NoumenaiFOR FINANCE WORK

The Ladder

01 — Shadow to auto-post

Autonomy is earned, never switched on.

We do not flip an autonomy switch. We move the system up a trust ladder: one supplier, one client, one consistent outcome at a time. Each promotion requires a measured history; demotion is automatic the moment a correction appears.

Stage 01
Shadow
Observe and propose, but do not act.
Stage 02
Eligible
Evidence is enough to admit for review.
Stage 03
Human-enabled
Every post confirmed by a person.
Stage 04
Auto-post
Autonomous action, only after proof.
  • The promotion metric is not the model's confidence. It is how often a human accepted the proposal without changing it.
  • Demotion is immediate and automatic on any subsequent correction. There is a global kill switch.
  • Aligned with Article 14 of the EU AI Act.

The Number

02 — Composed, not declared

Where the number comes from

Confidence is composed, not declared. A model reporting its own confidence is reporting an opinion.

01

A rubric, not intuition.

95%+ requires five or more concordant prior entries. With no history for that client, a hard ceiling of 85%.

02

A second opinion, with fixed arithmetic.

A reviewing agent independently re-derives the classification on every document. Agreement raises the number; disagreement discounts it.

03

History becomes statistics.

Where prior entries exist, the number is frequency, not opinion — an account used in 11 of 12 prior entries is 92%.

04

Provenance is mandatory.

An account with no source is capped at 50%. The weakest link decides — a document's confidence is the minimum across every element of the entry, never the average.

The Human

03 — Against automation bias

The other side of confidence

The human only stays in command if the human keeps looking.

The better the proposals get, the less the human checks them. Automation bias is the real failure mode of human-in-the-loop, and most systems ignore it. We design against it.

Disagreement penalises, it doesn't just warn

When proposer and reviewer diverge, confidence is deterministically demoted, pushing the document to human review.

IN PRODUCTION

Re-verification where complacency is highest

The reviewer runs again precisely on high-confidence entries, where the human's guard is lowest.

IN DESIGN

Forced justification on what's risky

Large or high-risk entries require a written reason to approve. It breaks the rubber stamp.

IN DESIGN

Measuring attention

Deliberately injecting incorrect documents to measure whether the reviewer is still looking.

EXPLORATORY

If this is the kind of system you want in your finance function — start small, and make us earn it.