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

# Workflow Runs

> Monitor complex, multi-step LLM workflows with execution timelines and trace debugging.

While the API Logs tab shows individual atomic requests, **Workflow Runs** are designed for complex applications that combine multiple AI tasks into a single workflow.

Navigate to **Logs** in the sidebar and select the **Workflow Runs** tab.

<Frame>
  <video autoPlay loop muted playsInline src="https://mintcdn.com/traceport/ZXBNThc7kv_3RvjA/images/logs-workflow.mp4?fit=max&auto=format&n=ZXBNThc7kv_3RvjA&q=85&s=8dc99314004fc545a4b1088ce1ba59c9" className="w-full rounded-lg" data-path="images/logs-workflow.mp4" />
</Frame>

## When to Use Workflow Runs

<Info>
  Use Workflow Runs when building **autonomous agents**, **logic routers**, or **multi-step chains** — scenarios where multiple LLM prompts execute to fulfill a single end-user request.
</Info>

## Workflow Detail View

Clicking a workflow entry opens a detail panel showing:

* **Workflow name** and execution timestamp
* **Total duration** and **aggregate cost** across all steps
* **Execution steps list** with per-step status, model, tokens, and cost

## Trace Debugger

Click **View Full Trace** to open the interactive trace debugger, which provides a rich visual representation of your workflow execution:

The trace debugger includes:

<AccordionGroup>
  <Accordion title="Execution Timeline">
    A top-down visual graph showing when each span (step) occurred and how long it took. This helps diagnose blocking code vs fast async operations.
  </Accordion>

  <Accordion title="Span Tree">
    A hierarchical tree of all spans in the workflow. The **root node** represents the total workflow, and **child nodes** represent individual steps like API calls, retrieval functions, or model completions.
  </Accordion>

  <Accordion title="Span Details">
    Click any span to see its detailed metrics: duration, model used, input/output tokens, cost, and any metadata attributes.
  </Accordion>

  <Accordion title="Attributes Panel">
    A metadata panel showing key-value pairs, node types, routing expressions, and other contextual information for each span.
  </Accordion>
</AccordionGroup>

<Tip>
  The trace debugger is especially useful for identifying bottlenecks in your AI workflows — look for spans with unexpectedly high durations in the timeline view.
</Tip>