The blog

Writing from the workbench.

Notes on AI agents, software, infrastructure, and things I’ve learned by building and debugging them.

  1. What Does It Actually Mean for an Agent to Learn?

    I dug into the Hermes agent's self-learning claims at the code level. What I found clarified what's possible, what's marketing, and what the real frontier looks like.

  2. The Telegram Session Routing Bug That Had My Agent Arguing With Itself

    Group chats, DMs, and heartbeats all create separate sessions inside the same agent. When you don't know that, things break in confusing ways.

  3. How My AI Agent and Claude Code Collaborate

    My OpenClaw agent launches Claude Code sessions, answers most of its questions autonomously, and only taps me when it needs my judgment. Here's how the whole system works — the SDK, the wake mechanism, and why I had to teach my agent to stop micromanaging.

  4. How I Got My AI Agent to Stop Doing Busy Work and Start Building

    A single commit to my agent's instruction files turned it from a process-document generator into a machine that ships real work. Here's what I changed and why it worked.

  5. Multi-Agent Architecture: One Gateway, Three Businesses

    How I split a single overwhelmed AI agent into three focused agents — each running its own business — on one Raspberry Pi.

  6. Beads: Structured Task Execution for AI Agents

    Why I built a dependency-aware issue tracker for my personal agents, and how it closed the loop between planning and shipped outcomes.

  7. How I Use Obsidian + OpenClaw as a Cross-Platform Personal Operating System

    A practical workflow for turning notes into shipped outcomes across phone, laptop, and Raspberry Pi using Obsidian and OpenClaw.

  8. My Raspberry Pi Became My Life Ops Server

    How a Raspberry Pi, Tailscale, Claude Code, and OpenClaw turned into a private 24/7 execution engine for work and life admin.

  9. The Files That Train Your Agent

    How editing OpenClaw's default workspace markdown files changed agent behavior, improved proactivity, and cut token waste in real usage.

  10. The AI Wealth Divide

    How access to high-tier AI models is creating a new economic and cognitive gradient.

  11. When My AI Agent Diagnosed Its Own Crash — And Fixed It

    A deep dive into how I investigated a system freeze, traced it to memory thrashing, and built a multi-layer defense system.

  12. Why Ambitious People Stay Mediocre — Lessons from Alex Hormozi

    Why ambition alone often produces mediocre outcomes — practical steps to convert ambition into focused action and measurable progress.