Most AI OS builds I see start with automations. Mine started with a knowledge base, and that order turned out to be the whole game. What I actually run: a plain markdown vault, no database, connected by links, with a team of named specialist agents. An orchestrator that routes, a researcher, a journal writer, a data analyst, and a few more. I drive it from Claude Code, Codex and Telegram, and it holds the real context for operations at my company. Three things I would tell anyone building one: 1. Build the brain before the hands. A capture habit that turns every input into linked notes beats a pile of clever automations that have no context to act on. 2. One fact, one file. The day the same fact lives in three places, your agent gives you three different answers. Link, do not copy. 3. Stay host-portable. I can open the same vault in Claude Code, Codex or a chat-only LLM. No lock-in means no single tool can ever strand my system. The trap I see most: handing agents real keys before the context is good enough to trust them. Build the knowledge first, hand over autonomy slowly. Curious what everyone else runs. What is the one piece of your AI OS you would not give up?

Let's get to know each other! Comment below sharing where you are in the world, a career goal you have, and something you like to do for fun. 😊

Here’s a small insight from my side. I noticed that I was still doing a lot of my work in separate projects, loose chats and separate documents. For example, for one new project I had already created quite a lot of documentation. Until now, I would usually work on that in ChatGPT Canvas, then move parts into Google Drive, update separate docs manually and keep switching between different places to keep everything aligned. But I’ve now started moving completely into VS Code and building a simple AIOS there. Even without going through Nate’s lessons yet, this already feels like a massive productivity shift. The biggest difference is that everything lives in one place. When something changes, I can update one part of the system and then let AI help me apply that change across all the relevant documentation, prompts, workflows and files. That sounds small, but in practice it removes so much friction. Less switching, less copying things around, less “where did I put that again?", less rewriting the same context over and over. It feels much closer to actually building a working system instead of managing a collection of loose documents and projects. Can;t wait to have the full AIOS setup with a personal wiki of all my knowledge from the past 14 years of creating courses, masterclasses, seminars, etc. Curious to hear from people who are already further with this: What is one skill, workflow or habit that has made the biggest difference for you when working this way, and that you would recommend building as early as possible?🔥

Hey everyone! So I am almost done with the video tutorial for the AI OS and ngl it answered so many questions in my head! I have already onboarded so from now on I am gonna be focusing on improving it's capabilities. As I am not a business owner (yet!) I have almost zero context, no clients, no SOPs, absolutely nothing but I decided to set it up anyway and use it like my right hand for building future business operations. I know where I need to start - automate my content creation to start filling up my socials for the future client outreach, but I was curious what's next? I'd be happy to hear about skills or workflows you guys did inside your own AI-OS! Gotta get some inspiration here! Thanks!

New here? 👋 Me too...navigating the Skool gate. Since we're both unlocking value: What's the one personal AI automation you've built that you use daily? Any unique workflows that you can't live without? Drop them below🔻