> ## 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 SDK. To install or publish skills from a terminal, use the `aireg` CLI; `aireg --map json` prints its command map. The `atlanai` CLI is deprecated. 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.
> These docs cover Atlan AI Registry, Atlan's hosted product. The AI registry specification and aireg CLI are maintained separately. /open-source lists publicly reachable signed installers and explains that the source repository and hosted CLI reference currently require GitHub access. Do not claim the repository or its reference docs are publicly accessible. Use these docs for Atlan-specific setup such as the adapter, sign-in and workspaces.

# Agent monitoring

> Follow recorded agent runs, evaluate their quality, and investigate token usage and cost.

Agent monitoring connects three kinds of evidence: what an agent did, how well it did it, and what its recorded work cost. Start with the question you need to answer, then follow a run back to its trace.

<CardGroup cols={3}>
  <Card title="Traces" icon="diagram-project" href="/registry/traces/index">
    Send execution records, group them into sessions, and inspect model calls, tool calls, and errors.
  </Card>

  <Card title="Evals" icon="flask" href="/evals/index">
    Test fixed cases before a release and score recorded production sessions.
  </Card>

  <Card title="FinOps" icon="chart-line" href="/finops/index">
    Compare spend and tokens across agents, then check the rates behind a run's cost.
  </Card>
</CardGroup>

## Choose an investigation

| Question | Start with | Follow through to |
| - | - | - |
| Why did this run fail? | The agent's **Sessions** or **Usage** tab | [Inspect a recorded run](/registry/traces/how-tos/inspect-runs) |
| Did a change improve the answers? | A fixed dataset and an experiment | [Review experiment results](/evals/how-tos/review-experiments) |
| Are real sessions meeting the rubric? | A hosted scorer | [Score production sessions](/evals/online) |
| Which agent drove the cost increase? | **Reports → Agent usage** | [Investigate agent cost](/finops/how-tos/investigate-cost) |
| Why is a skill's usage empty? | The recorded skill attribution | [How skill usage works](/registry/skills/concepts/usage) |

## Connect the evidence

A registered agent and a recorded run are separate records. Send telemetry with the agent's own credentials and the intended workspace, then [verify the trace arrived](/registry/traces/how-tos/send-and-verify). Add session, visitor, and skill identifiers when the application knows them.

A completed run can still produce a poor answer. Trace errors measure execution failures; eval scores measure the criteria your scorers define. Cost depends on the recorded token counts and the available rates. Read the trace, score, and price source together before deciding what to change.

<Note>
  Monitoring covers the work you send to Atlan. Missing spans, missing scores, and unavailable cost breakdowns do not establish that a run succeeded or cost nothing.
</Note>

## Start with one agent

1. [Register the agent](/registry/agents/how-tos/create-agent) and choose its workspace.
2. [Send and verify a trace](/registry/traces/how-tos/send-and-verify).
3. [Inspect one run](/registry/traces/how-tos/inspect-runs) before relying on aggregate reports.
4. [Run a small eval](/evals/quickstart) and keep a failed production case in the dataset.
5. [Compare usage](/registry/reporting) over the same workspace and period.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.