Skip to main content
The General view on your metrics dashboard covers chat channels-Web, Slack, and WhatsApp. In chat, conversations resolve in a single session, so Resolution Rate and CSAT are your primary success metrics. Use the channel filter to isolate specific chat channels.
For ticketing channels (Zendesk, Salesforce), see Ticketing Performance. Ticketing uses different primary metrics because human finishing is an expected part of the workflow.

Conversation Status

Every conversation has a status that indicates how it concluded.
StatusColorMeaning
ResolvedGreenThe AI or a human operator successfully answered the user’s question
UnresolvedRedThe question went unanswered or received an inadequate response
EscalatedPurpleThe system handed the conversation off to a human agent, automatically or on request

Metrics

CardDescriptionInterpretation
MessagesTotal user messages exchanged in the selected timeframeRising messages with stable conversations means longer discussions
ConversationsUnique conversation threads startedSpikes may indicate product issues or marketing campaigns
Unique UsersDistinct users who started conversationsCompare to conversation count to gauge repeat contact rate
CSAT ScorePercentage of satisfied customers (4–5 star ratings) out of all rated conversations80%+ is excellent, below 60% needs urgent attention
Resolution RatePercentage of conversations resolved without escalation or abandonment80%+ indicates strong autonomous performance

Charts and Use Cases

ChartUse case
Conversation StatusTrack resolution trends over time; correlate dips with deployments or knowledge updates
Conversation RatingCheck satisfaction distribution; a healthy profile peaks at 4–5 stars with under 10% at 1–2 stars
Message VolumeSpot changes in conversation complexity-average messages per conversation reveals efficiency (2–4 is quick, 9+ suggests struggles)
AI Involvement RateMeasure your automation mix; target 60–70% fully autonomous for a mature deployment
handoffFind peak escalation times and the most common reasons the AI hands off to humans
Answer CompletenessSurface knowledge gaps directly-a high “no answer” percentage points to missing content
User SentimentDetect frustration trends; rising negative sentiment with low CSAT means the AI’s responses frustrate users
User Rating TrendConfirm that improvements sustain over time-look for upward-sloping 4–5 star lines
User LanguageIdentify whether non-English traffic with low satisfaction signals a need for multilingual knowledge
Usage by PageFind high-traffic pages that generate many conversations-candidates for better self-service content
Knowledge Source UsageDetect underutilized knowledge sources and prioritize updates to frequently referenced ones
Conversation LengthFlag efficiency issues-many single-message conversations may mean disengagement, 9+ messages may mean the AI isn’t resolving
Activity heatmapsIdentify peak support hours for staffing and seasonal patterns
Hidden ConversationsMonitor spam detection accuracy and track abuse patterns

Identifying Issues

Find topics with low satisfaction. Filter conversations by topic and rating 1–2 to see where the AI struggles most. Cross-reference with the Resolution Status chart on the topics dashboard to quantify the problem. Spot knowledge gaps. The Answer Completeness chart shows how often the AI has no answer at all. Open those conversations and check the source attribution-”Used Sources (0)” means the AI fell back to general knowledge instead of your data. Create snippets to fill the gap. Understand escalation patterns. The handoff chart reveals when and why the AI escalates. Filter to escalated conversations and review whether escalations were necessary (complex issue) or avoidable (missing knowledge). Reduce avoidable escalations by adding the missing information. Track improvement after changes. After updating knowledge or guidance, use the date range filter to compare the affected topic’s metrics before and after. Look for rising resolution rates and CSAT on that topic.

Next Steps

  • Conversations - Review individual conversations to understand metrics in context
  • Ticketing Performance - Compare chat metrics to ticketing performance
  • Topics - Segment performance by topic to find improvement areas
  • Improve Answers - Use insights to refine knowledge and guidance