Evals for AI Agents
A practical look at testing agents against the work we actually expect them to do.
Watch the full talk ↗I'm Gareth Paul Jones. I lead AI product work at Poe, with a background in the APIs and developer tools that make technical systems usable.
A closer look at the work ↓
A practical look at testing agents against the work we actually expect them to do.
Watch the full talk ↗Leading AI product work, from model behavior to products people can understand and use.
Research product work across AI Companion, speech, and applied machine learning.
Developer experience across the API platform, SDKs, and command-line tooling.
Product and engineering leadership for Places API and its partner ecosystem.
Earlier chapters
Twitter · Developer Relations Lead · 2013–2016Apple · Product Manager · 2011–2013Google · Associate Product Manager · 2009–2011