I handed an AI agent 13 invoices and a list of what we had actually ordered. It approved 10 of them, $9,049.05, and refused 3. The 3 it refused were the exact 3 I had rigged to be wrong: a padded total, an invoice nobody ordered, and a straight duplicate. Together they came to $1,411.25 in payments that should never have gone out.
The satisfying part is not that it caught them. It is that the AI did almost none of the deciding.
The setup
13 invoice images across 4 different layouts, including one deliberately awful scan (crooked, low contrast, the kind of thing a phone camera produces at a bad angle on a bad day). A vision model reads each image into strict JSON. Then plain code, no AI anywhere in it, checks that JSON against the purchase orders we placed.
The stack:
