Topic
Knowledge management
MyVault: a written record of what a team has already learned about working with AI, applied automatically in every session instead of relearned by the next person. These pieces are the method — what makes a vault different from a README, how it audits itself, and what a single saved lesson looks like in practice.
-
Sep 11, 2026 Note For companies
Fast food architecture
AI is a very good drafter and a poor architect. Treating its output as finished engineering is like living on fast food: it works today and costs you later. The fix is a place the reasoning lives that the model can read back.
-
Sep 6, 2026 MyVault For both
The learning loop
How to take what you learn about working with AI and make it repeatable, automatically applied, and continually improved. The method behind everything else on this site.
-
Sep 5, 2026 MyVault For both
The lesson that saved itself
A short story about one note in the vault. Learned from a failing test, written the same afternoon, applied automatically on every project since. This is what "repeatable" looks like in practice.
-
Sep 5, 2026 MyVault For both
Make the vault garden itself
A knowledge base that nobody audits becomes a junk drawer within a quarter. How the vault checks its own links, flags weak entries, and forces contradictions to be resolved rather than accumulated.
-
Sep 5, 2026 MyVault For both
Ten notes every team should have in its vault
The first ten things to write down when you start a knowledge vault for AI-assisted work. Each one is a lesson your team has already learned and will otherwise relearn.
-
Sep 5, 2026 MyVault For both
What a knowledge vault does that a README does not
Giving an AI coding agent a place to read from and save to across sessions and projects, and the conventions that stop it becoming a junk drawer.