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

> ## Agent Instructions
> To act on Atlan objects, use the Atlan MCP server at https://api.atlan.com/mcp or the atlanai CLI; `atlanai --map json` prints its command map. Run a read-only identity check before any write.
> The docs MCP server at /mcp searches these docs only. It cannot read or change Atlan objects.
> SDK packages: Python `atlanai` (PyPI) and TypeScript `@atlanai/sdk` (npm). Show Python first, then TypeScript.

# Trace inspection

> Find execution evidence associated with an agent or session.

# Inspect agent traces

Agent and session trace views provide execution evidence for the selected
scope. Start with the agent profile when you know which agent you need to
inspect.

## Inspect a recent run

1. Open the agent profile and select **Usage**.
2. In **Recent runs**, select the run that matches the time and outcome you
   are investigating.
3. Start with **Highlights** to review the prompt, key decisions, errors, and
   response.
4. Select **Full trace** when you need each recorded step. Use the filters to
   narrow the view without changing the original run.

The run view explains when it is trimmed to the selected agent or skill. Treat
missing fields as unavailable, not as proof that nothing happened.

<Note>
  Trace availability depends on the execution data and your access to the
  selected agent or workspace.
</Note>