What files can I upload?

Your risk calculator as an Excel workbook (.xlsx or .xlsm), a PDF or a Word document, and your AML policy as a PDF or a Word document, each up to 25 MB.

What if the AI reads a setting wrong?

Mark it “Doesn’t match our policy” and tell the AI why, in plain language. It proposes a correction, showing each changed setting before and after, and nothing changes until your team accepts it.

Do you keep our policy documents?

No. The file is read to draft your configuration and is not stored. We keep the configuration itself, where each setting came from (a sheet and row, or a section of the document), who confirmed each setting and who approved the model. If your team corrects a setting with the AI, that conversation is kept with the model’s audit record, and may quote your document.

What does an AML policy configure today?

Today, the risk model. Drafting onboarding questions, document requirements, EDD triggers and country risk from your AML policy is coming next.

SET UP FROM YOUR POLICY

Early access

Nobody wants to spend months setting up a platform.

Upload the risk calculator you already use. The AI drafts your risk model in minutes, asks where your spreadsheet is ambiguous, and shows how your past cases would have scored. Your team confirms every setting, and a second approver signs it off before anything goes live.

Request early access →See how it works

THE PROBLEM

Your policy already exists. Re-keying it is the slow part.

Your risk methodology is already written down: in a spreadsheet your MLRO signed off, and a policy your board approved. Setting up a new platform usually means re-keying it by hand, factor by factor and band by band. That can take weeks, and every manual step is a chance for the platform to drift from the document your regulator will ask about.

HOW IT WORKS

From your spreadsheet to an approved risk model

Upload your risk calculatorA spreadsheet of up to 25 MB. Hidden sheets, formulas and named ranges are read too.
The AI drafts your risk modelCategories, factors, weights, scores and bands. A large calculator takes a couple of minutes.
It asks before it guessesWhere your spreadsheet is ambiguous, it asks you.
See the effect on past casesHow your existing cases would have scored, before anything changes.
Your team confirms every settingOne by one, with a record of who confirmed what.
A second approver signs it offNothing goes live until a different MLRO approves it.

WHY IT HOLDS UP

Fast to set up, and still yours to sign off

Faithful to your spreadsheet

It reads every sheet, hidden ones included, with their formulas and named ranges, rather than a tidied-up copy.

Every setting traced

Each setting records where it came from: a sheet and row, or a section of the document.

See the effect first

Before anyone approves, see how your past cases would have scored under the draft.

Disagree in plain language

Where a setting doesn’t match your policy, tell the AI why. It proposes a correction, and nothing changes until your team accepts it.

Four-eyes, always

A different MLRO approves the model before it goes live. No AI, and no AI tool connected to your workspace, can switch one on.

Re-import without starting over

When your policy changes, upload the new version and see exactly what changed.

What we keep

Never the file. We keep the configuration, where each setting came from, who confirmed each one and who approved the model, and every conversation your team has with the AI to correct a setting, which may quote your document. That record is kept for five years, including after you leave, so you can always show how a setting got there.

Coming next

Coming

From your AML policy: onboarding questions, document requirements, EDD triggers and country risk
An annual re-acknowledgement, run through the same four-eyes flow

PRICING

Pay when you switch a model on

Policy set-up is an add-on. You pay when you switch a drafted model on, not when you try one. Talk to us about pricing.

FOR DEVELOPERS

Prefer your own AI agent?

Point it at our MCP endpoint and it drafts through the same tools, reading your workbook on your side. It can’t switch a model on either: that stays with your approvers. Talk to us to set it up.

FAQ

Questions about policy set-up

What files can I upload?: Your risk calculator as an Excel workbook (.xlsx or .xlsm), a PDF or a Word document, and your AML policy as a PDF or a Word document, each up to 25 MB.
What if the AI reads a setting wrong?: Mark it “Doesn’t match our policy” and tell the AI why, in plain language. It proposes a correction, showing each changed setting before and after, and nothing changes until your team accepts it.
Do you keep our policy documents?: No. The file is read to draft your configuration and is not stored. We keep the configuration itself, where each setting came from (a sheet and row, or a section of the document), who confirmed each setting and who approved the model. If your team corrects a setting with the AI, that conversation is kept with the model’s audit record, and may quote your document.
Can the AI switch a model on by itself?: No. Your team confirms every setting, and a different MLRO approves the model before it goes live. No AI, and no AI tool connected to your workspace, can activate one.
What does an AML policy configure today?: Today, the risk model. Drafting onboarding questions, document requirements, EDD triggers and country risk from your AML policy is coming next.

Start from the policy you already have

We’re opening policy set-up to a small number of teams. Tell us about yours.

Your risk calculator in, a draft risk model out
Every setting confirmed by your team
A second approver before anything goes live

Request early access →See the whole lifecycle