▶ Watch the talk
Evals for AI Agents
A practical look at testing agents against the work we actually expect them to do.
From Gareth's video collection.Understanding what technology can do. Understanding what people need from it. My work at Poe brings those questions into AI products.
Watch a practical example ↓
▶ Watch the talk
A practical look at testing agents against the work we actually expect them to do.
From Gareth's video collection.At Poe, I lead AI product work focused on turning model behavior into understandable, usable products.
Before joining in 2024, I worked on AI Companion, speech, and applied ML at Zoom. Earlier, I led developer experience at Twilio and product and engineering for Foursquare's Places API.
Research Product Manager — AI Companion, Speech & Applied ML
Group Product Manager — Developer Experience
Product & Engineering Lead — Places API & Partner Ecosystem
Earlier chapters
Twitter · Developer Relations Lead · 2013–2016Apple · Product Manager · 2011–2013Google · Associate Product Manager · 2009–2011