Mandate Labs

Every case in.
One decision out.

Ward is the decision model for fraud, AML, sanctions and KYC.

[01] We took the narrow road

AI that answers with a paragraph, a maybe a decision you can defend.

01 / decision

Typed, not written

Approve, step up or decline, in the same envelope for every case. Your code branches on one field.

02 / risks

A probability for every risk

Fraud, AML and sanctions each come back with their own probability and interval. A close call looks like a close call.

03 / evidence

Shown, not claimed

The signals, the lists checked and the typologies behind every answer, ready for your analyst and your regulator.

ward-1 · probability
Thresholds0 approve · 0 step up · 0 decline

48 illustrative cases, one probability each.

0.0 · low risk0.30 · 0.70high risk · 1.0

[02] Confidence

Draw your own lines.

Every answer carries a probability and an interval, so your system decides what happens at each level: approve on its own, send the case to an analyst, or decline.

Move the two lines to see how the same cases split.

[03] See it decide

Pick a case.

Five of the eleven decision types. Same endpoint, same answer shape.

POST /api/v1/decidemodel ward-1

input

decision · type: payment

Illustrative examplesRun your own case →

[04] Capabilities

Eleven questions. One endpoint.

Send what you have. Ward works out what it is, runs every check that applies and answers, in one call.

[06] Research

The science Ward grew out of.

It began with one question: how do you trust an AI agent with money?

PaperWhat it doesIn WardPublished
Economic Decision Quality ScoreGrades an agent’s reasoning, not only its result.EDQS-B is live
EDQS-Q is in validation
Aug 2026
Agent Behavioral TelemetryDrift as an early sign of compromise.LiveJun 2026
The Decision Trust ProtocolSeven decision gates and two system steps.LiveMay 2026
The swarm that wasn’tLaundering through one’s own agents.Field noteSep 2026

Bring the case your team is stuck on.