1:1 mentoring with Big Tech AI engineers
Q42Premium

How do you evaluate an agent that does different things every time? It's not deterministic.

Evaluation & Quality

EvaluationA/B TestingProductionQuality

Asked at Sierra · Scale AI · Anthropic

How to Answer

"Three evaluation strategies:

  • (1)Outcome-based eval — I don't care about the path, I care about the result. Did the agent produce the correct answer? Was the customer satisfied? Use golden sets with expected outcomes and LLM-as-judge for quality.
  • (2)Trajectory-based eval — for important tasks, check that the agent took reasonable steps. Did it call the right tools? Did it ask for the right data? Score the trajectory, not just the output.
  • (3)A/B testing — run the new version on 10% of traffic, compare CSAT, accuracy, cost, latency vs the current version. Only promote if all metrics are equal or better. The key: separate what from how. The outcome must be deterministic (correct answer); the path can vary."

The deep dive — diagrams, tradeoff tables, and the follow-up trap

Loading…