Get customers
Answer customers
Work for you
Reach people
Give agents tools
Run and ship
Screen LLM content and tool definitions, inspect detection results and check policy health
Screen an LLM interaction using the project's runtime Guard policy. Guard can create screening logs. In detect mode flagged is always false; use the returned action and breakdown when interpreting results.
8 fields
Analyze historic content and calibrate detectors without screening logs. This endpoint does not make a flagging decision. Do not use its results for runtime security decisions; use Screen Content for runtime screening.
6 fields
Check the policy configuration of an explicit project.
1 field
Call the published policy-lint endpoint with no request body. The provider publishes no policy-input schema for this endpoint. For an arbitrary policy file, use the dashboard's policy-linter editor instead.
