SponsorEngineering trackconfirmed

Ask YouTube — Open Q&A

Day
Day 3 — Session Day 2 · Wed, Jul 1
Time
2:25pm-2:45pm
Room
Track 5 · Room 2005
Track
Evals
Share
Track theme
Evals

Evaluating agents — long-horizon benchmarks, autonomous debuggers, model whisperers, and evals-driven development.

Accessible with the Engineering pass and above.

About this session

(updated) an off-the-record session with Mihnea Munteanu, Senior Product Lead, Ask YouTube / AI Search @ Google

Speaker