Skip to main content
The Performance Dashboard provides a central view of your AI agent’s operational metrics. The Overview tab (shown by default) tracks conversation volume, user engagement, and quality indicators at a glance. The Dashboard has eight tabs, each focused on a different area:
Performance Dashboard showing key metrics, conversation volume chart, and distribution analytics

Performance Dashboard

​
Accessing the Performance Dashboard

Navigate to Dashboard in the sidebar. The Overview tab is displayed by default.
You need Admin or Account Manager permissions to access the Performance Dashboard.

​
Key Performance Metrics

The dashboard displays four primary metrics at the top, each showing the current value and change from the previous period:
Use period comparison (shown as +/- percentages) to identify trends. A sudden change may indicate an issue or improvement worth investigating.

​
Dashboard Components

​
Conversation Volume Chart

A bar chart showing the daily number of conversations over the selected time period. Use this to:
  • Identify peak usage days
  • Spot unusual spikes or drops in activity
  • Understand weekly patterns

​
Distribution Charts

​
Distribution by User Type

A pie chart showing conversations broken down by user permission level. This helps you understand:
  • Which user segments engage most with the agent
  • Whether certain user types have different usage patterns
  • How to prioritize improvements for specific audiences

​
Distribution by Agent

A pie chart showing how conversations are distributed across your agents (if you have multiple). This reveals:
  • Which agents handle the most traffic
  • Load balancing across agents
  • Opportunities to redirect traffic
The agent distribution chart only appears if you have multiple agents configured. If a conversation involves multiple agents, it may be counted for each.

​
Advanced Metrics

Below the main charts, the dashboard shows three additional metrics:

​
Understanding Advanced Metrics

Returning Users indicates user loyalty and ongoing engagement. A high number suggests:
  • Users find value in the agent
  • Good user retention
  • Opportunity to track satisfaction over time
Average Messages per Thread reveals conversation complexity:
  • Lower values (1-3): Quick, efficient resolutions
  • Higher values (5+): Complex issues or potential agent struggles
  • Sudden increases may indicate problems with response quality
First Contact Resolution Rate measures efficiency:
  • Higher rates mean users get answers quickly
  • Lower rates may indicate complex topics or knowledge gaps
  • Compare against escalation rate for a complete picture

​
Filtering Options

Use the dashboard header filters to customize your view:

​
Period Comparison

All metrics include period-over-period comparison:
  • Last 7 days compares to the 7 days before
  • Last 30 days compares to the 30 days before
  • Custom range compares to an equal period immediately prior
Changes are displayed as:
  • Green with arrow up: Positive trend (or negative for metrics where lower is better)
  • Red with arrow down: Negative trend
  • Gray: No significant change

​
Exporting Reports

​
PDF Export

Click the PDF export button in the dashboard header to generate a detailed report including:
  • All key metrics with period comparison
  • Volume chart visualization
  • Distribution charts
  • Advanced metrics
The PDF includes the date range and filters applied, making it suitable for sharing or archiving.

​
Best Practices

  1. Check daily: A quick look at the Overview tab helps catch issues early
  2. Monitor escalation rate: Rising escalation rates often indicate knowledge base gaps or agent instruction problems
  3. Track returning users: A growing base of returning users indicates the agent provides ongoing value
  4. Investigate anomalies: Sudden changes in any metric deserve investigation
  5. Compare periods strategically: Use “Last full week” for consistent week-over-week comparisons
  6. Drill down when needed: If you see concerning trends, use other dashboard tabs (Evaluation, Feedback, Knowledge) to diagnose the cause

​
Interpreting Common Patterns

​
High Volume, Low Quality

  • Many threads but low positive evaluation rate
  • Action: Review agent instructions and knowledge base quality

​
Low Volume, High Escalation

  • Few conversations but many escalations
  • Action: Check if users are finding the agent or if they’re immediately escalating

​
High First Contact Resolution, High Messages per Thread

  • Quick resolutions but verbose conversations
  • Action: Consider if agent responses can be more concise

​
Declining Returning Users

  • Fewer users coming back
  • Action: Analyze feedback and evaluate whether the agent is meeting user needs