Skip to main content

​
Analytics Dashboard

Your analytics dashboard is your command center for monitoring AI agent performance. It aggregates data from test simulations, live calls, and alerts to give you a complete picture of how your agents are performing.

​
Why Analytics Matter

Without data, you’re flying blind. Analytics help you:
  • Catch problems early - See quality drops before customers complain
  • Validate improvements - Know if your changes actually work
  • Identify patterns - Understand which scenarios cause issues
  • Make decisions - Use data instead of guesswork
Example: Your dashboard shows Agent V1 scoring 15% lower on Friday afternoons. Investigation reveals a tool integration that’s slower during high-traffic periods.

​
Dashboard Overview

The analytics dashboard combines four key data sources:

Simulations

Test results from automated scenarios

Live Calls

Real-time production conversations

Call Logs

Historical conversation analysis

Alerts

Automated notifications for issues

​
Key Metrics

​
Agent Performance Scores

Track overall quality across all agents:
Navigate to Analytics to see:
  • Average scores by agent
  • Score trends over time
  • Performance by scenario type
  • Comparison across agent versions

​
Call Volume & Success Rate

Monitor how many calls your agents handle and how well they perform: 
curl https://api.chanl.ai/v1/analytics/volume \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "timeRange": "7d",
    "interval": "day"
  }'

{
  "totalCalls": 3421,
  "successRate": 94.2,
  "avgDuration": 4.3,
  "byDay": [
    {
      "date": "2024-01-15",
      "calls": 512,
      "successRate": 95.1,
      "avgScore": 88.2
    },
    ...
  ]
}

​
Alert Frequency

Track how often alerts are triggered: 
curl https://api.chanl.ai/v1/analytics/alerts \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "timeRange": "30d"
  }'

{
  "totalAlerts": 47,
  "byType": {
    "quality_drop": 23,
    "compliance_issue": 12,
    "timeout": 8,
    "error": 4
  },
  "trend": "decreasing"
}

​
Score Over Time

Visualize agent performance trends: 
const chanl = require('@chanl/sdk');

// Get 30-day trend data
const trends = await chanl.analytics.trends({
  metric: 'score',
  agents: ['agent-v1'],
  timeRange: '30d',
  interval: 'day'
});

console.log(trends);
/*
{
  agent: "agent-v1",
  dataPoints: [
    { date: "2024-01-01", score: 85.2 },
    { date: "2024-01-02", score: 86.1 },
    { date: "2024-01-03", score: 87.3 },
    ...
  ],
  trend: "improving",
  changePercent: +4.2
}
*/

​
Persona-Specific Analysis

See how agents perform with different customer types: 
curl https://api.chanl.ai/v1/analytics/by-persona \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "agent": "agent-v1",
    "timeRange": "30d"
  }'
Results show strengths and weaknesses: 
{
  "agent": "agent-v1",
  "byPersona": [
    {
      "persona": "Analytical Customer",
      "avgScore": 92.1,
      "totalInteractions": 234,
      "status": "strength"
    },
    {
      "persona": "Frustrated Customer",
      "avgScore": 76.4,
      "totalInteractions": 189,
      "status": "needs_improvement"
    },
    {
      "persona": "Confused Customer",
      "avgScore": 88.3,
      "totalInteractions": 156,
      "status": "good"
    }
  ]
}

​
Comparative Analysis

​
Agent Comparison

Compare multiple agents side-by-side: 
curl https://api.chanl.ai/v1/analytics/compare \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "agents": ["agent-v1", "agent-v2"],
    "timeRange": "30d",
    "metrics": ["score", "duration", "successRate"]
  }'

{
  "comparison": {
    "agent-v1": {
      "avgScore": 87.3,
      "avgDuration": 4.2,
      "successRate": 93.1
    },
    "agent-v2": {
      "avgScore": 91.5,
      "avgDuration": 3.8,
      "successRate": 95.7
    }
  },
  "winner": "agent-v2",
  "advantages": [
    "+4.2 points higher score",
    "10% faster resolution",
    "+2.6% higher success rate"
  ]
}

​
Before/After Analysis

Measure impact of changes: 
const chanl = require('@chanl/sdk');

// Compare performance before and after a change
const impact = await chanl.analytics.compareTimeRanges({
  agent: 'agent-v1',
  before: {
    start: '2024-01-01',
    end: '2024-01-15'
  },
  after: {
    start: '2024-01-16',
    end: '2024-01-30'
  }
});

console.log(impact);
/*
{
  metric: "avgScore",
  before: 85.2,
  after: 89.7,
  change: +4.5,
  changePercent: +5.3,
  significant: true
}
*/

​
Scenario Performance

​
Success Rate by Scenario

Identify which scenarios are most challenging: 
curl https://api.chanl.ai/v1/analytics/scenarios \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "timeRange": "30d",
    "sortBy": "successRate",
    "order": "asc"
  }'

{
  "scenarios": [
    {
      "name": "Complex Technical Issue",
      "successRate": 72.3,
      "avgScore": 76.1,
      "totalRuns": 134,
      "status": "needs_improvement"
    },
    {
      "name": "Price Objection",
      "successRate": 86.7,
      "avgScore": 84.2,
      "totalRuns": 298,
      "status": "good"
    },
    {
      "name": "Simple Refund",
      "successRate": 96.4,
      "avgScore": 93.8,
      "totalRuns": 456,
      "status": "excellent"
    }
  ]
}

​
Custom Reports

​
Creating Reports

Generate custom analytics reports: 
const chanl = require('@chanl/sdk');

const report = await chanl.analytics.createReport({
  name: "Weekly Quality Report",
  timeRange: "7d",
  metrics: [
    "avgScore",
    "successRate",
    "totalCalls",
    "alertCount"
  ],
  groupBy: ["agent", "scenario"],
  filters: {
    minScore: 0,
    includeSimulations: true,
    includeLiveCalls: true
  }
});

// Schedule recurring report
await chanl.analytics.scheduleReport({
  reportId: report.id,
  frequency: "weekly",
  dayOfWeek: "monday",
  time: "09:00",
  recipients: ["team@company.com"]
});

​
Export Options

Export data for external analysis: 
curl https://api.chanl.ai/v1/analytics/export \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "format": "csv",
    "timeRange": "30d",
    "metrics": ["score", "duration", "persona", "scenario"]
  }' \
  > analytics_export.csv

​
Real-Time Monitoring

​
Live Metrics

Monitor current performance in real-time: 
const chanl = require('@chanl/sdk');

// Subscribe to real-time metrics
const stream = chanl.analytics.stream({
  agents: ['agent-v1'],
  metrics: ['currentCalls', 'avgScore', 'alerts']
});

stream.on('update', (data) => {
  console.log('Current calls:', data.currentCalls);
  console.log('Current avg score:', data.avgScore);
  console.log('Active alerts:', data.alerts.length);
});

stream.on('alert', (alert) => {
  console.log('🚨 New alert:', alert.message);
});

​
Best Practices

1

Review Daily

Check your dashboard every morning to catch issues early.
2

Set Baselines

Establish what “good” looks like for each metric so you can spot anomalies.
3

Track Trends, Not Points

Don’t panic over single data points. Look at trends over days or weeks.
4

Correlate Events

When you see changes in metrics, check what changed in your agent configuration.
5

Export Regularly

Keep historical exports for long-term analysis and reporting to stakeholders.

​
Troubleshooting

Problem: Analytics showing incomplete or no dataSolutions:
  • Verify agents are connected and active
  • Check if simulations or calls are actually running
  • Confirm date range filter includes relevant data
  • Try refreshing or clearing browser cache
Problem: Different dashboards showing different numbersSolutions:
  • Check time zone settings across dashboards
  • Verify filters are consistent
  • Ensure comparing same time ranges
  • Review what’s included (simulations vs live calls vs both)
Problem: Analytics taking too long to loadSolutions:
  • Reduce date range to last 30 days instead of all-time
  • Limit number of agents being analyzed
  • Use API with specific filters instead of UI
  • Contact support if performance issues persist

​
What’s Next?

Live Calls

Monitor ongoing conversations in real-time

Call Logs

Analyze historical conversation data

Set Up Alerts

Configure automated notifications

API Reference

Complete API documentation for analytics