> ## Documentation Index
> Fetch the complete documentation index at: https://docs.diga.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Call Traces

> Visualize the complete flow of a call with distributed traces to analyze timing and behavior

## What are traces?

Traces let you see the complete flow of a call broken down into individual steps called **spans**. Each span represents a specific operation — like a conversation turn, an agent response, or a tool execution — with its exact duration.

While [call logs](/en/deployment/call-logs) tell you **what happened**, traces tell you **how long each step took** and **how they relate to each other**.

## Trace structure

Each call generates a trace with a hierarchical structure. The root span represents the entire session, and individual steps are nested within it:

```
Agent session (full call)
├── User turn
│   └── User speaking
├── Agent turn
│   ├── LLM generation (AI response)
│   ├── Voice synthesis (text to audio)
│   ├── Tool executed (if applicable)
│   └── Agent speaking
├── Path transition (if using conversational paths)
└── ...more turns
```

## Span types

| Span                | What it represents                                    |
| ------------------- | ----------------------------------------------------- |
| **Agent session**   | The entire call from start to finish                  |
| **User turn**       | A complete turn of the contact speaking               |
| **Agent turn**      | A complete turn of the agent responding               |
| **LLM generation**  | The time the AI took to generate a response           |
| **Voice synthesis** | The time to convert text to audio                     |
| **Tool executed**   | The execution of a tool (integration, transfer, etc.) |
| **Path transition** | A node change in agents with conversational paths     |

## Information available in each span

Depending on the span type, you can see different attributes:

### Conversation turns

| Attribute          | Description                               |
| ------------------ | ----------------------------------------- |
| **User message**   | What the contact said                     |
| **Agent response** | What the agent replied                    |
| **Interrupted**    | Whether the contact interrupted the agent |

### Executed tools

| Attribute     | Description                       |
| ------------- | --------------------------------- |
| **Tool name** | Which tool was executed           |
| **Arguments** | The parameters it was called with |

### Path transitions

| Attribute            | Description                             |
| -------------------- | --------------------------------------- |
| **Source node**      | Which node the transition was made from |
| **Destination node** | Which node the agent moved to           |
| **Node type**        | The type of the destination node        |

## Use cases

<CardGroup cols={2}>
  <Card title="Diagnose slow calls" icon="gauge">
    Identify which step is taking the longest: AI generation? Voice synthesis? An external integration?
  </Card>

  <Card title="Verify conversational flows" icon="route">
    Confirm that conversational paths follow the expected transitions between nodes.
  </Card>

  <Card title="Analyze tools" icon="wrench">
    Review which tools were executed, with what parameters, and how long they took.
  </Card>

  <Card title="Understand interruptions" icon="hand">
    Detect when contacts interrupted the agent and how it responded.
  </Card>
</CardGroup>