Tool Gate · How it works
How the Agent Action Admissibility Engine gate works
How the Agent Action Admissibility Engine checks 8 proposed agent actions against 4 domain-rule constructs before any run: a structural-promotion gate forces functional and disjoint-class violations to blocking severity even when a rule pack marks them review — which is how the batch reads CONTRADICTIONS FOUND with 4 of 8 actions inadmissible.
How the gate works
This tool grades each proposed AI-agent action against your own domain rules before it runs. It reads 8 actions and rolls them into one verdict — the worst, never the average — and then a gate that can only make it worse.
The 8 actions
| Action | Verdict |
|---|---|
| A-1002 · refundfix first | INADMISSIBLEsecond refundsOrder assertion on order-4471 - rule marked review, promoted to blocking |
| A-1003 · payout | INADMISSIBLEpaysTo routed to party-88, a SupportRep - range requires Buyer |
| A-1006 · grant | INADMISSIBLEparty-88 asserted as both Customer and SupportRep - disjoint classes |
| A-1008 · refund | INADMISSIBLEthird refundsOrder assertion on order-5120 - promoted to blocking |
| A-1005 · status_write | REVIEWhasStatus 'probably shipped' is not in the closed set {paid, shipped, refunded} |
| A-1001 · refund | ADMISSIBLEfirst refundsOrder assertion on order-5120 - no rule violated |
| A-1004 · payout | ADMISSIBLEpaysTo party-41, a Buyer - within range |
| A-1007 · status_write | ADMISSIBLEhasStatus 'shipped' - in the closed set |
The verdict bands
Functional and disjoint-class rules assert impossibility, not surprise - a violation of either is always promoted to blocking severity, even when the rule pack marked it review, because a contradiction cannot be a warning.
In the worked sample it reads CONTRADICTIONS FOUND — R1 (at most one refund per order) was declared severity 'review,' but functional rules are structural, so the engine promotes the second refund on order-4471 to blocking regardless - a contradiction is never just a warning. The one thing to fix first: A-1002, the second refundsOrder on order-4471 - its own rule was marked review, but the promotion gate forces it blocking anyway..
Common questions
Can every action look survivable on the How the Agent Action Admissibility gate works and the company still read CONTRADICTIONS FOUND?
Yes. The roll-up takes the worst of 8 actions — never the average — then a worsen-only gate, the Structural promotion gate gate, escalates when trouble clusters. In the worked sample it reads CONTRADICTIONS FOUND because r1 (at most one refund per order) was declared severity 'review,' but functional rules are structural, so the engine promotes the second refund on order-4471 to blocking regardless - a contradiction is never just a warning.
What is a worsen-only gate?
A dispositive rule that can only lower a verdict, never raise it. One fatal flaw overrides an otherwise-set of survivable lines, because a single disqualifying gap shouldn't hide behind an average of the healthy ones. The tool also names the one thing to fix first — here, "A-1002, the second refundsOrder on order-4471 - its own rule was marked review, but the promotion gate forces it blocking anyway.".
Grades proposed actions against rules you write. It is a working aid, not legal, compliance, or security advice, and it never scores, ranks, or assesses people.
Embed this diagram
Free to share and embed with attribution (CC BY 4.0) — keep the link to redhub.ai.
Interactive — renders the live diagram
<iframe src="https://redhub.ai/visuals/tool/agent-action-admissibility-engine.html" title="How the Agent Action Admissibility Engine gate works — RedHub AI" width="760" height="2064" loading="lazy" style="border:0;width:100%;max-width:760px"></iframe>
<p style="font:14px/1.5 system-ui,sans-serif"><a href="https://redhub.ai/visuals/tool/agent-action-admissibility-engine">How the Agent Action Admissibility Engine gate works</a> — by <a href="https://redhub.ai">RedHub AI</a>, the AI that tells you when to doubt it.</p>Image + link — a static picture for any blog
<a href="https://redhub.ai/visuals/tool/agent-action-admissibility-engine"><img src="https://redhub.ai/visuals/tool/agent-action-admissibility-engine-share.png" alt="Diagram of the Agent Action Admissibility Engine: eight proposed agent actions rolled up to the worst, a structural-promotion gate, and the batch reading CONTRADICTIONS FOUND with four inadmissible actions." width="760" loading="lazy" style="max-width:100%;height:auto;border-radius:16px"></a>
<p style="font:14px/1.5 system-ui,sans-serif"><a href="https://redhub.ai">RedHub AI</a> — the AI that tells you when to doubt it.</p>
This is how Agent Action Admissibility Engine works. More diagrams in the Visual Field Guide.