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. Before AI product work at Poe, I led developer experience across Twilio's APIs, SDKs, and command-line tooling.
Explore selected talks ↓
Three talks on practical AI work.
A practical look at testing agents against the work we actually expect them to do.
Watch the full talk ↗Product, engineering, and developer relations have given me different perspectives on how technology becomes useful.
AI product leadership at Poe. Previously, research product work on AI Companion, speech, and applied ML at Zoom.
Poe / Quora 2024–nowGroup Product Manager, Developer Experience. API platform, SDKs, and CLI.
Product and engineering lead for the Places API and partner ecosystem.
Earlier chapters
Twitter · Developer Relations Lead · 2013–2016Apple · Product Manager · 2011–2013Google · Associate Product Manager · 2009–2011