Policy Versioning for AI Decision Consistency

The answer

Policy sets in Corules are versioned and immutable once published. When you update a discount cap, a new policy version is published — the old version remains available for historical audit. Every decision evaluation records the policy version that produced it. This means: policy changes take effect only from the publish timestamp, historical decisions reference the policy that was active at decision time, and the impact of policy changes can be simulated before publishing.

How it works

Corules's policy runtime sits in the enforcement path between your AI agent and the action it wants to take. The agent sends a structured context payload to /v1/validate. Corules evaluates the context against a compiled CEL policy set and returns a structured decision — ALLOW, BLOCK, or ESCALATE — with a reason and audit ID.

Every decision is recorded in an immutable audit ledger. You can replay any past decision by providing the policy_set_version and the normalized input hash — the result will be identical.

Policy example

Policies are written in CEL (Common Expression Language). They are compiled once at publish time and evaluated in microseconds at request time.

// Policy versions are immutable after publish:
{
  "policy_set_id": "pset_01J...",
  "version": "3.2.1",
  "published_at": "2026-01-15T09:00:00Z",
  "status": "active"  // previous versions: "archived"
}
// Decisions made before 2026-01-15 reference version 3.1.0

Frequently Asked Questions