AI Policies
Rule trees that govern every agent action — block, require approval, warn, or log.
—
Policies
—
Enabled
—
Blocking
—
Critical / High
—
Violations (recent)
| Policy | Severity | On violation | Frameworks | Violations | Updated | Enabled |
|---|---|---|---|---|---|---|
| loading… | ||||||
Simulate & evaluate
POST a candidate action context to /api/policies/evaluate. Every enabled policy is evaluated; the strictest matching action wins.
Action context
Verdict
Run an evaluation to see the verdict and which policies matched.