Conversation Insights

Conversation Insights provides comprehensive analytics about your customer conversations, helping you understand session patterns, agent performance, customer sentiment, and conversation distribution.

Overview

Conversation Insights gives you visibility into:

• Session Counts: Total conversations, unassigned sessions, and agent assignments
• Agent Performance: Human agent metrics including response times and handovers
• Label Distribution: How conversations are categorized by labels
• Sentiment Analysis: Customer sentiment breakdown across conversations
• Traffic Patterns: When conversations happen throughout the week

Accessing Conversation Insights

1. Navigate to Insights in the left sidebar
2. Click on Conversations (or it will be selected by default)
3. The Conversation Insights dashboard will load

Filtering Options

Time Range

Select a time range to analyze:

• Last 7 days (default) - View the past week
• Today - Current day's data
• Yesterday - Previous day's data
• This month - Current month
• This year - Current year
• All time - Complete historical data

Channel Filter

Filter insights by specific channels:

1. Click the Channel Filter dropdown
2. Select one or more channels:
   • Instagram
   • Facebook
   • WhatsApp
   • WebChat
3. Leave empty to view all channels

Conversation Counts

The Conversation Counts section displays key metrics about your conversation sessions:

Metrics Shown

• Total Sessions: All conversation sessions in the selected time range
• Unassigned Sessions: Conversations not yet assigned to an agent
• AI Agents: Sessions handled by AI
• Human Agents: Sessions assigned to human agents
  • Shows "Unreplied" count for human-assigned conversations

Understanding the Metrics

• Live Updates: All counts update in real-time (indicated by "Live" badge)
• Unreplied Count: For human agents, shows how many conversations haven't been replied to yet
• Auto-Refresh: Data refreshes every 2 seconds automatically

Agent Performance

:::info Feature Flag Agent Performance is available when the agent-performance-analytics feature flag is enabled. :::

The Agent Performance section shows detailed metrics for your human agents.

Label Distribution

The Label Distribution chart shows how your conversations are categorized by labels.

Understanding the Chart

• Visual Representation: Bar chart showing label distribution
• Percentage Breakdown: Each label shows its percentage of total conversations
• Sorted by Count: Labels are sorted by frequency (highest first)

Use Cases

• Identify Common Topics: See what customers are asking about most
• Track Trends: Monitor how label distribution changes over time
• Resource Planning: Understand which topics require more attention

Sentiment Distribution

The Sentiment Distribution chart analyzes customer sentiment across conversations.

Sentiment Categories

Sentiment analysis categorizes conversations as:

• Positive: Customers expressing satisfaction or positive emotions
• Neutral: Standard, factual conversations
• Negative: Customers expressing dissatisfaction or concerns

Understanding the Chart

• Visual Breakdown: Bar chart showing sentiment distribution
• Percentage View: See what percentage of conversations fall into each category
• Real-Time Analysis: Sentiment is analyzed automatically for each conversation

Use Cases

• Customer Satisfaction: Track overall customer sentiment
• Issue Identification: Quickly spot negative sentiment trends
• Improvement Tracking: Monitor sentiment changes over time

Session Traffic

The Session Traffic heatmap visualizes when conversations happen throughout the week.

Understanding the Heatmap

• Days of Week: Left column shows days (Monday through Sunday)
• Hours of Day: Bottom row shows 24-hour periods (0-1, 1-2, etc.)
• Color Intensity:
  • Light green: Lower activity
  • Medium green: Moderate activity
  • Dark green: High activity
  • Gray: No activity

Using Traffic Data

• Peak Hours: Identify when you receive the most conversations
• Staffing Planning: Plan agent schedules based on traffic patterns
• Response Optimization: Focus resources during high-traffic periods
• Hover for Details: Hover over any cell to see exact session count

Interpreting Patterns

• Weekday vs Weekend: Compare activity across different days
• Time Zones: Consider your customers' time zones when analyzing patterns
• Seasonal Trends: Track how patterns change over time

Best Practices

Regular Monitoring

• Daily Check: Review conversation counts daily
• Weekly Analysis: Analyze sentiment and label distribution weekly
• Monthly Review: Review traffic patterns monthly for staffing decisions

Actionable Insights

• High Unassigned Count: Consider adding more agents or improving AI responses
• Negative Sentiment Trends: Investigate root causes and improve processes
• Peak Traffic Times: Ensure adequate coverage during busy periods
• Slow Response Times: Provide training or additional resources

Data-Driven Decisions

• Resource Allocation: Use traffic patterns to schedule agents
• Training Focus: Address topics with high negative sentiment
• Process Improvement: Identify bottlenecks from agent performance data

Troubleshooting

No Data Showing

Problem: Insights show no data or empty states

Solutions:

• Check your time range selection
• Verify you have conversations in the selected period
• Ensure channels are properly connected
• Check that conversations have been created

Data Not Updating

Problem: Metrics show "Live" but don't seem to update

Solutions:

• Refresh the page
• Check your internet connection
• Verify conversations are being created
• Wait a few seconds (updates happen every 2-10 seconds)

Missing Agent Performance

Problem: Agent Performance section not visible

Solutions:

• Check if the feature flag is enabled
• Verify you have human agents assigned to conversations
• Ensure conversations exist in the selected time range

Related Documentation

• Marketing Insights - Campaign analytics
• Intelligence Overview - AI-powered features
• Channels Overview - Channel connections