Evaluate policy against historical traces
Policy
Evaluate policy against historical traces
Evaluate a CLPI policy against historical AIP traces for an agent. Replays past tool invocations through the policy to identify what would have been blocked, escalated, or flagged. Useful for understanding the impact of a policy change before rolling it out.
POST
Evaluate policy against historical traces
Authorizations
Supabase JWT token in Authorization: Bearer header
Body
application/json
A complete CLPI policy document defining capability mappings, forbidden tools, escalation triggers, and enforcement defaults.
Agent whose historical traces will be evaluated
Start of time range for historical traces
End of time range for historical traces
Maximum number of traces to evaluate