Reference: confidence levels
Every Chat answer (and every query log entry) carries one of four confidence levels.
| Level | Badge | System's interpretation | Recommended handling |
|---|---|---|---|
| High | green | Answered confidently from indexed documents. | Rely on it; spot-check citations when stakes are high. |
| Medium | accent | Answered, but with some uncertainty. | Read the cited excerpts before acting. |
| Low | amber | An answer was found but confidence is low — review recommended. | Treat as a pointer; verify in the source document. |
| Insufficient Data | red | Could not answer from the available documents. | No answer is fabricated. Follow the suggested next steps; the question is logged in Gap analysis. |
What drives confidence
Confidence reflects how well retrieved passages actually support the answer — how relevant the matched chunks were and how completely they cover the question. It is not a measure of how fluent the answer sounds; it's a measure of evidence.
Two related notices can accompany an answer:
- Degraded search — retrieval ran in a reduced mode; consider re-asking.
- Unverified sources — some model references couldn't be matched to real passages and are flagged rather than cited.
Improving confidence
Low confidence is nearly always a content problem, not a phrasing problem:
- Ask more specifically (helps retrieval find the right passage).
- Ensure the covering document exists, is current, and is INDEXED.
- Watch Gap analysis for recurring weak spots and upload what's missing.
