For teams whose agents call tools that do real things

Your guardrail said no.Find out whether anything stopped.

Most AI guardrails are obeyed because the calling code chooses to obey them. That holds until the next refactor by someone who did not know why the check was there. This asks one question about each of your gates, and it is not about the gate's logic: who holds the refusal.

Get the Gate-to-Tool Exposure Kit — $99one-time · instant download · yours to keep
Five deliverables · runnable
Custody engine (Python)
runnable
Conformance workbook (.xlsx)
3 tabs
Verdict envelope emitter
one flag
Eight-gate worked example
5 tools
Two playbooks (.docx)
custody + runbook
Works alongside
Verdict Envelope Standard · Access Auditor · Reliability Harness
01.The Problem

A guardrail nobody is obliged to obey is a suggestion.

The usual wiring looks like this: the agent calls a policy check, gets a verdict back, and the surrounding code decides what to do about it. That is a convention between two pieces of software written by the same person on the same afternoon. Nothing in the system enforces it. The tool is still reachable, the timeout path still proceeds, and the component doing the checking is the component being checked.

6
observations, one question

Who holds the refusal, what happens on a timeout, whether a route around exists, when the verdict is read, and whether an override is recorded.

1
observation between two gates

Two gates in the worked example are identical everywhere except whether the checking code is the governed code. One reads FAIL-OPEN. The other reads DECORATIVE.

0
credit for having more gates

A tool takes the reading of the weakest gate in front of it. Adding a flawless fourth guardrail cannot raise it. It can only give you a fourth way to be wrong.

02.See It Work

Move custody and watch a guardrail stop being one.

Load a gate
Refund amount ceiling · governs refund_api
Who holds the refusal?
Is the code that checks the verdict the code being governed?
If the gate errors or times out, what happens to the call?
Can the tool be invoked without passing this gate?
Is the verdict consumed before the side effect?
Can the refusal be overridden, and is that recorded?
This gate
FAIL-OPEN
decided by: custodian
The shipped eight-gate example
SOME TOOLS ARE HELD
refund_api · 2 gates · FAIL-OPEN
publish_endpoint · 1 gate · DECORATIVE
outbound_email · 2 gates · DECORATIVE
crm_write · 2 gates · DECORATIVE
payments_ledger · 1 gate · FAIL-CLOSED
1 of 5 tools held · fix first: publish_endpoint
Reported, never graded

8 gates in total. One tool in the example is protected by a flawless gate and a weak one, and it reads as the weak one. Another gate cannot raise it.

This grades wiring, never people. It says nothing about whether any gate's verdicts are correct.

03.The Engine

The full output on the worked example, verbatim.

Eight gates over five tools, one command, no dependencies. This is the complete run, pasted as printed.

GATE-TO-TOOL EXPOSURE KIT - custody report
spec_version 1.0.0 | 8 gates read across 5 tools

GATE    NAME                         GOVERNED TOOL          VERDICT       DECIDED BY
--------------------------------------------------------------------------------------------------------
G-01    Refund policy gate           refund_api             FAIL-CLOSED   custodian
G-02    Refund amount ceiling        refund_api             FAIL-OPEN     custodian
G-03    Publish safety check         publish_endpoint       DECORATIVE    self_policing gate
G-04    Outbound content filter      outbound_email         DECORATIVE    custodian
G-05    CRM write policy             crm_write              FAIL-OPEN     on_gate_error
G-06    CRM field validator          crm_write              DECORATIVE    reachable_without_gate
G-07    Ledger posting gate          payments_ledger        FAIL-CLOSED   custodian
G-08    Email rate guard             outbound_email         DECORATIVE    custodian

SELF-POLICING GATE
  G-03: the code that checks the verdict is the code being governed - decisive

UNESTABLISHED ANSWERS (scored as the worst they could have been)
  G-05: on_gate_error - a better answer would have made this FAIL-CLOSED
  G-06: reachable_without_gate - a better answer would have made this FAIL-CLOSED
  G-08: on_gate_error - nothing they could have been would change this row

PER TOOL (the weakest gate in front of it)
TOOL                     GATES    VERDICT       WEAKEST
------------------------------------------------------------
refund_api               2        FAIL-OPEN     G-02
publish_endpoint         1        DECORATIVE    G-03
outbound_email           2        DECORATIVE    G-04
crm_write                2        DECORATIVE    G-06
payments_ledger          1        FAIL-CLOSED   G-07

ESTATE
  1 of 5 tools are held
  VERDICT: SOME TOOLS ARE HELD
  FIX FIRST: publish_endpoint (DECORATIVE) - start at gate G-03

REPORTED, NOT GRADED
  8 gates in total. This count is reported and compared against nothing.
  A further gate in front of a tool cannot raise its reading. It can only give you one more way to be wrong.

This grades wiring, never people. It says nothing about whether any gate's verdicts are correct.

Note refund_api. It is protected by a gate that reads FAIL-CLOSED and one that does not, and the tool reads as the second one.

04.The Standard

Three rules, and the reason each one is not negotiable.

The caller cannot police itself

Where the code that reads the verdict is the code the gate exists to restrain, the restraint lasts exactly as long as that code keeps choosing to honour it. This is the one place the instrument overrules everything else on the row, and it only ever lowers a verdict.

An unestablished answer is the worst answer

If nobody has watched what happens when the gate times out, that is scored as the worse of the two things it could have been. The report then tells you whether establishing it would have changed the row, so you test the ones that matter.

A tool is as held as its weakest gate

Anything reaching the tool reaches it through the weakest path, so that is the reading. The engine proves rather than asserts this: across every arrangement it tests, adding a gate never raises a tool.

05.What This Is - And Isn't

An enforcement check, not a permission layer.

It is
  • A read-off of who holds the refusal at each gate in your stack.
  • A runnable engine, a workbook that reproduces it, and a demo that agrees with both.
  • A per-tool roll-up that tells you which of your tools anything is actually holding.
  • An emitter: one flag and the finding comes out as a verdict envelope a machine can be bound by.
It is not
  • A judge of your gates. A gate with perfect custody and poor logic reads FAIL-CLOSED here.
  • A permission layer. It never decides which identity may call what.
  • A way to halt an agent already running. That is a different question.
  • A scanner. It reads answers you supply about your own wiring and connects to nothing.

Scope: this is an engineering instrument. It grades the wiring around a gate, never a person, and asserts no regulatory position. It does not tell you whether a gate's verdicts are correct, and it is not legal advice.

06.Who It's For

For the stack where the agent already has the keys.

Buy it if
  • An agent in your stack can call something that moves money, changes access or reaches a customer.
  • You have added guardrails over time and could not say, today, which of them would actually stop anything.
  • You are wiring gates to agents through MCP and want the enforcement contract settled before there are nine of them.
  • Somebody asked what happens if the policy service is down, and the honest answer was that nobody has tried.
Skip it if
  • Nothing in your stack executes without a person approving it first.
  • You want to know whether your gate's decisions are correct. That is a different instrument.
  • You are looking for a scanner. Every input here is an answer you supply.
08.Common Questions

Direct answers, before you buy.

That there is no condition under which this gate stops the action. It produces a verdict and the world continues. It is not a criticism of the gate's logic, which may be excellent. It is a statement about the wiring around it: nothing downstream is obliged to care what it said. DECORATIVE ranks below FAIL-OPEN deliberately, because a gate that fails open still stops the ordinary case, while a decorative one has never stopped anything and never will.

You will find out eventually.
This is the cheaper way.

One purchase, lifetime access, 12 months of updates. $99, once.

Scope: an engineering instrument. It grades wiring, never people, asserts no regulatory position, and is not legal advice.

Sold by RedHub AI LLC · Secured by Stripe · redhub.ai