Eval Metric Selection for Multi-Step Agent Task Quality
Measure agent traces at the layer where they break, not at the final response.
Camille Sinclair
Reporter
Camille Sinclair
Camille Sinclair is a reporter at The Agentic Harness covering eval & validation. Based in Seoul, Camille has written for The Agentic Harness since 2016.
1 story · Seoul