Track: AI EngineeringFormat: TalkLevel: Intermediate
Evals as a Product Surface: Making Quality Legible
Wednesday, May 12: 10:15 AM – 10:40 AM
Mission Hall
Evaluations are usually treated as an internal chore. We shipped ours to customers instead, and it changed how the whole team argued about quality.
Speakers (1)
- DFDiego Ferreira
Staff ML Engineer, Cartograph AI
Diego works on evaluation tooling and spends most of his week arguing that a benchmark you cannot reproduce is a rumour.