Custom policy

A custom policy is a rule an operator writes to extend the built-in detection: a pattern, the action to take (observe, warn, require approval, or block), a severity, and the scan stages it applies to. Written once in the dashboard, it is enforced on every integration channel without a redeploy.

Built-in detection covers the attack classes every deployment shares; a custom policy covers the ones only yours has: an internal hostname that must never appear in a prompt, a table an agent may read but never drop, a phrase a support agent may not promise. In Shrike a rule is tested against a sample before it can block, propagates to every channel within about a minute, and every hit lands on the same evidence record as the built-in layers. The operator writes the rule; the governance layer enforces it wherever the agent acts.

Related

• What is action governance?
• How are AI agent policies written?
• Export and import a policy bundle (API reference)
• Pricing (policy authoring tier)
• All glossary terms