- Dashboards – high-level metrics and trends
- Conversation review – transcript-level inspection and tagging
Quick reference
| I need to… | Action | Time estimate |
|---|---|---|
| Check daily performance | Standard dashboard → Review key metrics | 5 min |
| Listen to recent calls | Conversation Review → Filter → Listen | 10-20 min |
| Find knowledge gaps | Analytics → Unhandled queries | 10 min |
| Review a specific topic | Conversation Review → Filter by topic | 5 min |
| Export call data | Conversation Review → Export CSV/JSON | 5 min |
| Tag problematic calls | Open call → Add category/annotation | 2 min |
| Check containment rate | Standard dashboard → Containment metric | 2 min |
| Review safety issues | Safety dashboard → Check flags | 10 min |
Pick the right dashboard
| Use case | Go here |
|---|---|
| Daily health check (calls, containment, AHT) | Standard dashboard |
| Risk or policy compliance | Safety dashboard |
| Anything bespoke (e.g. bookings, revenue) | Custom dashboards – ask your CSM if you do not see one |
Example workflow: did my FAQ edit improve containment?
- Open the Standard dashboard.
- Set the date range:
- From = the day you promoted the change
- To = today
- Check Containment rate.
- If it went up → good sign
- If it dropped or stayed flat, drill down to conversations (next section)
Review conversations
- Go to Analyze → Conversations → Review.
- Use filters:
- Date range – same window you used in the dashboard
- Topic – select the FAQ you edited
- Click a call to open the transcript.
- Check:
- Did the agent serve the new answer?
- Did the caller stay in self-service or ask for a human?
- If something looks off, tag it.
Tagging and annotations
At the bottom-right of a transcript:- Category – pick a label like Needs KB fix or Escalated unnecessarily
- Annotation – flag Wrong transcription or Missing topic
Export transcripts (optional)
Need raw data for deeper analysis?- In Conversations, select your filters.
- Click Export → CSV or JSON.
- You’ll get a download link with call metadata and the full transcripts.
Common workflows
Daily performance check
- Open Standard dashboard
- Review key metrics vs. baseline:
- Call volume
- Containment rate
- Average handle time
- Handoff rate
- Identify any anomalies
- Drill into Conversation Review if needed
Weekly quality review
- Filter Conversation Review to last 7 days
- Listen to 5-10 sample calls
- Mix successful and unsuccessful calls
- Tag issues for follow-up
- Identify patterns and improvement opportunities
- Update knowledge or settings as needed
Investigating a spike in handoffs
- Go to Standard dashboard
- Identify when handoff rate increased
- Go to Conversation Review
- Filter by date range and handoff = true
- Review handoff reasons
- Identify common patterns
- Add missing knowledge or adjust handoff rules
Related pages
- Performance monitoring - Detailed performance analysis
- Health checks - Proactive monitoring routines
- Standard dashboard - Key metrics overview
- Conversation Review - Transcript inspection
- Call data - Accessing raw call data
When to escalate
| Situation | Who to contact |
|---|---|
| Metrics flat after multiple tweaks | Your CSM – may need flow changes |
| Consistent ASR errors | PolyAI support – include call IDs |
| Dashboard missing a metric you need | Analytics team via your CSM |
| Safety dashboard shows spikes | Raise with PS immediately |
Next steps
- Check the standard dashboard now to make sure your latest edit had the intended effect.
- If you’re comfortable with bulk analysis, explore Smart Analyst for batched call scoring.
- Set up health checks for proactive monitoring.