A four-layer framework, context, connections, capabilities, and cadence, turns a single Codex project folder into a working AI operating system that answers questions the way a co-founder would, not a chatbot.
Who This Is For
Read if. Skip if.
READ IF YOU ARE…
A solo founder or creator already using Codex or Claude Code who wants one AI interface that actually remembers the business instead of a blank chat every time.
Someone juggling Slack, email, a CRM, and a project tool who wants to stop context-switching between tabs just to answer a simple question.
A builder willing to spend real setup hours writing context files, running audits, and iterating, instead of expecting a one-click app.
SKIP IF…
You want a plug-and-play SaaS second-brain product; this is a hand-built file system you maintain yourself.
You don't use Codex, Claude Code, or a similar agentic coding tool, since the whole system lives inside that interface.
TL;DR
The full version, fast.
A creator walks through turning an empty folder into a full AI operating system inside Codex, using a four-part framework: context (stable facts about you), connections (live tools), capabilities (skills), and cadence (automations). A free skill pack handles onboarding, auditing, leveling up, and building an interactive 3D knowledge graph, while an AGENTS.md file acts as a routing map so the AI always knows where to look. The system scores itself over time, starting near zero right after onboarding and climbing as more context and connected tools get added, and the most expensive model isn't the right default for routine tasks.
Free for members
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Demos the finished system: a 3D knowledge graph of the whole business, a synced OS dashboard with calendar, comms, and community pulse, all built with GPT-6 Astra in Codex.
02:12 – 04:51
02 · The Four Cs Framework
Introduces context, connections, capabilities, and cadence, and the three tests for knowing an AI OS is actually working.
04:51 – 07:34
03 · Free Skills and AGENTS.md
Points to a free resource pack with five skills (onboard, audit, link, level up, 3D brain) and explains what AGENTS.md does and why it matters most.
07:34 – 10:25
04 · Building Your AI OS
Step-by-step setup from an empty desktop folder: create a Codex project, install the resource pack, run onboarding, answer seven questions, paste writing samples.
10:25 – 11:41
05 · Connecting Your Everyday Tools
Sorts daily tools into tiers (revenue, customer, calendar, comms, tasks, meetings, knowledge) and shows asking Codex how to connect each one.
11:41 – 14:13
06 · Auditing and Improving Your OS
Runs the audit skill for a score across the four Cs (30/100 on a fresh build), stores dated reports, then runs level-up for concrete next actions.
14:13 – 15:26
07 · Building Context With Grill Me
Uses the Grill Me skill, inspired by Matt Pocock, to get relentlessly interviewed on business priorities, saving each session as a new file.
15:26 – 17:28
08 · LLM Wikis and Your 3D Brain
Applies Karpathy's LLM Wiki method to link notes by relationship, then runs the 3D brain skill to visualize the whole knowledge base.
17:28 – 19:25
09 · Choosing Your AI Model
Explains when to use GPT-6 Astra versus cheaper models like 5.6 Sol, and how effort level trades capability for cost.
19:25 – 19:49
10 · Next Steps
Closing CTA back to the free community and resource pack, teasing a follow-up video on voice-controlled multi-agent delegation.
Atomic Insights
Lines worth screenshotting.
An AI operating system is built from four layers: context (static facts about you), connections (live tools with changing data), capabilities (skills), and cadence (autonomous agents and automations).
Capabilities and automations only become valuable after context and connections are in place; skipping straight to automation produces generic results.
A working AI OS passes three tests: a teammate's question gets answered faster with sources than you could answer it yourself, you stop opening other tabs because the AI interface becomes your default surface, and you stop rehearsing facts because you trust the system to retrieve them.
AGENTS.md (Codex) and CLAUDE.md (Claude Code) can hold identical content; copying one into the other lets the same knowledge base serve either tool.
A routing map inside AGENTS.md, which tells the agent exactly which folder to check for which topic, matters more than the raw volume of files, because it is read before every single message.
A fresh AI OS scored 30 out of 100 on its first audit, immediately after the onboarding questions were answered, because the four Cs of a bare setup can't get much higher without real usage.
Dated audit reports are stored in their own folder every time the audit skill runs, so score changes become a trackable measure of how the system improves over weeks.
The Karpathy-method LLM wiki has AI crawl a set of documents just to surface the relationships between them, turning separate notes into a linked graph instead of a flat archive.
The most capable model isn't the default choice for daily tasks; a premium model like GPT-6 Astra burns through a shared weekly usage cap faster than a mid-tier model doing the same job, so routine work goes to the cheaper model and the expensive one is saved for harder builds.
Building AGENTS.md, CLAUDE.md, and a synced context folder in parallel keeps the resulting knowledge base usable from any AI tool, avoiding lock-in to one vendor's ecosystem.
Takeaway
Four layers that make an AI actually know you
Second Brain Setup
Building an AI system that actually knows you comes down to four layers, context, connections, capabilities, and cadence, plus a routing file that tells the agent where to look before it answers anything.
02The Four Cs Framework
Context covers information about you and your business that barely changes, quarterly goals, avatar, pain points, so treat it as the stable foundation, not something to update daily.
Connections are the tools that hold your fast-changing data, email, Slack, ClickUp, financial records, and the system should reach into them just in time rather than storing copies.
03Free Skills and AGENTS.md
AGENTS.md for Codex and CLAUDE.md for Claude Code can hold identical content, so writing the routing logic once and copying it across tools avoids re-explaining your business to every new AI product.
A routing map inside that file, which topic lives in which folder, gets read before every single message, so the specificity of that map determines whether the agent finds the right file or guesses.
04Building Your AI OS
Starting from a completely empty local folder and letting onboarding questions build the file structure keeps the system organized from day one instead of retrofitting structure onto a messy pile of notes later.
Pasting in a few samples of your actual writing lets the system learn your voice as a separate reference file, so later output matches how you actually talk instead of generic AI phrasing.
05Connecting Your Everyday Tools
Sorting your daily tools into fixed categories, revenue, customer, calendar, comms, tasks, meetings, knowledge, before connecting anything gives the system a checklist instead of an open-ended integration project.
Asking the AI directly how to connect a given tool, API key, MCP server, or browser automation, is faster than researching integration methods yourself, since it already knows what's available.
06Auditing and Improving Your OS
A brand-new system scored 30 out of 100 on its first audit right after onboarding, which is expected: the score exists to track improvement over time, not to pass a bar on day one.
Every audit run gets stored as a dated report in its own folder, turning system improvement into something you can track week over week instead of a vague feeling of 'it's better now.'
07Building Context With Grill Me
A dedicated interview skill that relentlessly questions you on one topic at a time captures more usable context than a single onboarding pass, because it keeps digging instead of accepting a short answer.
Each interview session gets saved as its own file, so repeated 20-30 minute sessions compound into a much deeper knowledge base instead of overwriting the same document.
08LLM Wikis and Your 3D Brain
A wiki built by having AI crawl your existing documents specifically to find relationships between them turns separate notes into a connected graph, which is what makes retrieval feel intelligent instead of like a keyword search.
Visualizing the whole knowledge base as an interactive 3D graph is a payoff step, and it only produces something meaningful once the wiki-building step has actually linked the underlying notes together.
09Choosing Your AI Model
The most expensive, most capable model isn't the right default for routine tasks like finding a document or drafting a spreadsheet, because it burns through a shared weekly usage limit faster than a mid-tier model doing the same job.
Effort level is a separate lever from model choice; a lighter effort setting trades some capability for speed and cost, worth testing once you're comfortable with how the system behaves.
Glossary
Terms worth knowing.
AGENTS.md
A markdown file inside a Codex project that the agent reads before every message, containing operating rules and a routing map to where information lives in the folder structure. It plays the same role CLAUDE.md plays for Claude Code.
Four Cs
Context, Connections, Capabilities, and Cadence, a four-layer framework for building an AI operating system, where the first two form the knowledge base and the last two form the automation layer.
Karpathy LLM Wiki
A method, credited to Andrej Karpathy, where an AI crawls a set of documents specifically to find and record the relationships between them, turning flat notes into a linked wiki.
Grill Me skill
A Codex skill that interviews the user repeatedly on one topic until it has extracted as much detail as possible, saving each session as its own file to build up personal or business context over time.
3D brain
An interactive 3D visualization of an entire personal knowledge base, generated from the linked wiki, that can be kept local or published as a shareable site.
Effort level
A per-message setting in Codex that trades some model capability for lower cost and faster responses, separate from which model is selected.
18:10toolGPT-6 Astra vs 5.6 Sol / 5.6 Terra (Codex models)
Quotables
Lines you could clip.
00:25
“It feels like I'm talking to a co-founder, someone that actually knows everything that's going on in my life and my business.”
reframes an AI chatbot as a co-founder in one line→ TikTok hook↗ Tweet quote
04:15
“You stop trying to remember business facts. You don't rehearse what you decided last quarter or what your customer said in that meeting because you trust the retrieval.”
concrete, memorable definition of what a working second brain feels like→ newsletter pull-quote↗ Tweet quote
13:10
“Automating some of these little tasks is no problem. The real issue is getting everything from your head into the system.”
reframes the hard part of AI automation as a data problem, not a tooling problem→ IG reel cold open↗ Tweet quote
18:25
“We're not just building a Codex skill or a Codex hub or a little 3D brain. We're building IP.”
punchy reframe of the whole video's premise near the end→ TikTok hook↗ Tweet quote
17:55
“I don't have to worry about being vendor locked because I own all of this stuff right here.”
ties the file-based approach to a concrete ownership benefit→ newsletter pull-quote↗ Tweet quote
The Script
Word for word.
Read-along
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
17px
metaphor
GPT -6 Astra is the most powerful AI model I've ever used, so I turned it into my AI operating system and my second brain. And this is just a quick visual, but right now what you're seeing is my actual company. This is my second brain, this is everything that I know and everything about my business.
And because I have everything actually stored and usable, that means so does GPT -6 Astra. So when I say AIOS, what I mean by that is an AI operating system where now I can basically do anything I need to from right inside of this interface with Codex, with GPT -6 Astra. Because now it doesn't feel like I'm just talking to a chatbot.
It feels like I'm talking to a co -founder, someone that actually knows everything that's going on in my life and my business. So today I'm going to show you guys how you set up an AI operating system from scratch, but if you already have one going, how you can keep improving it. And I'm going to give away a bunch of free skills that help you set up exactly this and help you set up other things like auditing your AIOS, leveling it up, and just setting up the structure right.
Now what you'll notice here is that this isn't just a random dump of knowledge. Right here in blue, this is my business wiki. So it's like AIS coaching, our corporate structure, our AI Automation Society Plus.
And when I click in, we can see all of these things in these different relationships. I can also see how stale this is. So I might need to update it.
And it calls out all these areas where like this number is old. I need to update this. But it also shows me all of the different connections where this specific node.
is linked into every other area of my business. So like I said, that was business wiki. I also have meetings that I've added in here, which takes up a big section.
I've got video knowledge. So every single YouTube video I've made, it has all that knowledge and it relates it back to everything in my business and in my meetings. Same thing with the cloud memory right here, as you can see.
Same thing with codex memory. I've also got a bunch of projects and then I have skills and agents. And this forms together my Herc brain.
And I've even gone as far as to take this exact brain and put it in its own OS dashboard where I can basically have my calendar over here. Today's a Sunday, so I don't have many meetings. And this is fully functional, fully synced with my calendar.
We've got these three stats, YouTube subs, AIS, AIS Plus, and these are fully synced. I can come in here and manage my brain. I can search for different things.
I can look through different things. I also have my communication fully synced. So Slack, click up an email, and these are functional.
I can respond to things from here. I can also see different meetings that I have coming up, as well as past meetings with the AI summaries already generated. And then I can get community pulse.
So top YouTube comments, top AIs plus posts, what people are stuck on, as well as industry pulse from things like YouTube and X. And all of this, of course, was made with GPT -6 Astra. But really the idea of an AI OS or an operating system is my framework that I call the four Cs.
So context, connections, capabilities, and cadence. And the way that I think about this is I think about these first two things as the second brain piece. So I think if this is your second brain, and then over here, we have the actual AIOS and this is the capabilities and the cadence.
So let me real quick explain what I mean by that. What's the actual difference? So the way that you get this thing to actually feel like it knows you is by giving it context.
So I mean things about you and your background and your business and your goals and your priorities and things like that. I think of context as the things that are in your life that really don't change too much. So quarterly goals or yearly goals or what your business does, your avatar, pain points, things like that.
And the connections, I think of things as the tools that you use every day because the data in there is always relevant and it's always changing every day. So your email, different data is always in there. Your conversation, Slack, ClickUp, your project management, your financial information.
Giving your AIOS the ability to know all the context, but also reach for things just in time when it needs it, that's how you build a really, really powerful second brain that helps you actually ask your AIOS questions or say something, and rather than getting a vague or generic response, it knows what to do. So for example, when I asked Codex to make me this AIS sizzle reel, I didn't tell it everything I wanted.
I just said, hey, make me a sizzle reel for AI Automation Society, and it knew all this context, and it also knew that it could go to my school community and look things up in order to make this. In fact, what you'll notice is it actually went so far as to go to the community, take pictures from it, like take screenshots itself and add those in here because it knew that this is what I was talking about.
So I have these three little tests that I like to run, which is basically if a teammate messages you with a question and you realize that your AIOS would answer better and faster with the exact sources, then that's a good sign that your AIOS really is where it should be. Another one is context switching reduction. One thing that you should challenge yourself to do after you've gotten this set up is to try to force yourself to do everything from here.
from this interface. Rather than opening up all those new tabs and doing it the old way, try doing it the new way of using the AI as your operating system. And then number three is the knowledge leaves your head.
So stop trying to remember everything. You don't have to rehearse what you decided last quarter or what your customer said in that meeting because you trust the retrieval of asking your AIOS because it can find it. In your Slack threads, it can find it in your email, find it in your meetings, or it just knows it.
Because if you start to build new skills and capabilities and you start to put cadence into play, which means agents that run autonomously and automations and things like that, these things are not nearly as valuable without the first two Cs. Because otherwise, these skills are very generic and automations are just, like I said, generic.
So these four things really come one after the other, context, connections, capabilities, and cadence, and they all work together very beautifully. And that's how we get. our AI operating system.
So in order to get started or to scale all this up and get all the resources, I need you to go to my free school community. The link for that is down in the description. Like I said, it's completely free and you're going to go to classroom.
You're going to click on all YouTube resources and you're going to grab the AIS OS resource pack. This thing is going to come with five skills. It'll come with an onboard skill to get you set up.
It'll set up your whole project structure, your files, and your folders. Then you'll have an audit skill to do frequent checks on your iOS. You'll have a link skill, which helps you route to different files when you need to.
You'll have a level up, which you can run after your audits that tell you, hey, this is probably some stuff you should do based on this audit. And then you have the 3D brain skill, which helps you turn your knowledge into this actual 3D brain like you guys saw right over here. Now, yes, it is these four things.
And when you start to run that resource pack, it'll onboard you. and ask you questions, and it will start to fill in this information, which is great. But then what comes next is something that's super, super important, and that is called theagents .md.
And so if you've been using Claude, this is basically the Claude .md, but now this is the one that Codex is more familiar with reading, and it's the exact same thing. So if you are coming over from Codex, literally what I would do is I would just copy your Claude .md and then just name it agents .md. It's the exact same thing.
And just to show you guys what mine looks like, if I go into here and I go to my files, you can see that it's very simple. It's you are Nate Herc's AI operating system. Here's your job.
Agents .md and Claude .md contain the same stuff. And then I basically give it a few core operating rules, like to be concise, and I use... bullet points and don't use em dashes and, you know, use the Oxford comma, but then I go into a routing map and that's the majority of my agents .md.
I think of it as, you know, core rules, but then I think of it as routing, meaning can my agent understand where everything lives? Because if I open up my Herc 2 project, which is just like we said, a combination of folders and files, and that's all this is displaying is folders and files and it's showing the relationship between all of that.
But the point I'm trying to make is that this is a lot, right? There's a lot of folders and files and I can go into my projects and there's a lot more in here.
And then I can go into things like, you know, my YouTube videos in here and it's even more. But because all of this is laid out in a way that to me is intuitive, that also means that my agents can crawl it a little bit better. But the more that I have information in here, like routing logic, like, hey, if you need business advice or team stuff or OTAs, you look in the wiki.
If you need corporate structure or entities, you look in this section of the wiki. If you want to look at Nate's voice and style, you look here. If you want to look at course knowledge, you look here.
If you want to to look X, go Y. If you want to look A, go B.
And you can see there's a ton of different rules in here, but what's important is that the agent knows this every single time it loads up so that when you ask for something, it knows where to look. Because that's essentially how the agents .md file works. You know, you say, hi Codex, and before it even will read your message, it reads this first.
So it reads this, and then it reads your message, and then it will respond with like, hey, how can I help you today? You know, that's kind of what it will say. But it always reads this context first, which is why it's so important.
All right, so if you're a complete beginner, how do you actually get set up with all this? Well, let me show you. First thing what you're gonna wanna do is you're gonna wanna go to somewhere on your computer, let's just say it's your desktop, and you're gonna create a new folder.
And so for example, this is where I am using my HERC 2 project, but for now I'm just gonna call this AIS OS demo. So you can call this whatever you want. Now, once that folder has been created locally, which just means on your computer, you're gonna open that up in Codex.
So at this point, if you don't have the Codex desktop app, download that. And then if you aren't on a subscription, just get on a subscription. But now what we're going to do is we need to open up this OS.
So what that means is you would come in here and you would click on new project. You would create a local project and then you would give it a name and then choose this folder. So this is once again going to be AIS demo.
And I'm going to open up that folder if I go to my desktop and I just have to find this folder we just made right here. Select that and then go ahead and click create project. So this now means whenever we are doing things in here, we're working inside of this actual local folder, which if I open this up, there's nothing in here right now.
But you will see as we start this whole onboarding, this folder will fill up. So what I'm going to do is I'm going to go to the resource pack and I'm just going to copy this actual URL. And I will now paste that into the chat and say, hey, I want you to install this and just go ahead and run the onboard so I can start giving you some information and building my AI OS.
So now that this is installed, it's gonna start onboarding you. And you can see that it's gonna say, I will save your answer as you go. So obviously you guys should take some time and give this some pretty specific.
information but i'm just going to blow through this real quick so my name is nate and i run an ai education community and we have a certification program and we have live events and things like that and what's going to happen is it's going to start creating folders and files for you if you click on this button and you go to files you can see that it's already created a bunch of stuff in here none of this was in here if you guys remember this was all completely empty but now it's starting to set up the actual structure but really the two most important things to call out right now are the context folder this is where it's going to start to create some markdown files of business context and also the agents .md i remember i showed you guys mine and this is going to start getting built out over time with you guys right in here then it asks you to paste some of your recent writing so that it can start to build some skills around how you write so what i'm gonna do real quick is just basically fly through these seven questions and then you guys do this as well and then come back all right so now that i've done those seven questions if i open up a new thread i can actually say hi who am i and it will check my profile first
because now it can actually look at all that and understand that. So if I open up the files, once again, we can now see that if I go to my context, we have one called about business, we have one called about me, and we have one called priorities. So if I open this up, you can see that this has information.
If I open this one up, this one has information too. And over time, these will continuously get more filled with context. And this is context, like I said earlier, when I was talking about these four Cs, context that we want to basically be more evergreen, right?
Information that's... not changing very often. Whereas these are more of the connections where you have information that changes very often.
And that's when you're going to start filling it up by looking at things like this. You're going to start looking at what bookmarks do you have? What desktop apps do you have?
What apps do you use the most on the weekly basis? And I like to think about it as far as like revenue, customers, calendar, comms, tasks, meetings, and knowledge. And then once you've taken some time to like list them out here, just say, hey, Codex, I want to connect to school.
How can I do that? I want to connect to Stripe. I want to connect to YouTube.
How can I do that? And it will tell you, oh, you need to get this API key, or you need to use this MCP server, or maybe you need to use browser use. And it will help you figure out the best way to connect to all these tools.
But what else you'll notice is that it's creating the things that we need in case you ever want to go over to Cloud Code, like a .cloud folder, as well as a cloud .md. So it's really helping you make this your own AIOS, your own IP, where you're not locked into one ecosystem. So anyways, I just wanted to call that out.
But the agents .md and the cloud .md file are basically identical. Right now we have like the operating system. We have some skills.
We have where things live. But right now this is pretty empty. So obviously we need to get this filled up a little bit more.
You can also see that in the references section, we have a voice. So if I go to my references and I go to... the voice MD, we can see that this is stuff about how Nate talks based on the information that I've given it so far.
So anyways, now you can see we're starting to get some stuff filled up here. But now what you'll do is once you have connected some things, you're going to go ahead and run the audit. So you can do slash audit.
This will automatically be installed because you use the resource guide. And this basically checks the iOS. It looks at the four Cs, it gives you a score, and it will also look at your agents .md or your clouds .md and make sure everything's synced up, like I said.
And what else is cool about this is this creates another folder in your AIOS called audits. You can see there's nothing here called audits, but what's gonna happen is it's going to give you a report and then it's going to store your audit. So every single time you run this, let's say you wanna run it every Monday or every two weeks, it will store your scores every time so that you can see how you're actually improving your system month over month.
So I know if you're new to Codex and everything, this might feel a little bit intimidating, but it's really not too bad. And the cool thing about this is you can just ask questions. If you ever get confused, hey, why'd you do that?
Or where should I put this? Or how do you feel about all this? You can treat this thing like your best friend who's really smart, who's also a mentor, rather than just like...
a chat bot. Okay. But you can now see that this audit is done.
And obviously we scored a 30 out of a hundred because we literally just built this and there's not much in here, but it'll show you across those four C's what needs improvement. And you can keep working on that stuff. And over here, you can see that we have a new folder called audits.
We have this markdown file, which shows us that today, September 7th, you ran this audit. And here was basically the conclusion of that audit so that you can improve on it. Now, what you can do from there is you can go ahead and run another skill which comes in the kit, which is called a level up.
So this one will basically look at this audit report and then it will help suggest. areas for you to improve it it'll help you think about different connections and different ways that you could you know build in some more capability and build in some more cadence so that this thing keeps growing and keeps growing so here you can see it said i'd start with turning team updates into one clear action list it targets your stated bottleneck coordination taking time away from learning ai and making videos so two candidates here which are team action list and certification improvement backlog so i would then think okay cool so how do we actually start driving towards this.
What do you need to see? What connections do we need to set up? And then how do we build these automations?
And so you can just keep running this loop of auditing, leveling up, building, auditing, leveling up, building. And this is the type of stuff that Astra is so good at because it's so, so smart. It really feels like it's got some really incredible general intelligence, especially as you give it more and more data because it's really good at building automations.
It can one shot a lot of the stuff and it will help you build all these routines. So automating some of these little tasks is no problem. The real issue is getting.
everything from your head into the system. Because the more you give it, the more context you give it, the better it gets, obviously. So yes, it can give you these recommendations, but now what I want you guys to think about is how you can give it more data.
So I do have this other skill here called Grill Me. It was inspired by Matt Pocock's Grill Me. And I will actually put this in the AIS OS kit.
So if you install it based on this video, you'll have this here, but I didn't do it right now. So anyways, then you could use the Grill Me and say, I need you to use this Grill Me skill to just find out. as much as you can about my current priorities in my business.
And what this does is it will basically do similar to the onboard where it asks you questions, but this is a separate skill where it just relentlessly grills you over and over. And what's cool about this is you just keep having it grill you on different topics because every time you start one of these interviews, it will create a new file in your AIS OS and it will store all this interview.
So every single time that you come in here for 20 minutes, 30 minutes, and you just get interviewed by AI, it's going to store all that. So you're just building up your second brain over time. And it's really, really cool.
As you can see, it said, I'm going to. save every answer in business priorities capture it created a new folder right here and now we have this markdown file where as i start to answer these questions it's going to store everything so that's something that i would recommend going through with business priorities your team you know your goals and just like a bunch of different topics about your business and about your life Now, the next thing you need to do, and it's how you actually get something more like this, where you actually have like all of these relationships forming between these different things that you want to put into your AIS OS or into your second brain.
This gets really important because the relationships is what makes this actually connect to everything and what makes it feel more holistic rather than just like a data dump. So the way that you get to this point with all these relationships is we're going to use Karpathy's LLM Wiki. This basically just has AI crawl through data sources and find those connections for you.
So it's really, really cool. And guess what? It's really easy to use because all you have to do is you can either copy this URL, which I'll put in the description of this video, or you could just come in here and you could copy this.
Like you could literally just go like this, copy it, and then come into your actual AI SOS. You can start a new chat and then say. Hey, based on what you currently know about me, I want you to build me a new LLM wiki, and I want you to do so on all my business contacts and everything using this Karpathy wiki method.
And then you can literally just paste in that prompt and boom, it's going to crawl through everything. It's going to create you a new wiki vault. And you can obviously be more specific.
Like I have one vault for my YouTube videos. I have one vault for my business knowledge. I have one vault for my meeting transcripts.
And so I started to separate them out over time. But just to start, you could do, hey, this one's just for business or whatever you need to do, and it will help you find those relationships. And then once you've done a bunch of grill me's, once you've built out these LLM wikis, then you're gonna go in here and you're going to run that 3D brain skill.
And that is the one that's gonna take all your knowledge and it's gonna turn it into something like this. And this obviously will continue to sync and stay optimized and continue to improve for you. And it will probably build that out into something called a local host.
But what's really cool is you could ask it. To turn that into a site, as you can see, Codex basically lets you build things and store it on their domain. So then after you build it, you can have it be accessible to different laptops or to your phone or whatever you want.
Or if you wanted to keep it local, you can do that as well. And if you also wanted to connect your own custom domain, you can do that too. So really the possibilities here are endless.
And it's just about doing that loop, like I said, of constantly scaling up your four Cs and doing that loop of the audit, level up, audit, level up. Now, the last thing I wanted to address was the whole idea of GPT -6 Astra driving everything, right? Because Astra is an incredibly powerful model, but I also wanted to say, so is 5 .6 Sol and so is 5 .6 Terra.
And for the majority of this knowledge work that you're doing here in your iOS, like asking, oh, can you find this doc or can you help me create this spreadsheet? A lot of that using Astra is probably overkill. Like Astra is one of the most.
It is the most capable model that I've ever played with. So what I would recommend is build out some of the stuff, get familiar with how this model works, but then when you start to try to use different skills and when you start to try to connect to different things, I would recommend trying with 5 .6 Sol because Astra is going to crawl through your usage limit, which is the weekly limit.
It's going to eat at that more because it's a more expensive model than 5 .6 Sol is. And once you really start to get comfortable here, you can play with different things too, like the effort level. You can make it go on lights, which reduces some of the capability, but it also makes it cheaper.
And then you could also go to 5 .6 Sol, and you could play with the effort level over here as well. There's a lot of cool things to dig into once you really start to connect a lot of stuff to your Codex system. But once again, I just think it's important to call out that all you're building here is you're building files and folders.
And what's cool about that is as you build out your files and folders, it will grow into something that's just amazing. So now I have my Herc 2, which like I said, has everything in here.
And the cool thing is if I wanted to build a Hermes agent, I can connect that to this. If I go back to Cloud Code, I connect it to this. Whatever is the new tool, whatever is the new AI model, I don't have to worry about switching over.
I don't have to worry about being vendor locked because I own all of this stuff right here. And every agent can crawl through it and use it. And that's really what we're building here.
We're not just building a Codex skill or a Codex hub or a little like 3D brain. We're building IP. We are building a knowledge base that is going to be the most valuable thing because now we can work through it.
because there's so much context and knowledge in here. So I really want you guys to seriously get in there and start doing a bunch of grill me's and just building up your routing and your context. So remember, free school community linked in the description.
You'll find all the resources that you need right in here. But that is gonna do it for this one. If you guys now wanna see, since you have an AIOS set up, how you can control everything with your voice and just delegate out tasks to a bunch of different agents at the same time, just with your voice, then check out this video, which I'll tag right up here.
I hope to see you guys over there. Check it out, it's super cool. And...
I'll see you in the next one. Thanks, everyone.
The Hook
The bait, then the rug-pull.
The video opens on a live 3D map of the creator's own business, every meeting, video, and decision rendered as a connected node, before walking back to show how it was built from an empty folder.
Frameworks
Named ideas worth stealing.
02:21acronym
The Four Cs
Context
Connections
Capabilities
Cadence
Context and connections form the second-brain knowledge base; capabilities and cadence form the AI OS automation layer built on top of it.
Steal forstructuring any personal or team AI knowledge base before adding automations
03:40list
The Three Tests
Teammate reaches out
Context-switching reduction
Knowledge leaves your head
Three checks for whether an AI OS is actually working: it answers a colleague's question better than a person could, it becomes the default surface instead of opening more tabs, and you stop rehearsing facts because you trust its retrieval.
Steal forevaluating whether any internal AI tool is actually being used, not just installed
CTA Breakdown
How they asked for the click.
VERBAL ASK
05:20link
“I need you to go to my free school community... grab the AIS OS resource pack.”
Soft-pitched mid-video right after explaining the four Cs, then repeated as a closing CTA; the ask is a free community join, not a paid product.
Add Modern Creator as a preferred source and Google shows you more of our breakdowns in Search, Top Stories, and AI Overviews. It only changes what you see, and you can undo it in your Google settings anytime.
Add to Preferred SourcesOpens your Google source preferences with us pre-loaded. Tick the box and you're done.
A two-hour gap after Claude Fable 5.1 shipped, a site-wide AI outage, and a blog post that got pulled mid-cycle — the strange week OpenAI introduced GPT-6 Astra.
Nate Herk builds ClientPack, an AI tool that turns discovery-call transcripts into branded client proposal decks, from a blank folder to a live paid subscription in about eight hours of prompting three different AI agents.
A five-prompt AI agent build produced a working Calendly clone with live calendar sync and Stripe payments, then the real bill showed up: five days of agent runtime and about $15,000 in inference.
00:22
00:37
00:52
01:06
01:21
01:36
01:51
02:21
02:50
03:05
03:23
03:35
03:50
04:05
04:20
04:34
05:04
05:19
05:34
05:49
06:04
06:18
06:33
06:48
07:03
07:18
07:48
08:03
08:17
08:32
08:47
09:02
09:17
09:32
09:47
10:01
10:16
10:46
11:01
11:16
11:31
12:00
12:15
12:30
12:45
13:00
13:15
13:30
13:44
13:59
14:29
14:44
14:59
15:14
15:43
15:58
16:13
16:28
16:43
16:58
17:12
17:42
17:57
18:12
18:27
18:42
18:56
19:11
19:41
Video of the Day14:45
05:42
16:13
2:22:51
13:59
20:34