tools-only Continuous Improvement
Conversation design is never "done." Production usage reveals gaps that testing cannot fully predict.
The Iteration Cycle
┌─────────┐
│ MONITOR │ Track KPIs, review dashboards
└────┬────┘
▼
┌─────────┐
│ ANALYZE │ Identify misrouted utterances, low-CSAT sessions
└────┬────┘
▼
┌─────────┐
│ FIX │ Update instructions, adjust classifications, add actions
└────┬────┘
▼
┌─────────┐
│ RETEST │ Run regression tests, add new test cases
└────┬────┘
▼
┌─────────┐
│ DEPLOY │ Push changes, monitor for improvement
└────┬────┘
│
└──────→ (back to MONITOR)
Key Performance Indicators
| KPI | Target | Measurement |
|---|---|---|
| Resolution Rate | >70% | Conversations resolved without escalation |
| Classification Accuracy | >90% | Utterances routed to correct topic |
| Avg Turns to Resolution | <6 | Efficiency of information gathering |
| Customer Satisfaction | >4.0/5 | Post-conversation survey |
| Escalation Rate | <30% | Percentage escalated to human |
| Containment Rate | >65% | Percentage staying within agent |
| First Contact Resolution | >60% | Resolved in first session |
| Error Recovery Rate | >80% | Errors gracefully recovered |
Utterance Analysis Process
- Export unmatched utterances — Pull from Agentforce analytics
- Categorize — New intent? Phrasing gap? True out-of-scope?
- Update — Add new utterances to library, adjust classifications if needed
- Test — Verify changes don't break existing routing
- Deploy — Push updated agent configuration
- Schedule — Repeat weekly for first month, then bi-weekly
Deep Dive: Quality Metrics | Template: Improvement Plan