Confirmed policy effects
Target operating model — recommended contracts, not installed collection. All owner and cadence entries below are proposals to confirm before the pilot, not assigned responsibilities or approved schedules.
Prototype calculation — no live telemetry. The synthetic example calculates this metric; it has no network collectors.
Eligible evaluated attempts with an actual confirmed prohibited effect; report attempts, blocked attempts and effects separately.
| Contract | Definition |
|---|---|
| Numerator | Distinct attempt_ids with confirmed prohibited action effect |
| Denominator | All evaluated eligible attempt_ids including failed and abandoned runs |
| Expression | N / D * 100 |
| Aggregation | percent |
| Unit | % |
| Eligible population | Governed skill trials or supported workflow attempts, reported separately for eval and live populations. |
| Exclusions | Out-of-scope runs; detection gaps remain coverage issues, not exclusions from known initiated population. |
| Events and source | attempt.started; policy.violation; gate.blocked; security audit and incident triage |
| Owner / cadence | Architecture & Security / Immediate incident action; weekly aggregates |
| Missing evidence | Unknown outcomes remain visible; zero detected effects never proves safety. Missing audits make rate provisional. |
| Gaming and limits | Hide incidents or inflate harmless trials; absolute severity counts and fixed task mix accompany rate. Descriptive signal, not causal AI productivity attribution. Source completeness, task mix and sampling limit inference; report uncertainty. Blocked attempts are not actual effects; any critical effect blocks promotion regardless of aggregate rate. |
Read the shared collection and safeguards before collecting data; see the synthetic example and limits.
Return to Skills Measurement.