Skip to main content

​
Analytics Dashboard for Voice AI

Coval's Dashboard Monitor, analyze, and optimize your voice AI performance with real-time insights and drill-down capabilities. Whether you’re tracking simulation results, monitoring live system health, or analyzing conversation patterns, our dashboard provides the tools you need to make data-driven decisions.

​
Flexible Dashboard

  • Multiple Configurable Dashboards: Organize and switch between dashboards instantly to monitor different aspects of your voice AI system
  • Intuitive Layout: Rearrange widgets, automatically adapts to any screen size, resize widgets, and automatically saved

​
Widget Configuration with Live Preview

Widget Configuration
  • Choose from all available metrics on Coval’s platform
  • See your changes applied immediately in the live preview pane
  • Filter widgets by specific agent IDs for focused monitoring
  • Add multiple aggregation dimensions (Agent + Persona combinations)

​
Widget Library

​
Bar Charts

  • Compare performance across categories with regular or stacked visualizations
  • Perfect for analyzing success rates, error distributions, or agent performance comparisons
  • Smart color-coding for binary metrics (Yes/No scenarios)

​
Line Charts

  • Track trends over time with multi-series support
  • Built-in outlier detection to quickly spot anomalies
  • Ideal for monitoring response times, call volumes, or quality scores

​
Review Management

Monitor and manage your human review assignees directly from the dashboard. These widgets give you a centralized view of review progress and activity across all your projects.

​
Threshold / Target Zone Visualization

Display your org-level metric thresholds directly on dashboard charts to quickly assess whether performance is within acceptable bounds.
  • Enable it: Toggle “Show target zone” in the widget configuration panel for success rate bar or average line chart widget
  • Line charts: renders a shaded “fail zone” above or below the threshold line, making out-of-range periods immediately visible
  • Bar charts: renders a dashed reference line at the threshold value for at-a-glance comparison against each bar
  • The threshold value is pulled automatically from the custom threshold set in the metrics page

​
Question Monitoring

  • Track unanswered questions and conversation gaps
  • Identify areas where your AI needs improvement
  • Monitor user satisfaction and engagement patterns

​
Filtering & Analysis

​
Multi-Dimensional Aggregation

  • Agent-Level Analysis: Compare performance across different AI agents
  • Persona-Based Insights: Analyze how different conversational personas perform
  • Combined Analysis: Mix and match agents and personas for comprehensive views
  • Binary Metric Support: Automatic Yes/No breakdowns for quality metrics

​
Intelligent Date Range Management

  • Per-Widget Control: Set different time periods for each widget
  • Global Overrides: Apply date ranges across all widgets instantly
  • Smart Presets: Today, Yesterday, Last 7/30/90 days, Year-to-date
  • Custom Ranges: “Last N days/weeks/months” or specific date periods

​
Metadata Filtering

Filter your dashboard data using custom metadata fields attached to your simulations or live calls. This allows you to segment your analytics by any attributes you track—such as customer tier, campaign ID, region, or experiment variant.
Metadata filters work with any key-value pairs you’ve included in your simulation or monitoring data. Values are matched exactly, and multiple filters are combined with AND logic.
How it works:
  • Key Selection: Choose from existing metadata keys or enter a custom key name
  • Value Filtering: Select from suggested values or type your own custom value
  • Search Support: Quickly find values by typing—results filter as you type
  • Multiple Filters: Add several metadata filters to narrow down your analysis
Common Use Cases:
  • Compare performance across different customer segments
  • Analyze A/B test results by experiment variant
  • Filter by deployment environment (staging vs. production)
  • Segment by geographic region or language

​
Powerful Filtering Options

  • Filter by agent types, conversation attributes, and metadata fields
  • Real-time filter application without page refresh
  • Save and reuse common filter combinations

​
Deep Dive Analysis

​
Focus Mode

  • Click any data point to enter full-screen analysis mode
  • 50/50 split view: chart on left, detailed run data on right
  • Seamless transition back to overview dashboard

​
Run Details Investigation

  • Drill down from aggregate charts to individual conversation data
  • See exactly which calls contributed to each data point
  • Investigate outliers and anomalies at the source level
  • Full context for root cause analysis
Run Details Investigation

​
Smart Data Bucketing

  • Automatic time bucket optimization based on data density
  • Calendar-aware grouping (hours, days, weeks, months)
  • Timezone-aware calculations for accurate reporting
Ready to transform your voice AI analytics? Our dashboard platform provides the insights and tools you need to monitor, analyze, and optimize your voice AI performance with confidence.