I build agentic systems and evaluation infrastructure for LLM products, with a focus on making AI systems measurable, reliable, and usable in production. Previously, I co-founded ThreatKey (acquired) and worked at Vanta, Carta and Snap.
Recent writing
- Orchestrating AI Coding Agents: What I Learned Running Three Autonomous Sessions at Once
- Building Kestrel: A Context-Aware AI Desktop Assistant in One Session
- DiffScope: What Happens When You Give a Code Review Agent Real Context
- The 10-Minute AI POC That Becomes a 10-Month Nightmare
- Why Your AI Strategy is Actually a Spreadsheet Strategy