Analyze completed calls in detail. The Call Inspector shows transcripts, audio recordings, timeline events, LLM prompts/responses, tool executions, and latency breakdowns for every conversation. What you’ll learn: Accessing the inspector, understanding sections, and navigating to detailed analysis.Documentation Index
Fetch the complete documentation index at: https://docs.blackbox.dasha.ai/llms.txt
Use this file to discover all available pages before exploring further.
Screenshots may differ from current UI version.
Access the Call Inspector
- From Calls page
- From Dashboard
- From Agent details
- From API
- Go to Calls in the sidebar
- Select the Past Calls tab
- Find your call in the list
- Click the Inspect button
- Inspector opens in a new tab
Inspector sections
| Section | Contents | Use case | Learn more |
|---|---|---|---|
| Overview | Call metadata, status, duration | Quick context | Below |
| Transcript | Full conversation with timestamps | Conversation review | — |
| Audio | Recording playback | Voice quality | Common Issues |
| LLM | Prompts, responses, tokens | Model debugging | Common Issues |
| Tools | Function calls and responses | Integration debugging | Common Issues |
| Timeline | Chronological events | Latency analysis | — |
Call overview
The inspector header displays key call metadata at a glance.Header information
| Field | Description | API field |
|---|---|---|
| Call ID | Unique identifier (UUID) | callId |
| Status | Completed, Failed, or Canceled | callStatus |
| Agent | Agent ID and name | agentId |
| Duration | Total conversation length | durationSeconds |
| Endpoint | Phone number or “web” | endpoint |
| Call Type | Connection type | callType |
Call type values
| Type | API value | Description |
|---|---|---|
| Inbound phone | InboundAudio | Incoming phone call |
| Outbound phone | OutboundAudio | Outgoing phone call |
| Web voice | WebCall | Browser WebRTC call |
| Web chat | Chat | Text conversation |
Timestamps
| Timestamp | Meaning |
|---|---|
| Created | When the call was scheduled |
| Started | When the conversation began |
| Completed | When the call ended |
Custom data
AnyadditionalData passed during call creation appears as formatted JSON:
Example: Call overview with custom data
Example: Call overview with custom data
Quick analysis
Check conversation quality
- Open the Transcript section
- Scan for red flags: repetition, off-topic responses, user frustration
- Listen to audio for voice quality issues
- Review LLM logs if responses seem wrong
Check performance
- Open the Timeline section
- Look at latency breakdown: STT, LLM, TTS
- Identify the slowest component
- Compare against targets (under 2s total)
Debug failed calls
- Check Status in the header
- Look for error messages in system events
- Review LLM logs for API errors
- Check tool executions for failures
Best practices
During testing
- Review 5-10 test calls before enabling an agent for production
- Verify all conversation paths work as expected
- Check that tool executions succeed
- Confirm latencies are within acceptable ranges
In production
- Sample 5-10% of calls randomly for quality review
- Review all failed calls within 24 hours
- Track performance trends over time
- Monitor tool success rates
Data privacy
- Redact PII before sharing transcripts externally
- Comply with call recording consent laws in your jurisdiction
- Implement data retention policies
- Secure access to recordings with proper authentication
What’s next
Call History
View and filter past calls
Troubleshooting
Common issues and solutions
Common Issues
Solutions for frequent problems
Concurrency Monitoring
Monitor active calls and capacity