Architectural governance, in writing.

The homepage teaches the category in six cards. These essays are the long form: why architecture trapped in markdown cannot be checked, and why reading the tree still cannot find what was never written down. Back to the story.

A million-line source tree versus a change-scoped architecture graph.

An agent that reads faster still can't find what was never written down.

Reading code does not scale. Neither does delegating it.

Read the post →
A CLAUDE.md file of architectural prose versus an architecture.calm.json graph.

Get the Architecture Out of Your .md Files

AI agents need an architecture model, not more markdown.

Read the post →