Real-Time Policy Monitoring for AI Agents

The answer

Corules enforces policy synchronously in the critical path — not asynchronously after the fact. Every decision is evaluated before execution. The audit ledger streams decision events in real time, enabling operations dashboards to show: current violation rates, escalation volumes, policy threshold breaches, and agent behavior patterns. Anomalies surface immediately rather than in the next audit cycle.

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.

// Real-time metrics from audit stream:
{
  "last_60_min": {
    "evaluations": 1847,
    "allow": 1642,
    "block": 89,
    "escalate": 116,
    "block_rate_pct": 4.8,
    "top_violation": "discount_pct > max_discount_by_tier"
  }
}

Frequently Asked Questions