← back to the directory
Hosted Service Observability & Evaluation

Braintrust

1Evaluate, 2log, 3and 4improve 5AI 6products.

the six Ws · specification

W1 Who

By Braintrust.

W2 What

A platform for evals, prompt experimentation, and production logging.

W3 Where

A hosted SaaS with SDKs.

W4 When

When iterating on prompts and measuring quality.

W5 Why

Makes AI quality measurable and comparable.

W6 With

An API key and outbound HTTPS.

W7 Watch

Commercial SaaS, API key required; logs and eval data are sent to Braintrust.

EvaluationLoggingExperiments

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.