Writing.

Specifics, not abstractions. I write about the work I'm actually doing: modifying open-source agent-orchestration tooling, building on-prem AI governance, tracking the structural shifts in per-seat pricing for dev tools. Every piece also goes out on Substack. The canonical version lives here. I use AI to help me write every post and each is anchored to my actual usage data or commit history.

Substack → RSS →

/ 01
posts

2026-05-27

Introducing wood-fired-tasks

Coordination infrastructure for fleets of AI coding agents — the missing primitive between one Claude Code session and ten of them working the same backlog without stepping on each other. MIT, on npm, self-hostable. Here's the origin story, the design, and how I run it.

release
17 min

2026-05-20

From workstation buildout to AI in the loop

Two and a half years of AI practice, told in three acts. The story of how I went from asking a chat assistant inside Rider for help with build errors to running an orchestration layer that ships work I could not have written alone — and the measurable output curve that confirms the compound.

MECS
21 min

2026-05-13

From engine to platform

The October 2023 prototyping contract that finally moved MECS from an in-process model of authoritative-server multiplayer to a real UDP wire, the 2024 backend stand-up that grew up around the engine, and the five-layer architecture that turned the simulation and the services around it into one codebase.

MECS
28 min

2026-05-06

Six years of an engine

MECS is six years old. The thinking that produced it is twenty-three. This is the origin story — from peer-to-peer lockstep RTS networking in 2003, through the Dropzone ECS engine in the mid-2010s, into the educational-MMO project that made the case for a new engine, to the thesis I wrote down in late 2020 that became MECS.

MECS
31 min

Cadence: target one post per week sustained. Posts cross-publish to Substack; the version here is canonical. Subscribe by email →