Stop Building AI Agents. Use This Folder System Instead.

Hi everyone. In this video, we're going to dive into my concepts around folder as a workspace and architecture, what it means to use AI in a way that will actually probably last the next decade,

and what I think the industry is actually moving towards.

Now, if you've seen any of my other videos, I'm sure you've seen screenshots or snippets of crazy folder structure I'm doing where I'm routing Claude to different folders, my markdown files,

using skills at certain times, creating animations or code with it. I have all sorts of different ways I'm doing it, but I don't think I have a video out there that really dives into how I

structure it and teaching you to do that. And I decided to go ahead and

that. And I decided to go ahead and create a kind of template folder to walk you through all of this. This is

something you could use to be able to apply to any of your workflows, build through it, understand it, and kind of explore, you know, building your own version of this. Now, throughout this

video, I'm actually going to teach some concepts along the way for people who are not familiar with maybe VS Code, which is the workspace I'm working in.

Don't worry, you don't need VS Code to do the things I'm showing you. You can

do it within claude, but I just want to describe like what markdown is, what it means to have an IDE, all of these things. And if you are familiar with

things. And if you are familiar with these, you're a software engineer, you probably are. Don't worry, I'm still

probably are. Don't worry, I'm still going to be diving into the specifics, and I think you're going to get a lot of out of this either way. However,

sometimes it's also nice to just dive back into the fundamentals. So, let me paint a little scene for you. Right now

most people if they are even using AI which fun fact about 84% of the nation is still not fully using it but log in and use claude or chatt or Gemini and

they're typing things they're diving in um maybe they get something back they start another conversation start over and sometimes they're able to share context between conversations right like

chat GPT and claude can do that I can say you know tell me a software stack for Vigilor which is a software that I was working on for another company and it's able to go and look through our older conversations, which is nice.

That's a little bit of extra there, but it's still not, you know, it's not able to look at files, have persistence, things like that, and you're constantly having to make these huge prompts. Maybe

you have some sort of prompts that you save and throw in or documents, and you're throwing it in, and then you have to start a new conversation, throw it in, start a new conversation, you hit a wall, there's too many tokens, right?

All sorts of problems there. And don't

get me wrong, there's some really good prompt engineering techniques out there.

But at the end of the day, AI can only hold so much in a single information or chat area. And even further, that's not

chat area. And even further, that's not your workflow. Having to have it create

your workflow. Having to have it create a whole bunch of stuff and then re-edit it again, it's it's not sustainable.

It's not scalable. Now, for those of you who don't understand why they struggle so much, essentially AI reads everything, all of your sentence, and

measures it by something called tokens.

A token is roughly three quarters of a word or a single word. Sometimes the

word hamburger could be three tokens.

Hamburger. Hamburger. The term comes from NLP research in the '9s. A bunch of researchers needed a unit smaller than a word because language doesn't all break

the same way, right? So, they borrowed token from linguistics, which borrowed it from old English taken, which means a sign or a symbol. A token is just the

smallest meaningful chunk of a sentence or a word. There's only so much tokens an AI can have in its context window before it starts failing. When people

say context window, they mean how many tokens the AI can see at once. And that

window is in fact finite. So if you dump everything into one file, an AI writing a blog post is also reading your video production notes. You're burning tokens

production notes. You're burning tokens on stuff that doesn't matter. So instead

of building one big file, you want to separate your thoughts, your ideas, your work into separate areas. This is

something I created for all of us. It's

called a workspace blueprint. Here you

have three workspaces. And again, this is an example. You don't always have to do this, but each one handles a different kind of work. One for the community, right? Maybe I have this one

community, right? Maybe I have this one for working on content and docs in the community production, right? What am I building? Where are scripts? Maybe I'm

building? Where are scripts? Maybe I'm

creating animations. Writing room, maybe I need to have some sort of process of thinking or I have a client list or insert as many things as I have there.

And we're going to dive deeper into it.

This is a space that does the job well because you can circumn and AI seeing everything and only direct it to what you want. Let me explain how that

you want. Let me explain how that actually works though. So, I'm going to show you inside of VS Code, which is an IDE, basically a developer environment

that allows people to kind of look at folders in a different way. Okay. So,

instead of having to click into the folders like you just saw here, I can just open the folders and see everything and open the files without having to doubleclick the files, right? So,

instead of having to doubleclick this text document and opens another window, I can just bounce between them. It's

much cleaner, much easier. Even if

you're not into code, it looks overwhelming. I promise you, all of this

overwhelming. I promise you, all of this is just natural language. This literally

reads like a document. So, this is a Markdown file. If you haven't seen them

Markdown file. If you haven't seen them before, markdown is just a text file with some lightweight formatting, right?

You have dashes for bullets. You have

hashtags or pound symbols, if everyone else remembers when they were just called that, for headers. Um, you have all sorts of stuff like asterisks for bolding or doing things in that way. And

there's a lot of programs that can actually run this to look a certain way.

In fact, your claude does exactly that.

If you look when you're talking to an AI, it's writing in markdown already.

These boldings, these lines, all of these things. Watch what happens when I

these things. Watch what happens when I copy this. All of that formatting

copy this. All of that formatting disappears when I paste it into here.

And it turns into markdown because that's how it's making it look like that. Markdown is just a good way to

that. Markdown is just a good way to format text. If you're curious, there's

format text. If you're curious, there's a man named John Gruber. He actually

created this in 2004. The whole idea was write something that's readable as plain text but can also render into a formatted document. He named it markdown

formatted document. He named it markdown as a play on markup language which is the same stuff that HTML right the stuff that builds websites uh hypertext

markdown language and all it does is mark stuff down with tags. Markdown

strips all the tags and absurdity away and makes it look like something simple like this. But again, you're probably

like this. But again, you're probably not here for this. you're here for the file system. So let's move on to that

file system. So let's move on to that next step. So in this specific folder,

next step. So in this specific folder, which is an example, it runs on essentially three layers. And there's a reason for each one. If you look at my

clawed MD, my clawed markdown file, this is something that my AI will read every time it's in any one of these folders.

So this is something that the AI will always have and always reads. Imagine

it's you're just copying and pasting this into claude code or into claude every time you open it. Now you can actually just type in to claude read the

claw.md. In this case it's claude code.

claw.md. In this case it's claude code.

You could be working inside of claude co-work as well which is again a video I have on how to install and it can operate inside of folders in case the VS code is too much for you. Um but just

read the cloud imd and tell me what this is. Before you had to copy and paste do

is. Before you had to copy and paste do all these things. it had to read the entire every file that's in here. In

this case, it reads the cloud.md and

immediately without having to read everything else understands the product, the process, what's going on, my writing room, my production, my community. It

knows where to find it, what the file names are, all from just a single text prompt that allows it to understand where to go, what to do, what are these areas. But let me describe this a little

areas. But let me describe this a little simpler for those of you who might, you know, feel like this is a bit overwhelming. Layer one in this is the

overwhelming. Layer one in this is the map. This is what loads automatically,

map. This is what loads automatically, right? It's looking at it. So, you put

right? It's looking at it. So, you put the stuff the agent always needs to think about. Folder structure, naming

think about. Folder structure, naming conventions, where files go. Think of

this as the floor plan. You walk into any room, the floor plan is on the wall, and the agent knows where to go. Now

layer two is where the floor pan tells you to go. It's the actual rooms. What is your task? Go here. I want to write a blog post. Well, then you need to go to

blog post. Well, then you need to go to here and read this context or this markdown file. If you want to build a

markdown file. If you want to build a demo or a video, you need to go here and read this context or markdown file. And

this could be one that you wrote by hand or it could be one that you told Claude to wrote. And we're going to dive into

to wrote. And we're going to dive into that here shortly. Layer three is the actual workspace itself. Where do you want your files going? What content are you doing? If you're writing stuff,

you doing? If you're writing stuff, where do you want the events to be?

Where do you want newsletters to be?

Where do you want social to be? And it's

just a file system. Again, if you don't want to work inside of here, you can actually just go straight into the folder and just create new folders. New

text document. That can be a prompt, that can be a context, right? It's that

simple. And you can just you can just edit it without any of this. Look, my uh my claw.md this is what it looks like in

my claw.md this is what it looks like in if you open up Notepad. Same thing. And

nothing breaks when you edit it. You can

type whatever you want in here. It's

just English. Now, it's good to have it uniform and well, but that's the idea here. Most people are only doing one of

here. Most people are only doing one of these layers, maybe two. The reason you want to actually have these three layers is it stops the narrow funnel of AI

doing too much all at once without allowing you to edit every single part but still give you the ability to automate the entire process. So again,

the router, the initial claw MD or whatever you're naming it is loaded when you start any task. The workspace is loaded when you're in the workspace.

When you want to do production, it's only reading stuff that's in production as it needs to. When you're doing stuff in the writing room, it's only writing it when you're in the writing room. For

example, go to writing room. Let's start

making something. Very little prompting, almost terrible prompting. Yet, the

agent without wasting a whole bunch of tokens and going through everything immediately goes to the context file that I have in writing room that describes what it is. describes what to

load and what not to load and just describes the folder structure and what the process is. First I understand the topic, then I find the angle, then I write it, then I catch problems. You can

also incorporate skills into this, right? So you can download the humanizer

right? So you can download the humanizer skill which is an actual GitHub I recommend you all check out or like doc co-authoring skill which is another set of markdown files or even Python scripts

and tutorials that someone else build to do a certain task. And this is where this whole process is different than just running skills. You're putting

skills inside of a thought process. And

as you can see right here, we're in the writing room. Clean slate, no drafts in

writing room. Clean slate, no drafts in progress. Voice is loaded. Style is blog

progress. Voice is loaded. Style is blog post. What do you want me to make? From

post. What do you want me to make? From

one single prompt, we've gotten it in there. But while that's going on, I can

there. But while that's going on, I can open up another cloud and I can say, "Hey, I want to do some work in production." And it's going to go in

production." And it's going to go in there and I can do whatever work I want to do in production, right? I want to maybe make some designs. I want to create some sort of code for workflows in there. But the real fun happens is

in there. But the real fun happens is when you're building stuff in production with one of your cloud code instances, you're writing a script and you can say,

"Hey, take the script from writing room and let's make an animation out of it in production." It's moving that file. It's

production." It's moving that file. It's

going to go there. Now, it's going to notice that I don't have any scripts in there when I send this out. But if I did have a final in there, it's going to go look for it, right? There's no scripts.

Boom. It didn't waste a whole bunch of tokens. It didn't do anything, but it

tokens. It didn't do anything, but it immediately knew, oh, well, we have to write a script first. Or if you have a script somewhere else, you can upload it. You see, most apps or frameworks or

it. You see, most apps or frameworks or aantic things require you to build an agent for each of these. I need a writing room agent. I need this agent. I

need this agent. But the way in which you approach each task is always different. Why not just have Claude code

different. Why not just have Claude code become the agent you need when you're working in the workspace? And you see from there you get the most important

part of this process is just good routing in English language. Again, this

is all just English, right? File, folder

names, titles. It's describing what you want, right? This right here is the most

want, right? This right here is the most important pattern in the whole system.

It's just a simple table that tells the AI, "For this task, read these files.

Skip those files. You might need these skills." Without this, the AI either

skills." Without this, the AI either reads everything and runs out of the room and just does all sorts of stuff you don't want it to do using way too many tokens, or it guesses wrong about what matters or just doesn't hit what

you need, or you can't edit what it creates along the process. This table

eliminates all of those problems. This this system here gets rid of all of that. Now, let's go ahead and zoom in a

that. Now, let's go ahead and zoom in a little bit here and actually really look at this kind of folder structure. Walk

through this pipeline. Imagine you're

sitting here and you open up production and you go to workflows, right? So, you

know, you're doing some sort of animation production or insert whatever it is that this folder is as a separate workspace as part of a larger task flow

that you're doing. Production has a pipeline in itself as well. Four stages.

You have to do a brief. You need a spec, which a specification, a build, and an output. I have a brief, some sort of

output. I have a brief, some sort of script that I want to do. I have a spec that's generated from that brief, and then it goes into the builds and it builds out the animations. And then

finally, you have the output. More

importantly, this allows me to have one MD file, right? So for my production, I can have a context for this file system that is generating different types of sub aents or ways to look at it. Again,

I'm not even worried about agents. I'm

just worried about what the workspace is, what I want to do in these workspace. If I want to understand, look

workspace. If I want to understand, look up technical standards, look up design rules, I can find that because I might have that in a doc, right? So, I have components or maybe some way I like to

design these systems with my color designs, my headers, my quality. And

again, these are all just generated from English, super short docs. These are

visual philosophy or what type of tech you want to use. And it doesn't always have to read that, but maybe during the brief stage, it does. Right? When you're

sitting there and you're going through and you're loading the brief, well, I need to make sure you look at this text standards when you're making the brief.

If it's loading the spec, I need to make sure it looks at the design system and our component library. And then maybe it does need to load the deck as well. And

you can swap this around super easily just by looking at it. This is

traditional function calling software routing. This has existed for decades

routing. This has existed for decades and decades. But now it gets to be

and decades. But now it gets to be natural language, English. Now, at this point, many of you are like, "Oh, well, you're just making a bunch of skills."

Technically, yes. Now, for those of you who don't know what skills are, again, I mentioned them earlier. I I talked about this idea that you can download them from everywhere. There's PowerPoint

from everywhere. There's PowerPoint skills and I have other um videos on this, but at the end of the day, skills are a process that someone else figured

out and designed a set of packages or folders just like I'm doing here to tell Claude how to do something. Thing is,

skills aren't just markdown files with instructions. Some are just that, but

instructions. Some are just that, but skills work best when they're wired into a system. One important note too is this

a system. One important note too is this is where the difference between it's just skills we're creating here and it's a system. You're actually putting skills

a system. You're actually putting skills inside of your MD. So in this case I have in my context for production I have the fire outlook what I want to do but

also right this is where you can call to call skills or MCP servers. If you don't know what an MCP, it's model context protocol. I think that deserves an

protocol. I think that deserves an entire video in itself, but just think of it as a way that the AI can talk to other apps and services easier. It's

designed to just kind of plug and play it in rather than you have to create all these custom integrations. At certain

points, we might want the front-end design skill or a web app testing skill or a PDF skill. Or I might want to give Claude the opportunity to look up a

skill, find a new skill, or even possibly create one. You can wire up to 15 skills, 20 skills, 100 skills into a

workspace, or you can perfectly add the skills where you would need them inside the workspace rather than having them loaded at all times. That's the whole

idea here is about plugandplay and routing. One other sneaky thing I do to

routing. One other sneaky thing I do to like completely ignore like databases or anything like that in my claude MD the main file at the beginning that shows you know every AI or every agent that

comes into this workspace can see my entire folder structure and navigation I just add naming conventions right so if a file is going to be outputed a certain

way it needs to name it for blog drafts it needs to be like file name where it's at is it draft is it v2 is it v3 example API off guide draft, right? Or same for

newsletters. Here's the year and day and

newsletters. Here's the year and day and then here's what it's kind of is, right?

2026 03 launch week MD. So the AI knows to organize and move stuff which comes in handy when instead of having to navigate through these files or have an agent that's connected to some sort of

you know SQL database or vector database or query or Postgress or anything like that. I could just say hey pull

that. I could just say hey pull my uh O demo demo v2 and build a spec from it. It

immediately knows without me doing anything to look where that v2 demo script would be because it knows how to find it. It knows to pull it. Then it

find it. It knows to pull it. Then it

knows to read the docs associated with specs and then start building it. I have

zero code technically speaking running any sort of Python injection or framework or database. This is tools that people are building right now.

They're building apps and crazy Python stuff which in some very bespoke cases might be useful but most of the time for most people you don't need all that extra stuff to get the process and the

job done. The job to be done is more

job done. The job to be done is more important than this kind of rigid architecture that so many people are building. You see the folder becomes

building. You see the folder becomes your app. This is your UI. What's

your app. This is your UI. What's

simpler UI than a folder? And the best part is I don't even need to technically click on anything. I could just talk with my voice to AI, have it do all the text work for me. The next stage of

this, I promise you, within six months, everyone's going to be doing this, is just talking to your folder setup. It's

going to be designed and set up to be this way. It's going to be around yours,

this way. It's going to be around yours, which leads into a good final point. How

do you make this yours? This template

uses a fake idea with fake process, right? Fake blog posts and demos. If

right? Fake blog posts and demos. If

you're a content creator, writing room might become your script lab. Production

becomes your edit bay. Uh whatever

community becomes a distribution hub.

And you're going to remove and change these rules to edit your platform. Maybe

your tone and voice inside of these, right? So what is your audience? That's

right? So what is your audience? That's

what you want to hear. It's working

developers, two to eight years of experience, technical decision makers, developer advocates. It might be

developer advocates. It might be something completely different. You

might be in construction or real estate, but this is roughly what you would be doing across all of them. And the best part is all you need is one subscription

to Claude Code and you can generate a hundred quote unquote apps that are just folders creating what you need.

Obviously, it's much more complicated once you get into breaking down your workflow. But if you're a developer, if

workflow. But if you're a developer, if you're a freelancer, right, just swap design for engineering and docs or intake and production and delivery,

right? This workspace changes lightly.

right? This workspace changes lightly.

But the three layer routing system, the idea that you go from, hey, look at this area. This is what you're going to to

area. This is what you're going to to lower level context ones to lower level skills is the idea here. It's just

layered. This isn't a prompt trick. This

isn't some sort of crazy infrastructure.

It's folders and markdown files with the understanding of advanced software engineering. Every conversation after

engineering. Every conversation after that, the AI knows where it is, what to load, what tools to use, and where to put the work in. Now, there is a lot of history behind my thinking. I didn't

just randomly come up with this. And

there's a lot of people who are already doing this. And the reason they're doing

doing this. And the reason they're doing this is because it works. I'm writing a very large research paper right now that goes into the history of programming, rules of transparency, rules of

composition, um, all the way back down to 1972 and then I'm bringing it forward and applying all this stuff to modernday AI, what it means to have humans in it.

And I specifically talk about the layers that we could actually have. And I

actually go into a five layer architecture in the paper, but realistically, most of you just need to understand the three main layers that we talked about here. I will be making videos on this. However, it is in the

main chat. Um, if you want to download

main chat. Um, if you want to download this and give it to Claude so that it can tell you about it rather than having to read through it, I highly recommend that. In fact, I urge you to do it

that. In fact, I urge you to do it because some of this is kind of technical information. I'm being nerdy.

technical information. I'm being nerdy.

I'm being structured in it. But this is layering out what the next decade is looking like. And this isn't because I'm

looking like. And this isn't because I'm predicting the future. It's because I'm learning from the past, from the last 200 years of software engineering. And I

mean 200 when I say that and applying it to AI. I want to teach the concepts that

to AI. I want to teach the concepts that last, not the concepts that are replaced next month. I understand that some of

next month. I understand that some of this might be in a little fast. It might

be a little confusing. I'll keep making deeper dives. Give me feedback on what

deeper dives. Give me feedback on what you didn't understand. How did I move too fast? I want to make these better

too fast? I want to make these better every day. Again, I'm making these on my

every day. Again, I'm making these on my own. So hopefully this all gave you a

own. So hopefully this all gave you a good idea. If you do want access to any

good idea. If you do want access to any of these files or worker templates, um I am giving them already to my VIP and my uh premium accounts. It's my one way of

like the work, right, to be able to support this. So, if you're able to

support this. So, if you're able to subscribe, amazing. If it actually is

subscribe, amazing. If it actually is that much of a financial challenge, please reach out to me. I can try to see if I can get you something, you know, quick and easy for you. Um but at the end of the day, go go check it out. Go

check out all my other courses that I'll be doing. And again, as always, happy

be doing. And again, as always, happy learning.