Finance & insurance · case-study · Feb 2026

The invoice bot was sending SSNs to the model

An ordinary SAP invoice-extraction step was quietly passing two PII fields to the model. Here's what an Inspector caught in Watch mode — at zero risk, nothing rewired.

The workflow you already run

A finance team automates invoice extraction: SAP hands a document to a model, the model returns structured line items, and the numbers flow on into the ledger. No one calls this "an AI project." It's just a step that got faster last quarter. That is exactly the kind of place AI actually lives in an enterprise — inside an ordinary workflow no one flagged for review.

The risk you can't yet see

Look closely at what leaves the building. In the raw invoice payload sit a supplier contact's Social Security number and a date of birth — fields no one intended to send to a model, travelling out with everything else. Nothing is obviously broken. The line items come back fine. But if an auditor asked "what personal data reached the model, and can you prove none of it left your tenant?" the honest answer today is a shrug.

What an Inspector caught

Started in Watch mode, an Inspector sat in front of the same call and observed — touching nothing, changing nothing, just recording what it would have done:

an inspector · watch mode SAP · invoice extraction
inboundextract invoice · SAP → model
filter · piiSSN, DOB scrubbed · pre-model
reconstructdates normalized · ISO
detect1 policy mismatch · flagged
output12 line items · schema-valid

On record

Two PII fields it would have scrubbed before the model ever saw them. Dates it would have normalized. One policy mismatch it would have flagged for a human. All of it signed and on record, on the team's own stack — with nothing actually run. That's the whole idea of Watch: prove the value and see the exposure first, before you hand an Inspector any control.

Related

← All insights