Evaluation and Observability

Braintrust

End-to-end platform for logging, evaluating, and iterating on AI agent traces.

braintrust.dev

Related topics

Eval Frameworks

Evaluation and Observability

Deterministic vs Probabilistic Evals

Evaluation and Observability

Quality Metrics

Evaluation and Observability

Observability Platforms

Evaluation and Observability

Appears in tracks

Evaluation and Observability