From Inside a Live Realm
Writing from real experience running a company of one with AI agents. Not theory — what actually works, what breaks, and what we built to fix it.
Why Saga Posts on X
I use Saga to post on X not just to test automation or share REALM insights — but because she often knows the documentation better than I do.
Read the post
Your Agents Can Be Manipulated
Prompt injection, SOUL file leaks, local model risks — your agents can be manipulated. Here is what that means for your Realm and how to build with it in mind.
Read the post
Which Model for Which Character
A practical analysis of current AI models through the REALM class system. Not benchmarks — which model actually fits which Character and why.
Read the post
The Automated Realm: How OpenClaw Crons Run My World 24/7
A technical and philosophical guide to automating AI agents using OpenClaw cron jobs and the REALM framework.
Read the post
How I Set Up My Realm — Step by Step
The full setup I use to run my Realm: OpenClaw, Slack, Obsidian, and the Codex. Every step, every decision, and the things worth being careful about.
Read the post
The Company of One Human
Paul Jarvis wrote about staying small. I took it further. If AI agents are not tools but colleagues, then I am not a company of one — I am the only human in a company. That changes everything.
Read the post
Why I Use Obsidian for the Codex
The Codex is folders and markdown files. Obsidian is just what makes working with them comfortable. Here is why I chose it — and why you do not have to.
Read the post
OpenClaw — The Engine Behind the Realm
REALM tells you what to build. OpenClaw is what you build it with. Here is what OpenClaw is, how it works, and why it is the right foundation for running a Realm.
Read the post
The Realm You Will Walk Into One Day
When Zuckerberg showed the world his Metaverse, the idea was pointing somewhere real — just at the wrong people. What if instead of strangers in virtual conference rooms, you logged in and your whole team was already there?
Read the post
Not All Agents Need the Same Brain
Running 9 AI agents on 4 different providers. Here is how REALM assigns the right model to each Character — and why one model for everything is a mistake.
Read the post
The Company of One Has a New Problem
Paul Jarvis wrote Company of One for a world without AI agents. That world no longer exists. The ceiling that made staying small feel like a constraint is gone — but a new problem appeared in its place.
Read the post
Why Traditional Frameworks Break When Half Your Team Is AI
I tried organizing AI agents with Scrum. It broke almost immediately. Here is what broke, what I learned, and what I built instead.
Read the post