DEV LOG

build-in-public · what shipped · what broke · what i learned

1. 2026-06-13

   Your LLM eval suite is probably testing the wrong thing

2. 2026-05-25

   MCP and CLIs are the same shape: notes on tool design for AI agents

3. 2026-05-19

   The framework was the easy part: shipping AI tooling inside a Fortune 500

4. 2026-04-18

   Why an agent-native portfolio?