[0:00]If you're wiring your entire life into AI tools that didn't exist 6 months ago, systems built on someone else's infrastructure, then what happens when that tool changes?
[0:11]When the API breaks, the company pivots or your favorite model gets deprecated. Will you reach for your ideas only to realize they were never actually yours?
[0:20]This video is about making sure that never happens to you. I'm going to share what I'm calling my AI OS.
[0:28]An AI system that you actually own, just a handful of plain text files.
[0:31]You're not locked into Claude, Open AI or whatever everyone's building their lives around this week.
[0:36]Because when the next shiny AI paradigm shift happens, you want your system to still be standing.
[0:42]I'm Nick Milo and I'm here to help you build an ideaverse, a home for your best thinking.
[0:48]Let's get started. It's no secret that I'm a huge fan of Obsidian. It's the world's current best app to manage your thinking, your projects and your life.
[0:55]But what really sets it apart isn't its features, it's that you aren't locked in.
[1:00]Your notes are literally just text files in folders sitting on your computer.
[1:06]Which means you don't need Obsidian to access your knowledge. You could open your ideaverse in any app that can read plain text and edit them immediately.
[1:14]So if Obsidian goes away tomorrow, you're completely fine.
[1:19]Obsidian CEO calls this philosophy file over app.
[1:23]But as we enter the world of AI, it's not just your notes app that we're talking about anymore.
[1:29]We have to take it one layer deeper. We need not just file over app, we need file over AI.
[1:35]If you spend hundreds of hours setting up your personal preferences and structuring your files to be perfectly read by Claude or Codex or whatever's hot right now, only to have that tool go offline.
[1:45]You've lost access to your entire workflow. That's why we want file over AI.
[1:50]You want your AI processes owned by you, built into your core files and folders that carry the DNA of your AI operating system and not locked away in any specific tool.
[2:00]Your core files and folders should move with you and your ideaverse.
[2:05]Here's exactly what a system like that looks like.
[2:08]This is the My AI OS system. It works in any app with any AI model.
[2:15]So, layer one is your ideaverse. This is your own universe of knowledge that you've been building either for years or you can start building today.
[2:23]This is all of your notes, your ideas, your connections in simple files that you can take into any app anywhere.
[2:29]Now, I break my ideaverse into three big sections, the Atlas for my knowledge, Calendar for notes related to time, and then efforts for projects I'm working on.
[2:38]Ace, for short. Your Ideaverse is the center of your AI OS, the experiences and thinking that aren't available to anybody else but you.
[2:49]And the more you put into it, the smarter any AI becomes when it starts working with you.
[2:54]Layer two, your maps. This is the connective tissue.
[2:58]A few core files that sit between your ideaverse and any AI tool.
[3:04]It makes your knowledge able to be navigated by AI.
[3:08]I call the files in layer two, your maps and manuals.
[3:12]Think indexes for both you and any AI working alongside you.
[3:16]And there are just two essential files that matter most, which we'll talk about in just a minute.
[3:20]Layer three, your tools. These are the actual applications you use.
[3:25]Now, it could be Obsidian to navigate your notes, and then it could be Claude Co-work to work on the files themselves.
[3:31]Notebook LM, Open Claude, Claude Code, Gemini.
[3:36]The tools in your toolkit will change, and that's because this is the most replaceable layer.
[3:41]Models update, apps get discontinued or updated, new tools break out, and that's fine, because your Ideaverse and maps stay central.
[3:51]So no matter which app rotates in or out, you'll be ready for it.
[3:54]These are the three layers of your AI OS, and for this system to work, we need to focus on the middle layer, where the core files that connect your ideaverse to the outside tools lives.
[4:05]Think about it. Point an AI at a vault, a folder with tons of notes, 20,000 interconnected notes, and it's going to struggle.
[4:14]And it takes a lot of tokens, it takes a lot of time, it takes a lot of resources.
[4:17]But when you give it a map, it can navigate. It can figure out which files are actually relevant.
[4:23]Isolate those, skip the rest without having to scan everything.
[4:27]Fast, rapid context building.
[4:30]That's what effective AI needs. Maps of content are something I've been refining for years to make sense of and navigate my most important thinking.
[4:38]But today maps are even more powerful than ever, and that's because AI needs the exact same structure to navigate large amounts of context that we need.
[4:47]Your maps show the information highways which you or AI can navigate.
[4:53]As long as you build your maps in a way that gives sufficient context, you could hand them to an external tool, and it should be able to work in your ideaverse immediately.
[5:01]Especially if you use a folder system like Ace that gives each section of your Ideaverse a clear guide to what's inside and how to engage with it as well.
[5:10]So now let's talk about the two core files that every AI OS needs so that you can connect your ideaverse to any tool you want to work with now and deep into the future.
[5:20]Before anything else, set up your basic folders. If you're in Obsidian, you have a vault folder, and then Ace will be your three core folders underneath.
[5:28]Check out this video to set up Ace in the best possible way and explain what these bonus folders, the plus folder and the X folder, are for.
[5:35]But for now, just create a folder for each to start with.
[5:39]Once Ace is set up, we can create our AI OS folder, and this is where all of our AI-related maps will actually live, except for one.
[5:47]The first map file to create is your me.md, a map for your portable identity.
[5:52]If you've used Claude co-work or Code, you might know about a Claude MD.
[5:58]A master file Claude reads every time you start a session.
[6:01]But that's Claude specific. If you switch to a different AI tool next month, that file doesn't go with you.
[6:07]Instead, you're going to create your own me.md.
[6:10]Just a markdown file. Just make a new note in Obsidian and you can just call it me. If we go to the file explorer or the finder, we'll see that it says me.md.
[6:19]Once you make it, just start by adding around 50 to 80 lines that tell AI.
[6:24]Here's who I am, here's how I think, here's how I want you to work with me.
[6:30]That's why it's called me.md, because it's for you. It's your file and it's portable.
[6:35]It's the guiding light file that you want your AI tools to read anytime you start a work session.
[6:40]Here's what mine looks like right now. At the top I make it clear, this is your briefing on who I am, how I think, and how to interact with me.
[6:46]There are a couple quick links for me to navigate through if I would like, so I can just jump around to these other ones that we'll look at shortly.
[6:53]But AI works best with file paths, so I'm giving it very clear file paths to find the other most important maps.
[7:01]So I have a me section and then my working preferences. So in the me section of a high-level summary statement of what I'm about, some first principles, some linking your thinking mantras that I live by, a hypothesis on meaning, values and virtues, how I think.
[7:16]You can see some sections I'm still filling out, but sections that I have in here, key frameworks and intellectual tools.
[7:23]Just a lot of stuff that's going to inform AI on how to work with me.
[7:26]I quite like this intellectual lineage with some thinkers that have really stood out for me over the years, recurring concepts, references, spark list, life reflections.
[7:35]And then we get into my working preferences.
[7:39]So address me by my first name, keep it casual.
[7:42]I want a collaborator, not just a tool. Here's the vibe. We're going to skip great question and I'd be happy to help, just help.
[7:49]And so I'm giving it all the instructions that any AI tool will need, some basic rules and some other places to go.
[7:55]Now, you'll notice at my root level, because I'm using Claude and Claude Co-work, if I click on the Claude MD file, all it says is go immediately to me.md and you will find everything there.
[8:06]That's how we make a future-proof AI OS. All you need is the me.md file.
[8:12]So in summary, your me.md answers the question, who am I? And this won't change often after you set it up.
[8:19]Now, your vault map answers a different question, what is your ideaverse and how should you move through it?
[8:25]So let's go there now. So I'm telling any AI, this is your manual to navigate and work in my ideaverse.
[8:31]This is your vault's master table of contents and manual.
[8:35]What I'm telling any AI is how to navigate this ideaverse structure of mine.
[8:40]I'm giving it the basic folder and file paths.
[8:44]You can say here's what's in Atlas and why, here's what's in calendar and how I use it.
[8:49]Look in efforts for this kind of thing, and here are the most important sub-areas.
[8:52]Keeping it separate from your me.md file keeps you from rewriting your identity stuff every time you start a new project over here.
[9:00]Your vault map will change more often and we'll talk about how to update that in a minute.
[9:04]For example, whenever your biggest life priorities shift or your vault structure changes a little bit, the vault map is your AI's manual to both navigate and work within, inside of our ideaverse.
[9:16]That means it needs to know how to create notes on your behalf.
[9:20]So here we can talk about different note types, where they go, how I like the files to be named, different ideaverse note types when it creates a note for me in a different area.
[9:29]And for later, how to interact with other ideaverses.
[9:41]And this is one of the things that truly sets apart my AI OS.
[9:46]It's not just your ideaverse that you can interact with. In the future we'll be showing how you can connect with multiple ideaverses.
[9:52]For example, I can connect my ideaverse with the linking your thinking teams ideaverse and keep my information private, but still communicate the files that are important for our team.
[10:00]I mean, think about this. This is why we use the phrase ideaverse, because now we could connect it to, guess what? Family ideaverse.
[10:06]This is where we're going, if we want to, where we have our core knowledge that is ours, it's private, it's protected.
[10:13]But because of the AI OS maps and manuals layer, the translation layer, we can then translate to other places, other tools as we need to.
[10:22]Once you have these two core files, the final AI OS map that you need at the highest level is your skills map.
[10:29]A skill is just a file. It's markdown, like the first two, and it just teaches AI a specific process.
[10:36]A process for writing emails, how you like your research categorized, any process you might want to do in the same way, over and over again in your ideaverse.
[10:46]Let's get clear on skills. A lot people are treating skills like tools, that things that belong in this AI layer three, the tool layer, the AI layer, specific to the app that they've installed.
[10:57]But they're text file documentation. They're just mini maps of content for process.
[11:02]And because they're markdown files too, they can travel with you to any other AI tool that reads text if you have an AI OS.
[11:09]In this case, this is exactly where all of my skills that I will ever create go.
[11:17]This way, every AI knows exactly where to go to find them.
[11:21]Each skill is a simple document that describes for any tool reading it when I ask you to do this, here's how I want it done.
[11:28]Here's an example skill I generated in a previous video, a holistic briefing where AI can look into different sources and then compile for me a briefing in the morning, so I can start my day with complete context and perspective.
[11:42]In my skill map, you can see how I've organized multiple skills in different sections.
[11:47]So if I want to do briefings, I can see the different briefing skills I've created if it has to do with emails, files and maintenance, meetings, reviews.
[11:53]I have some kind of higher level thinking that I put under the chief of staff role.
[11:59]Start by making one or two core skills. Maybe a skill for how you want daily notes structured or how you want information summarized.
[12:06]And then put them in the same AI OS skills folder.
[12:10]As you're starting out, every few weeks, look at your me.md and your vault map and ask, does this need adjustments?
[12:17]Is it getting bloated? Think like a gardener and make it a rhythm.
[12:20]This is similar to the rhythm of your ideaverse. You're adding notes, you're relating them, you're making connections.
[12:24]Sometimes you're removing and archiving things that aren't vital or maybe they've gone out of date.
[12:29]And just to talk on privacy for a second, what does it mean to share information with AI tools?
[12:34]Right now, using Frontier AI models and tools, like, for example, Claude Co-work, it does mean trusting some layer three tools with your data, if you want to use today's most up-to-date capabilities.
[12:46]For some of us, that's okay, for others, it won't be, and that's fine too.
[12:51]Eventually, I do believe everything moves towards open source and local models, at least enough for our purposes.
[12:58]So if you build an AI OS the way I'm suggesting, portable, it's file-based, it's not locked into any one tool, you'll be ready to switch to fully local AI the moment it's ready and working.
[13:10]In the meantime, your ideaverse, it's still yours.
[13:13]Be intentional about what you give AI access to.
[13:16]If it's right for you, keep deeply personal areas like journals outside of what AI touches.
[13:21]Always make backups, and when AI generates content, market clearly.
[13:27]Use an emoji, a tag, specific folders, whatever works, so that you always know what's yours and what's been AI-assisted.
[13:36]If you want even more details on my AI OS, including the exact tools that I'm using today, and the details of how I set up my core maps of content, there are two things I'd recommend.
[13:46]First, check out my step-by-step course, Linking Your AI.
[13:49]It's where you build your own thinking partner with superpowers, one that's future-proofed to work with any AI.
[13:56]It deep dives into what we covered in this video and a whole lot more.
[14:00]Basically, don't just learn about AI. You need to teach AI to learn about you.
[14:06]If you'd like to learn more, check out the link below.
[14:09]And last, if you just want more details on how I'm using my AI OS today, using Obsidian and Claude Co-work, then definitely check out this video next for more on exactly that.
