I build AI agents that do real work. Then I write about it.
I'm an engineer. For a few years I've built agents that do real work. The last ones quietly ran the company I started. This is where I write about it. What held up. What broke. What I'd build differently.
Selected writing
All posts →Why we replaced RAG with an LLM-native wiki
For a year our agents retrieved. Then we let them reason over a curated knowledge base instead — and most of our reliability problems quietly disappeared.
Running a company as a fleet of stateful agents
Domain-based AI roles instead of Scrum. How Temporal coordinates long-lived agents across billing, operations and support — and what that does to an org chart.
Opus, Sonnet or Haiku: a cost & latency model
A practical framework for model selection under real rate limits, latency budgets and unit economics — from someone who pays the bill.