top | item 46573174

Anthropic: Demystifying Evals for AI Agents

4 points| Bayram | 1 month ago |anthropic.com

1 comment

order

dangelosaurus|1 month ago

I work on Promptfoo (an open-source eval framework). Appreciate the mention here. This post captures a lot of the hard lessons around agent evals. In particular, task ambiguity and brittle graders are things we run into constantly.