Auto QA (Insight Recipe)
Auto QA evaluates conversations using your QA scorecard and produces: - an overall QA score (and optionally section/question scores) - evidence-based explanations for each evaluation
Where Auto QA appears
- Conversation Details (QA results)
- QA dashboards (score distribution and trends)
- Search filters (e.g., QA score < threshold)
Configuration checklist
- Create or verify your QA Scorecard (sections/questions)
- Enable/configure the Auto QA AI Task
- Configure filters (which conversations to evaluate)
- Test in Playground and calibrate against human QA
- Roll out dashboards and workflows
See: - Auto QA (Scorecards and Tasks) (configuration) - Playground and Validation Checklist (testing)
Auto QA Dashboard
Figure: Auto QA Dashboard showing overall score distribution and trends.
Auto QA Report View
Auto QA results are displayed in a dedicated QA tab on conversation details, showing:
- Overall score
- Section-by-section breakdown
- Per-question results with explanations
Figure: Auto QA report showing detailed results alongside the conversation transcript.
Users can provide feedback on Auto QA results if they disagree with the scoring:
Figure: Feedback option for flagging incorrect results.


