For the day somebody asks you to explain a decision

You kept everything.Nothing connects any of it.

Four artifacts in four systems with nothing tying them to the same event are four artifacts, not a pack. This grades the joins, and the joins are what nobody grades.

Get the Audit Evidence Pack Assay — $119one-time · instant download · yours to keep
Five deliverables · runnable
Evidence-pack engine (Python)
runnable
Assay workbook (.xlsx)
3 tabs
Verdict envelope emitter
one flag
Seven-class worked example
4 artifacts
Two playbooks (.docx)
joining + runbook
Works alongside
Audit-Trail Kit · Write-Back Warden · Postmortem Gate
01.The Problem

Everything was logged. Nothing was joined.

Somebody asks what happened on the fourteenth. The decision is in the agent's output store. The inputs it saw are in an observability platform that rolls off after ninety days. The policy that was live is in a repo with no deployment record. The approval is in a ticket. Every one of those exists, and there is no identifier that runs between any two of them, so the only person who can say which rows belong together is the engineer who built it — and the account you produce is their memory with attachments.

3
joins, not four items

From the decision to the context it saw, to the policy in force, to whoever authorised it. A chain is only as good as its joins, so the pack takes its weakest.

1
person between evidence and nothing

Two classes in the worked example are identical except for whether one person is still available. One reads NEEDS A WITNESS. The other reads NO RECORD.

7
years of retention, unanswerable

The class in the worked example keeping seven years of artifacts is the one that cannot be assembled at all. The one keeping thirty days is fully answerable.

02.See It Work

Remove one person and watch evidence become testimony.

Load a decision class
Discount auto-approval
Which artifacts exist?
What carries the link from the decision to: What context did the agent have?
What carries the link from the decision to: Which policy was in force?
What carries the link from the decision to: Who authorised it?
Is the person who can assert those connections still here?
This decision class
NEEDS A WITNESS
decided by: decision_to_policy

Nothing ties the decision to the policy version in force at the time.

The shipped example, read by question
SOMETHING HERE HAS NO RECORD
What context did the agent have? · NEEDS A WITNESS · 5 of 6
Which policy was in force? · NO RECORD · 3 of 6
Who authorised it? · ANSWERABLE · 6 of 6
fix first: decision_to_policy
Reported, never graded

The class in the example keeping seven years of artifacts is the one that cannot be assembled at all. The one keeping thirty days is fully answerable.

This grades whether an account can be assembled, never a person, and says nothing about whether the decision was right.

03.The Engine

The full output on the worked example, verbatim.

Seven decision classes, one command, no dependencies. This is the complete run, pasted as printed.

AUDIT EVIDENCE PACK ASSAY - could somebody who was not there assemble the account
spec_version 1.0.0 | 7 decision classes read

ID      DECISION CLASS               CONTEXT   POLICY    AUTH      VERDICT           DECIDED BY
------------------------------------------------------------------------------------------------------------
A-01    Refund auto-approval         id        id        id        ANSWERABLE        -
A-02    Discount auto-approval       id        person    id        NEEDS A WITNESS   decision_to_policy
A-03    Support ticket auto-close    id        -         id        NO RECORD         contradiction_cap
A-04    Content publish release      id        -         id        NO RECORD         witness_gone
A-05    Vendor payment release       person    id        id        NEEDS A WITNESS   decision_to_context
A-06    Inventory reorder            id        id        id        ANSWERABLE        -
A-07    Account closure              id        id        id        NO RECORD         no_hub

A LINK TO SOMETHING THAT IS NOT THERE
  A-03: decision_to_policy was recorded as carried, but the artifact at the other end does not exist.

THE WITNESS HAS GONE
  A-04: decision_to_policy depended on somebody who is no longer available.

BY QUESTION (read across every decision, worst first)
QUESTION                     VERDICT           ANSWERABLE WEAKEST
----------------------------------------------------------------------
decision_to_context          NEEDS A WITNESS   5 of 6     A-05
decision_to_policy           NO RECORD         3 of 6     A-03
decision_to_authorization    ANSWERABLE        6 of 6     A-01

ESTATE
  2 of 7 decision classes are ANSWERABLE end to end
  VERDICT: SOMETHING HERE HAS NO RECORD
  FIX FIRST: decision_to_policy (NO RECORD) - weakest at A-03

REPORTED, NOT GRADED
  Longest retention in the file: 2555 days. This figure is compared against nothing.
  1 decision class(es) have no decision record at all: A-07

This grades whether an account can be assembled, never a person, and says nothing about whether the
decision was right or whether it was in fact consistent with the policy.

Read the BY QUESTION block rather than the rows. This organisation can always say who authorised a decision and can almost never say which policy was in force — one problem with one fix, which reading it class by class would have shown as five.

04.The Standard

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

A link is only as good as its far end

An identifier connecting the decision to a policy version that does not exist connects to nothing, whatever your register says. This is the one place the assay overrules an answer you gave it, and it only ever lowers a reading.

A person is not a join

A pack that assembles because somebody remembers how the systems fit together stops existing when they leave. It did not degrade at that moment — it was never evidence. NEEDS A WITNESS names that state precisely rather than politely.

Read it by question, not by decision

Which decisions are weak is rarely actionable. Which of the four questions you can never answer is one problem with one fix, and it is usually the same fix everywhere: one identifier that travels.

05.What This Is - And Isn't

A reconstruction check, not a retention policy.

It is
  • A read-off of what carries each join between the four artifacts an account needs.
  • A runnable engine, a workbook that reproduces it, and a demo that agrees with both.
  • A per-question reading that names which of the four you can never answer.
  • An emitter: one flag and the finding comes out as a verdict envelope.
It is not
  • A retention policy. Whether you keep records, and for how long, is a different instrument.
  • A judge of whether the decision was right, or whether it really was consistent with policy.
  • A regulator-facing defensibility opinion. It asks whether an account can be assembled, nothing more.
  • A scanner. Every input is an answer you supply about your own wiring.

Scope: this is an engineering instrument. It grades whether an account can be assembled, never a person, and asserts no regulatory position. It does not tell you whether a decision was right or whether it was consistent with policy, and it is not legal advice.

06.Who It's For

For the estate somebody will one day ask about.

Buy it if
  • Automated decisions in your business affect customers, money or access.
  • You could not say today whether the inputs a decision saw can be tied back to the decision itself.
  • An account of any past decision would currently depend on one engineer being available.
  • Somebody is going to ask, and you would rather find out now than then.
Skip it if
  • One identifier already travels through every system you own. There is nothing here to find.
  • You need a retention schedule. Different instrument.
  • You want an opinion on whether a decision was defensible. This asks whether it is reconstructable.
08.Common Questions

Direct answers, before you buy.

Because keeping is not the same as assembling. The common failure is not a missing log — it is four artifacts sitting in four systems with nothing tying them to the same event. You have the decision in one place, the inputs in another, the policy in a repository and the approval in a ticket, and no identifier runs between them. That is four artifacts, not a pack. This grades the joins, which is the thing nobody grades.

Four artifacts with nothing between them
are four artifacts.

One purchase, lifetime access, 12 months of updates. $119, once.

Scope: an engineering instrument. It grades whether an account can be assembled, never a person, asserts no regulatory position, and is not legal advice.

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