When AI writes all the code
I delegate implementation to agents while staying involved in design, evaluating larger features, and checking that the whole application works as I expect.
Writing
2026
Giving my AI agents access to my RSS reader
How I turned Cove, the Mac RSS reader I built, into an MCP server so my AI agents send me a daily digest in Discord while my library stays on my Mac.
Building an LLM-powered code review sidebar
How I built Sherpa, a Chrome extension that uses LLMs to explain pull requests as you review them, with progressive file and hunk-level detail.
Running AI agents in devcontainers
How to use devcontainers to run AI agents like Claude Code and Codex in isolated environments you control, so you can skip the permission prompts.
2016 to 2022
The archive, 19 older postsThe letter
New essays by email. It costs nothing.