Hey everyone! I finally have a folder structure that keeps me organized and gets me faster, better outputs from my agents. Quick tour of how I set it up. I have one root where my AI OS lives. It's also where my personal stuff lives and where my AI work lives. I plan to be in many different projects and businesses over time, and this root is where each of them gets its own home. One brain, many workspaces. The AI OS itself is just folders Claude Code reads like a runbook: context/ tells it who I am, my business, my priorities. references/ holds my frameworks, my voice, and how each connected tool works. connections.md lists every system the OS can actually reach. projects/ is where the real builds live (my LinkedIn feed assistant is in here). .claude/skills/ is my growing library of custom skills, one job each. decisions/ logs what I chose and why, so I never re-litigate it. Then there's a separate space I call Akshu Mind. My second brain. This is the part I'm most happy with. It has a raw/ folder where I drop sources untouched. Whitepapers, transcripts, notes. I never edit those. Then the agent reads each one and synthesizes it into clean, linked pages. So the messy input stays in one place, and the distilled knowledge that actually feeds my builds stays in another. The OS and the second brain reference each other, but neither clutters the other. The whole thing runs on Nate Herk's 3Ms (Mindset, Method, Machine) and the AIS-OS kit he put together. Still figuring out where heavier retrieval like RAG fits, or whether agent skills make most of it unnecessary. Huge thanks to Nate for making such great resources free.

When I started the AI Automation Society, I had no idea it would grow into this. Under two years later and we just crossed 400k. The largest AI automation community in the world. Yes, the space is exploding. But this community grew because you guys keep showing up, asking questions, dropping answers, sharing builds, and helping the person one step behind you. Huge thank you to the team that keeps this thing running, and to every single one of you who's posted, commented, or just been here. I feel lucky to get to do this. So excited to share with you guys what we've been quietly cooking up over here at AIS...👀 - Nate

The video you just watched made itself. I gave Claude Fable 5 one prompt inside Claude Code, walked away, and came back to a finished video I never filmed, edited, or even watched while it was being built. In this one I show you what Anthropic's new Mythos-class model can actually do, then break down exactly how it wrote the script, cloned my voice, rendered the avatar, built every motion graphic, and edited the whole thing on its own.

I schedule / routine code review. to review commit done in last 24 hours with suggestion, what to do next.

Just completed the day 5 of AIS Challenge. Screenshot loop, that i also used in my workflow of own idea. that look really interesting to build.