Deterministic ranking
In failure triage, the model doesn’t decide what’s likely.
When an engineer describes a failure, the system first turns the description into structured fields — product, environment, time in service, onset, symptom pattern — and shows them back for correction before anything is ranked. Candidate causes are then ranked by a scored match against a failure-mode library your senior engineer has reviewed and signed off, mode by mode. That scoring is plain and repeatable: once the fields are confirmed, the same fields produce the same ranked list every time, with no model involved. A mode nobody has approved is never matched.
Only then is the model called — to explain why each candidate matches, cite the precedent and design rules behind it, and name the check that confirms or rules it out. It can’t add a cause, drop one, or reorder the list. If nothing clears the match threshold, or the only matches rest on documents the asker isn’t cleared to see, the answer is the same sentence as every other refusal: Insufficient evidence in the knowledge base. It refuses rather than guesses.
- 1
Describe, then confirm
The model turns free text into structured fields. The engineer checks them before anything is ranked.
- 2
Filter by who’s asking
Same rule as above: modes whose evidence the asker can’t see are removed before scoring.
- 3
Score against the signed-off library
Plain, repeatable scoring against approved modes only. No model call.
- 4
Explain and cite — or refuse
The model explains each candidate from the evidence it’s handed. It can’t add, drop or reorder one.
The recording above shows the question-answering path. Triage runs on the same permission filter and the same refusal, with the ranking step added.