A permissions check sees one action at a time. Whole classes of agent failure — a consequential step repeated, an escalation across agents, a sensitive record reassembled from harmless reads — exist only in the trajectory. The Governance Plane evaluates the sequence. Here it is measured on real recorded agent behavior, with its findings scored against the domain's own policy by an independent oracle — not a claim, a test.
Evidence · controlled · internally reproduced 27 Oct 2026: 38 of 460 recorded trajectories carry an at-most-once violation (41 findings), precision and recall 1.00 on every rule, identical on both agentic-os versions tried; a per-action check catches 0 of the 38. The payment rule has no positive cases in this set.
460 real GPT-4o agent trajectories from
τ-bench retail (Sierra, MIT) — returns,
exchanges and cancellations over a 1,000-order store. Every governance rule is derived verbatim from
the domain's shipped policy (wiki.md);
an independent structural labeler — not the plane — reads the same policy + database to mark
the ground-truth violations. The plane runs its trajectory engine over the events and is scored
against those labels.
| policy rule (from wiki.md) | violations caught | precision | recall | span |
|---|---|---|---|---|
| At-most-once"exchange or modify order tools can only be called once" | 38 | 1.00 | 1.00 | multi-event |
| Status preconditioncancel needs 'pending'; return/exchange need 'delivered' | 29 | 1.00 | 1.00 | single |
| Cross-user"help one user only; deny requests for any other user" | 4 | 1.00 | 1.00 | single |
| Payment not in profilepayment method must belong to the user | 0 | – | – | unexercised |
// 460 recorded GPT-4o trajectories · precision/recall of plane findings vs an independent policy oracle · reproduce (full run, offline): TAUBENCH_TRAJ=…/gpt-4o-retail.json python -m agentic_os_enterprise.governance.testbed.taubench.score
Scored against the oracle the plane reads the same policy from, the single-event rules agree by construction — a conformance result, worth having but not the point (the mission benchmark makes the same disclosure). Two things here are genuinely load-bearing, and neither is a permission check in disguise.
| the difference | per-action gate | trajectory plane |
|---|---|---|
| Multi-event violationsthe "called once" rule — each individual call is valid; only the second call, correlated on the order, is the violation | 0 of 38 | 38 of 38 |
| False alarms across 460 interleaved-order sessionsthe real test of correlation: two different orders each touched once must not trip the rule | – | 0 |
| Detect vs block, reported separatelythe same cross-user rule, resolved by the surface it lands on | – | 6 DENY · 12 NO_OVERRIDE |
// walk it live at gov.redevops.io — pick a real session, step it call by call, see the plane's verdict inline · data: tau-bench (MIT) · code: agentic-os-enterprise/governance/testbed/taubench
// τ-bench retail (Sierra, MIT) is used only to benchmark the governance plane — real recorded agent trajectories + the domain's shipped policy; not redistributed, not shipped in the product. A balanced fixture is committed; the full 460-trajectory run reproduces from the upstream files.