Quality scorecards
Set the criteria, weights and instructions the AI uses to score every conversation.
Scorecards
Assigned by category and interface
- Active
- Active
- Active
- Draft
Content quality v1 criteria
Weights must total 100% · currently 100%
| Criterion | Weight | Scoring instruction | |
|---|---|---|---|
| Brand kit | 20% | Colours, logo and typeface match the brand kit for this brand | |
| Right asset | 25% | Image or footage shows the exact product and variant the brief asked for | |
| Offer accuracy | 25% | Price, dates and terms match the approved offer sheet | |
| Audience fit | 10% | Message suits the segment (e.g. renewal due, recent visitor) | |
| Compliance | 15% | Required disclaimers and opt-out text present | |
| Channel format | 5% | Length, size and aspect ratio fit the channel |
Auto-fail rules
Any match scores the conversation zero
- Payment card read back aloud
- No recording disclosure on an outbound call
- Rude or dismissive language
- Promise made outside published policy
Who gets reviewed
Sampling rules per interface
- Voice
- 100% AI scored · 5% human review
- Chat
- 100% AI scored · 3% human review
- 100% AI scored · 2% human review
- Escalations
- Always human reviewed