For teams whose software acts on an AI verdict

Your gate returned a verdict.Nothing downstream is bound by it.

A verdict a person reads only has to be understandable. A verdict a machine acts on has to be checkable, expirable and replayable, by someone who was not there. This grades the payload your system already emits against six elements and tells you which of the two you built.

Get the Verdict Envelope Standard — $129one-time · instant download · yours to keep
Six deliverables · runnable
Conformance engine (Python)
runnable
MCP reference server
3 tools
Conformance harness
41 checks
Envelope shim for your engines
one line
Conformance workbook (.xlsx)
3 tabs
Two playbooks (.docx)
authoring + runbook
Works alongside
MCP Builder Kit · Skill Trust Gate · Audit-Trail Kit
01.The Problem

Every AI tool you own ends at a verdict a human reads.

Then somebody wires it to something. The gate says approve and a refund goes out; the gate says publish and a page goes live. At that moment the output stops being advice and starts being an authorization, and almost nothing about how it was written changes to match. It still names a model without a version. It still points at thresholds by a label that could have been edited on Tuesday. It still has no expiry, so it authorizes forever.

6
elements, two groups

Identity says what was decided, by which build, on exactly what. Binding says when it stops and how to re-derive it. Miss one and you are not enforceable.

1
word between the two

In the worked example two decision points are identical in all twelve marks. One references its thresholds by digest, one by version string. They read opposite verdicts.

0
paths, URLs, keys or clocks

The MCP server takes no file parameter, makes no network call, holds no credential and has no clock. There is nothing in it to leak and nothing to drift.

02.See It Work

Change one field and watch a verdict stop binding.

Load a decision point
What the payload carries
decision
Identity · Decision value, from a closed set
CARRIED
producer_id
Identity · Producer identifier AND version
CARRIED
input_digest
Identity · Digest of the exact inputs
CARRIED
config_digest
Binding · Thresholds in force, by content digest
CARRIED
expires_at
Binding · Explicit expiry
CARRIED
replay
Binding · Replay handle
CARRIED
This decision point
ENFORCEABLE
identity: COMPLETE
binding: COMPLETE
first element not carried: -
The shipped eight-point example
PARTLY BOUND
1 of 6 machine-acted points are ENFORCEABLE
fix first: D-04
1 read by a person · 1 consumed by nothing
11,450 decisions/day, compared against nothing
Reported, never graded

Only points a machine acts on are graded. The worst payload in the example belongs to a quarterly summary a person reads, and it moves the rollup by nothing.

This grades payloads, never people. It says nothing about whether any verdict inside was correct, and it never measures elapsed time.

03.The Engine

The full output on the worked example, verbatim.

Eight decision points, one command, no dependencies. This is the complete run, pasted as printed.

VERDICT ENVELOPE STANDARD - conformance report
spec_version 1.0.0 | 8 decision points read

ID      DECISION POINT                 ACTED ON VERDICT        FIRST ELEMENT NOT CARRIED
--------------------------------------------------------------------------------------------------------
D-01    Refund auto-approval           machine  ENFORCEABLE    -
D-02    Discount auto-approval         machine  ADVISORY ONLY  config
D-03    Vendor payment release         machine  ADVISORY ONLY  expiry
D-04    Support ticket auto-close      machine  NOT A VERDICT  inputs
D-05    Quarterly board risk summary   human    NOT A VERDICT  decision
D-06    Content publish release        machine  NOT A VERDICT  producer
D-07    Nightly anomaly verdict        nobody   ENFORCEABLE    -
D-08    Inventory reorder trigger      machine  ADVISORY ONLY  replay

ELEMENT STATES
ID     DECISION   PRODUCER   INPUTS     CONFIG     EXPIRY     REPLAY
-------------------------------------------------------------------------
D-01   CARRIED    CARRIED    CARRIED    CARRIED    CARRIED    CARRIED
D-02   CARRIED    CARRIED    CARRIED    STATED     CARRIED    CARRIED
D-03   CARRIED    CARRIED    CARRIED    CARRIED    OMITTED    CARRIED
D-04   CARRIED    CARRIED    OMITTED    CARRIED    CARRIED    CARRIED
D-05   OMITTED    OMITTED    OMITTED    OMITTED    OMITTED    OMITTED
D-06   CARRIED    STATED     CARRIED    CARRIED    CARRIED    CARRIED
D-07   CARRIED    CARRIED    CARRIED    CARRIED    CARRIED    CARRIED
D-08   CARRIED    CARRIED    CARRIED    CARRIED    CARRIED    OMITTED

SELF-DESCRIPTION GATE
  D-02 references thresholds by name, not by content digest - decisive: this row would otherwise have read ENFORCEABLE

ROLLUP (machine-acted decision points only)
  1 of 6 machine-acted points are ENFORCEABLE
  VERDICT: PARTLY BOUND
  FIX FIRST: D-04 (NOT A VERDICT) - inputs is OMITTED

REPORTED, NOT GRADED
  1 point(s) are read by a person, not acted on by a machine - excluded from the rollup.
  1 point(s) are consumed by nothing at all. A verdict nobody reads is not a governance problem.
  11450 decisions per day across every point. This figure is reported and never compared against anything.

This report grades payloads, never people. It reads what your system emits; it decides nothing about whether any verdict inside was correct.

The worst payload in that file is D-05, and it moves the rollup by nothing, because a person reads it. D-08 makes 9,600 decisions a day and D-03 makes 45, and volume orders neither of them.

04.The Standard

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

A name is not a check

Thresholds referenced by version string cap at STATED however confident you are. Two configurations can carry one name; a digest of the content cannot be two things at once. This is the one place the engine overrules your own answer, and it only ever lowers a verdict.

Present is not carried

An element that is in the payload but that nobody holding the payload could confirm is an assertion. Assertions do not count toward completeness. A standard assembled out of unverifiable claims is a description of a standard.

Only what a machine acts on is graded

This exists to make verdicts binding on machines. A payload a person reads is reported beside the finding and folded into nothing. If a machine acts on none of it, the rollup says so instead of grading you.

05.What This Is — And Isn't

A conformance instrument, not a control plane.

It is
  • A written standard for what a machine-binding verdict payload has to carry.
  • A runnable engine, a workbook that reproduces it, and an on-page demo that agrees with both.
  • A working MCP server with describe_inputs, evaluate and verify_envelope, plus a conformance harness you run before pointing any client at it.
  • A one-line shim so an engine you already own starts emitting conformant envelopes.
It is not
  • A permission layer. It never decides who may call what.
  • A judge of your verdicts. It says nothing about whether any decision inside was right.
  • A clock. It never measures elapsed time or tells you whether a given verdict is still current.
  • A scanner. It reads answers you supply about your own payload and connects to nothing.

Scope: this is an engineering conformance instrument. It grades the structure of a payload, never a person, and asserts no regulatory position. It does not tell you whether any verdict inside was correct, and it is not legal advice. Confirm any record-keeping obligations with whoever owns them in your organisation.

06.Who It's For

Built for the moment software started acting on the answer.

Buy it if
  • Something in your stack executes on an AI or rules-engine verdict without a person in between.
  • You are wiring gates to agents through MCP and want the contract written down before there are nine of them.
  • Someone will one day ask which thresholds a particular decision was made under, and you would like to be able to answer.
  • You ship deterministic engines and want them to emit something a third party can verify.
Skip it if
  • Every AI output you produce is read by a person who then decides. The rollup will tell you so and stop.
  • You want to control which identity may call which tool. That is a permission problem and this is not it.
  • You are looking for a compliance certification. This is an engineering conformance check.
08.Common Questions

Direct answers, before you buy.

Both, and the running part is the point. The Verdict Envelope Standard ships the spec, a stdlib Python engine that grades your decision points against it, a workbook that reproduces the engine formula for formula, and a working MCP server your agents can call. The server exposes three tools: describe_inputs, evaluate, and verify_envelope. A standard nobody can run is a document; this one comes with the reference implementation and a conformance harness that proves the implementation is correct before you point a client at it.

A receipt explains what happened.
An envelope binds what happens next.

One purchase, lifetime access, 12 months of updates. $129, once.

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

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