Manufacturing & quality · case-study · Apr 2026

The deviation-report bot couldn't show its work

A regulated manufacturer let a model draft deviation reports from batch records. It was fast — until an auditor asked how each conclusion was reached. Here's what an Inspector caught in Watch mode.

The workflow you already run

When a batch drifts out of spec, quality has to write a deviation report — root cause, impact, disposition. It's slow, so a model drafts it from the batch record and the deviation log. The report comes back well-structured and the reviewer signs. Cycle time drops. Everyone's pleased.

The risk you can't yet see

Then the audit arrives. An investigator asks the question audits always ask: how was this conclusion reached, and can you show the trail? The model read the batch record, weighed some numbers, and wrote a confident paragraph — but which readings did it use, were the units consistent, and did anything in the source violate the SOP it was supposed to apply? None of that was captured. A fast report with no provenance is, to a regulator, a liability wearing a nice format.

What an Inspector caught

Started in Watch mode, an Inspector sat in front of the same drafting call and recorded what it would have done:

an inspector · watch mode Batch record → deviation draft
inbounddraft deviation · batch record → model
filteroperator IDs masked · pre-model
reconstructunits normalized · mg/L, °C
detectreading outside spec · unflagged in source · caught
outputdraft · every figure traced to source

On record

Units it would have normalized before the model reasoned over them. A reading outside spec that the source log never flagged, surfaced and recorded. And every figure in the draft traced back to the line it came from — the provenance an auditor actually wants. Signed, on the manufacturer's own stack, nothing run. That's Watch: prove the trail before you trust the draft.

Related

← All insights