I Stopped Being the Switchboard for My Coding Agents
A decision memo on moving from agent-by-agent coordination to Firstmate and Herdr: isolated worktrees, durable state, supervised loops, decision gates, and evidence-backed PR handoffs.
Posts
Long-form write-ups with enough method and caveat to be useful later.
Explore by topic
-
-
Day 3 with Fable: Announcing the Autonomy Alpha
The Autonomy alpha is live — a native macOS app and local MCP server that lets AI agents work through your real accessibility setup — plus the day-three build-log of shipping it with Claude Fable 5.
-
Steps to Make Accept: text/markdown Work Everywhere
I thought I had built Accept-header Markdown for AppHeat. Production had other plans, because Cloudflare was skipping the Worker entirely.
-
I Built an AEO Agent Workflow. Google Made Me a Skeptic.
A field note from setting up a local Pi workflow with OpenRouter agents to research AEO topical authority. The real surprise was not any agent tactic — it was what Google's own guidance actually says.
-
What I got done with Fable that kept slipping before
A field note on handing a large Rust refactor to Fable: knowledge-graph analysis, a full graph rebuild that survived a mid-run failure, and a 9,859-line file cut to 877 across six verified commits.
-
AEO from the jump: build pages people can quote
A practical note on making pages easy to read, cite, and hard to misquote.
-
Don't give your agent memory before you give your user control
A field note from adding memory to a Bible study agent app: start with user-visible records, then add semantic retrieval and traces.
-
Apple container vs Colima: local datastore benchmarks on an M4 Mac
A practical benchmark comparing Apple's container runtime and Colima across Redis, Postgres, ClickHouse, DuckDB, and Neo4j on one M4 Mac.