Verified record · from the answer index

agent-observability-eval-bootstrap

skilltested · static-verifiedscore 47/100signed passport ✓523 uses

Bootstrap evaluators from production traces — by default propose online LLM-judge evaluators and, after you confirm, create them in Datadog as disabled drafts (never auto-enabled); on request emit Python SDK code or a framework-agnostic JSO

Declared tools (1)

skill:datadog-labs/agent-skills/agent-observability-eval-bootstrap · published by datadog-labs · source repository