Policy setup

Define allowed tools, domains, and approval gates.

Step by step

  1. List tools your agents may call and mark high-risk actions.
  2. Define data domains (PII, secrets, customer data) and blocked prompt patterns.
  3. Set internet usage rules and human approval requirements for sensitive operations.
  4. Map policies to agents in the dashboard; evaluation runs on each ingested trace.
  5. Configure tool execution policy and optional policy packs under organization settings; per-asset overrides merge for gateway traffic.