Quality loop
Answers improve through review
Dchat closes the answer-quality gap with feedback, unanswered searches, knowledge revision packets, usage review, and escalation analysis instead of claiming self-learning automation.
Approved knowledge
AI response quality starts with enabled articles, approved policy wording, and source boundaries operators can inspect.
- Enabled articles
- Source boundaries
- Revision history
Feedback and misses
Thumbs-down answers, unresolved intents, top unanswered searches, and stale-knowledge misses become review inputs for the team.
- AI feedback
- Unanswered searches
- Knowledge gaps
Cost and prompt review
Usage review separates model spend, prompt waste, knowledge gaps, and tool-call risk before pricing or ROI claims are made.
- Usage export
- Prompt waste
- Provider cost
Review signals beat unsupported self-learning claims.
| Capability | Status | Detail |
|---|---|---|
| Knowledge base articles | Available | Enabled articles can ground AI context while article snapshots preserve what changed over time. |
| Article feedback | Available | Visitor and operator feedback can identify stale, confusing, or missing article coverage. |
| Top unanswered searches | Available | Unanswered help-center searches become content-gap signals for future articles and policy fixes. |
| Knowledge revision packets | Available | Revision packets support human drafting, rollback review, and procurement-friendly change evidence. |
| AI response feedback | Available | Feedback on AI answers helps prioritize prompt, article, and escalation review without claiming verified resolution learning. |
| Multi-source ingestion parity | Not claimed | Do not claim broad Drive, Notion, Dropbox, Confluence, YouTube, or past-interaction ingestion until those connectors ship with proof. |
| Self-learning automation | Not claimed | Dchat should not claim autonomous retraining, automated prompt rollback, or verified outcome learning from review signals alone. |
The quality story is deliberately human-reviewed: use signals to improve approved knowledge before expanding automation.