PlatAtlas

How it works, in four pictures.

Every example here is Larkspur Garden Co., a made-up company whose accounts payable team uses PlatAtlas. The suggestions and the check results come from real runs of AI models on its invoices.

1

One request, start to finish.

The AI only suggests. Your team's rules decide what happens next, and anything they don't clearly allow waits for a person.

A REQUEST ARRIVES Invoice email Corvel Fleet Parts$768.66 PLATATLAS SUGGESTS Hold: bank details changed98% sure YOUR TEAM'S RULES Bank changes alwaysgo to a person, however sure it is. FINISHES ON ITS OWN Only answers your teamallowed, e.g. "Pay it"when 97%+ sure. WAITS FOR A PERSON Dana, AP lead,decides. It's written down,with Dana's name.
The AI was 98% sure, and the invoice still went to a person, because a change of bank details is the classic way payments get stolen and the team's rules say so. What may finish on its own is written by your team, not decided by the AI.

From Larkspur's rules (examples/demo-org/accounts-payable/thresholds.yaml) and a live run.

2

Who may decide what, wherever they work.

Outlook, Teams, Slack or a web browser only show the request and pass on who clicked. PlatAtlas checks that person against your team's list before anything is written, so the rule is the same everywhere.

WHERE THEY CLICK Outlook Teams Slack Web browser YOUR TEAM'S LIST Who clicked?May they decide this one?Refused: nothing is written. Sam, AP clerk Pay it · hold for receipt · price question. Not bank changes. Dana, AP lead · Priya, Controller Anything, including bank changes. The assistant (Ask Atlas, or any AI agent) Reads, explains, drafts an email for you to send. Never decides: it has no button to press. The browser works today. Outlook, Teams and Slack are built and tested, and not yet running at a customer.
If Sam clicks "Hold: bank details changed", PlatAtlas refuses before anything is written, in every tool. Because the list lives with your team's rules and not inside Teams or Slack, switching tools doesn't change who may decide.

From Larkspur's list of people (examples/demo-org/accounts-payable/people.yaml).

3

Your team's know-how is yours. The AI is rented.

Only the bottom layer is your organization's asset. Everything above it can be swapped without touching it.

WHERE PEOPLE WORK · RENTED Outlook · Teams · Slack · a web browser · any AI assistant that can read it THE AI MODEL · RENTED Claude, a small open model, or next year's. Switch with one setting; it must pass the same check first. YOUR TEAM'S PLAYBOOK · OWNED A folder of plain files your organization keeps. What each answer means · who may decide what · what always needs a person · every past decision, and why It runs on computers your organization runs. Running it for you in the cloud, or inside your Microsoft 365, is designed, not built.
When someone retires, their successor starts from the playbook. When a vendor changes, you remove it and the playbook is untouched. Anyone can open it with a text editor.

4

Every week, a check that can fail.

The AI is graded against the 60 decisions Larkspur's team already made. The team's limit is 5% wrong. Above it, the check fails and nothing is allowed to finish on its own.

Test stand-in, no AI(Deterministic mock) 34 misses · 56.7% · fails An AI model, invoices withold vendor names 7 misses · 11.7% · fails The same model, on theLarkspur invoices 5 misses · 8.3% · fails Claude Sonnet 5, the sampleinbox's past invoices 2 misses · 3.3% · passes the team's limit (steward's bar: 5%)
Three runs failed, and said so. That is the point: a check that can't fail proves nothing. Switching to a different model is a one-line change, and it has to pass the same check before it is trusted.

Recorded runs in examples/demo-org/accounts-payable/measure/reports/ and the sample inbox's check (demo/try).

See it for yourself.

Try the sample inbox, no login Watch the three short videos Get started