New essay: Stop paying your best model to type
A new piece is up on the site. I drained a hundred-task prototype under three model policies and priced every task against my own telemetry. Routing a...
You can't ask an agent to log itself
No vendor sells a per-developer view of what your AI agents cost across vendors, so I built one. A coding agent will not log itself, so the capture path sits...
How I stopped reading the code
I stopped reading AI-written code line by line and replaced review with overlapping systems that grade each other: tests, pre-action hooks, CI gates,...
Stop talking to your agents
The most reliable way to make an AI coding agent follow an unusual rule is not a better prompt; it is making the violation a compile error. Prompts nudge a...
Introducing wood-fired-tasks
wood-fired-tasks is the coordination layer I built so a fleet of AI coding agents can drain one shared backlog in parallel without colliding. It is a self-...
From workstation buildout to AI in the loop
Over two and a half years my AI practice moved through three stages: an advisor that compressed my learning curve while I wrote every line, a collaborator...
From engine to platform
To turn a game engine into a multiplayer platform, I validated the authoritative-server architecture for years inside a single process — two MECS services...
Six years of an engine
I built MECS, a custom C# Entity Component System engine, because I needed one codebase to run the same deterministic simulation on a Unity client and a .NET...
