Policy Versioning for AI Decision Consistency
Teams managing policy changes while ensuring AI decisions stay consistent and historical decisions remain auditable.
El problema
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.
Cómo lo resuelve Corules
Corules's policy runtime evaluates structured context against compiled CEL expressions — returning ALLOW, BLOCK, or ESCALATE with a reason and audit ID.
Ejemplo de política
// 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 3.1.0Frequently Asked Questions
Can I roll back a policy if it causes problems?
Yes. Activating a previous policy version is an API call. The previous version is never deleted — it is always available for reactivation.
How do policy changes affect in-flight decisions?
In-flight decisions (mid-workflow) evaluate against the policy version that was active when the evaluation began. Policy changes are not retroactive.