← All Articles

Recommend A, implement A: behavioral contracts for AI collaborators

My AI assistant argued for prevention, then implemented detection. Behavioral contracts in CLAUDE.md turn recommend-A-implement-B drift into a review comment.

· 8 min read

Context Loss and How to Prevent It

Why AI assistants forget what you told them, and practical strategies to prevent it. The difference between context that survives and context that gets lost.

· 5 min read

How Claude's Memory Actually Works (And Why CLAUDE.md Matters)

Understanding Claude's context architecture changes how you work with it. The tradeoffs between automatic continuity and on-demand depth explain why persistent

· 7 min read