Blog
Measurements from our own repository, with the numbers and the mistakes left in. We do not only write up what worked.
Practice2026-10-15 · 5 min readClaude Code todo list: the day I stopped rebuilding it from memoryA beta plan, a v1 plan, a development plan v0.5, a next-milestone plan v0.1. Then I could no longer see how much was done, what was left, or what contradicted what.2026
- Run a small AI coding productivity study, then audit your own numbers2026-09-26 · 10 min read
- Spec-driven development with Claude Code: check that the spec arrived2026-09-26 · 9 min read
- Running Claude Code agents in parallel: what git stops, and what it doesn't2026-09-06 · 9 min read
- Building a Claude Code handoff, and measuring what it carries2026-09-06 · 8 min read
- Why Claude Code ignores the rules you wrote for it2026-09-06 · 8 min read