← [BACK_TO_DIRECTORY]
[TOOL_PROFILE]

braintrust

medium risk

Enterprise evaluation, dataset curation, and proxy CLI for agent teams.

testdebug lang: all
[USE_WHEN]ALLOW
  • ✓ Running regression test suites on agent prompts and managing golden datasets
[AVOID_WHEN]BLOCK
  • ✕ Ad-hoc exploratory prompt prototyping
[DETAILS]RAW_META
Binary
braintrust
Effects
network_access
[SIMILAR_TOOLS]03