> ## 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.

# Traces

> Understand execution evidence for agents, sessions, and skills.

Traces record execution evidence that can be associated with agents, sessions,
and skills when the required attribution is present.

## Core flows

<CardGroup cols={2}>
  <Card title="Attribution" icon="link" href="/registry/traces/concepts/attribution">
    Understand how trace fields connect activity to agents and skills.
  </Card>

  <Card title="Verify ingestion" icon="badge-check" href="/registry/traces/concepts/verify-ingestion">
    Confirm that trace data appears in the intended scope.
  </Card>
</CardGroup>

## Verification

A successful request or exporter configuration does not prove that a trace is
visible in the intended workspace. Every ingestion guide must end with a read
or product check that confirms the matching trace and attribution. When you
know the agent, open its **Usage** tab and select the matching item in
**Recent runs**. Use the trace timestamp and recorded attribution to confirm
that you found the intended execution.

## Data handling

Trace examples and screenshots must exclude tokens, customer data, private
prompts, internal hosts, and production responses.