maybe there's 5,000 notes you have on a specific topic, you want to be able to have like an index that's like, "Hey, here's all of our like marketing images tied to this product. And here's all of our marketing and products tied to this." And have like a short summary of each piece, so the AI can quickly read the indexes and know like, "Oh, here's where I can go to find other details." Because the AI could read maybe 500 notes before it would have to actually uh come back to you with an answer. So, you you ask it a question, it goes to the knowledge graph, it it's too much for it to just fit all into one prompt. So, it reads across and finds relevant things to inject its knowledge into its knowledge. Maybe it'll read like your brand pillars, your brand strategy, different things like that, or your images, your products, or previous marketing campaigns that worked. Um, maybe even tie it into some data to show what works well. So, you could basically have all of that to where the AI could re-research all that in a few seconds and then come back to you with the perfect answer. But, that's the dream and the vision of knowledge graphs.
One thing that I added to my infinite brain system that I'm seeing a lot of people missing is that I am adding these edge types and a few other things. So, definitely if you're interested, like go check out the video and I'll walk you and it walks you through more about the infinite brain system. And what I used to have is I used to have a system where I would have like a folder, honestly, like the old hierarchical folders that have like agents, that have like skills, that have workflows. And then within that I would store each of those pieces. But, now what I've done is instead of having it in that hierarchy, I've started just making it to where everything is an infinite brain. Like the more I thought about it, the more the infinite brain just ate everything except for quantitative data, which I'll talk about in a future video what to do with that. But, pretty much the whole system has just become an infinite brain type system.
And so now I have my own I'm I'm finalizing an operating system that I'm going to open source for free, and we're going to talk about in our school community as well. But, it basically um uses mainly just free tools to free or cheap tools to interact with this operating system. So, you can continue to build out this AI architecture for you. And then at that point, you're like agnostic. It doesn't matter if Claude becomes way better, or if Grok comes into the race, or Google suddenly pulls ahead. Um, you can just take your operating system and move it between the models. And if there's other really cool tools, they're probably going to integrate with systems very similar to this kind of architecture anyway.
And so now in my infinite brain, instead of my hierarchical folders I used to have, I now have entity types that could be like an agent. So, you might define this as, you know, the persona, capability. Um, I am making it to where all my agents will pay per click. Um, you also could have skills, you could have workflows, you could have rules, tools, knowledge. So, this is like just knowledge within knowledge. Like if you want a whole knowledge space just tied to one particular topic, you can have that. And different projects, outputs. So, anytime it creates something my AI, I always save it. But, what's cool about this system is that you can store all this in markdown. And markdown is basically just English. Like maybe it's like a little bit overwhelming to read, but you You read all this. But, you don't need to learn any crazy coding languages, or anything else like that. You just need to know English and how all these all these components can work together.
So, all of this can then be stored in a way that's compatible with Infinite Brain. And, what's cool to me is that you can store all of this in a folder. And, what I'm starting to do with companies that I work with is we actually will give every single one of their team members one of these types of folders. We'll train them on it because it does take a little bit of training on how to use this. But, then they basically have their own personal AI operating system where they can add agents, they can add workflows. And, Claude Coder Codex can just build all this out super fast. Um, so, you don't even have to like understand how to solve the problem. You can just explain the problem, and it'll convert it to an Infinite Brain shaped solution. So, this has been working really well.
And, then what's cool is that we're making it to where the person has as much power as they can in their own repo. But, then what we do is we in our AI Architect service, we actually will review all the person's repos, help them refine it, and improve it. And, then we'll move it to like an apartment level repo. So, if you if some if one Meta Ads analyst creates an amazing report, it can then be moved up to the Meta Ads department. Or, if they make a knowledge graph that lists all their creative images and creative copy and everything that's working with that, that also can be added to the Meta Ads department knowledge graph. So, this is a system that we built because we think it's best for AI. But, what's also really cool is that the CTOs and traditional tech leaders that we've been showing this to also think that this makes a lot of sense and are very happy with it. It's a very similar to how other people have worked with us. And, the only concern they have is if the business power users are going to be overwhelmed with GitHub, or overwhelmed with these other tools. And, we're not finding that. We're actually finding that people when they're empowered with all this setup are very quick to just take it and run with it.
Well, I think this is really the pattern that I think more and more companies should do is building this AIOS architecture, having every person build their own, and then having it slowly solidified into department operating systems and company operating systems. And, then at that point, your company can scale, and it doesn't matter which AI tool you use because you have an operating system on top of it, you're going to be doing way better than whatever the base model would show.
So, I also just want to show these are the tools that I think I'm solidifying on for this AI operating system. So, you have it all in that markdown English text that honestly anybody should understand. It's going to be so large in terms of the files and the agents and the skills that probably you're going to have AI agents that read it and ingest it and then use it. But, if anybody if there's any component you want to understand, you could just open it up and understand it. But, what do you build on top of it? And what I'm finding is is that yes, you do need a Claude code subscription or Codex, that's like OpenAI's version of Claude code. And that works really well. When you put those tools on top of a infinite brain-like system, it works really, really well. It'll start storing agents for you. It'll be finding skills, finding workflows, and different things. But, I've also decided to structure the infinite brain in a way that can work with three really cool free tools. And I think that's what's best for my for our clients. Like, we want them to be able to move between the tools, be able to use the best that's available, and then not be locked into some third-party vendor that may cause issues for them down the road.
So, the first one is we're trying to make it to where the entirety of the infinite brain is structured in a way where it's easy to open in Obsidian. So, Obsidian's a great tool, it's free, and it's great for looking at knowledge graphs. A lot of people have been using it. And so, that way everybody can just download Obsidian, and if they want to open up different sections, they can see different components of the infinite brain in a nice system. For workflow, so this is like when you have if this then that. Like, maybe you have like an automation where like first you gather data, then you build a report, then you take this kind of action, and you like have all that marked out in like a flowchart with lots of different to-do's and if this then that's. So, n8n does seem to be the gold standard for this. And so, we're defining our workflows in a way where if you want to, you can just one-click upload it to to a company in n8n. And then if n8n is self-hosted, n8n's free. So, you basically can have the ability to then have these workflows for free available whenever.
But then also, this is the newest one that I've added. We've started adding Paperclip Departments that I have a new video that's coming out soon on Paperclip Shadow Departments. And I'm finding that storing agents in a Paperclips We're storing all of our agents in a style that is compatible with paperclip and trying to make all the rest of our systems also compatible with paperclip because paperclip is also open source, so you can self-host it and have a paperclip style OS. And so what's cool is that you can have this entire operating system that's stored in markdown, easy for everybody to work with, that's well structured, that makes it where AI can even continue to build this out. You describe a problem and then AI breaks it down into what are all the components that it needs to build to solve that problem. And then when you want to analyze it, you have three open source great tools you can read it in. And then also the the you already have two amazing options for really powerful AI tools, Claude Coder Codex, that you can then use to to operate this AI OS or to continue to build it and develop it further. And it took me a long time to figure out that this is the perfect style and perfect system. I tried a lot of other tools and there are some other components like Hermes has a specific use case that is sometimes nice. I'm staying away from Open Claw completely. There's a lot of other tools that I am considering adding to this, but it just doesn't make sense. We've tried We've tried to make it as simple and powerful as possible.
So if you're interested in learning more about this Infinite Brain system, on June 10th, we're going to open source it. So it's going to be free. Anybody that wants to have access to a template, we're going to make it free. We believe in open source and having free options. We want AI to be free and people to push it forward. Um, so if you're into that, subscribe and then we'll have a big video explaining it and walking through in detail when it's free. We also have a school community that if you want to go through a structured course on how to learn these AI operating systems and then build something out compatible with the Infinite Brain, we're also releasing a course to go alongside that on our school. So you're welcome to join that, but the school price is going to go up on June 10th when we release this. If you subscribe now, you're going to lock in the lower price and on June 10th it's going the price is going to increase. And our school community is focused on making business users AI power super users. So putting the right architecture in place to where that can scale horizontally across your entire organization and vertically across all the different problems you may run into.
And then finally, if you'd like to hire us to set up a system like this, or even to set up AI transformation for your entire company, that is something we can do, and we can do it well. And if you'd like to reach out to us to have us set up this system for you, then feel free to go to our website where you can sign up, and it will either be me or my business partner, Matt, who will help set this up for you and your company. Awesome. So, subscribe to stay up-to-date on all the latest AI architecture news. We will keep you updated as we release more things.