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

# Klaudia Investigator

> Puts Komodor's Klaudia behind an agent — ask a Kubernetes question across clusters and get her answer, with any approval she raises surfaced to you.

Deploy this agent when you want Komodor's own Kubernetes investigator reachable as part of your
fleet: in chat, on a schedule, or as a step inside a workflow. It relays your question to Klaudia
and returns her answer, including the structured root-cause analysis where she produces one. This
page covers what it needs, how pauses are handled, and where it stops.

## What it does

You ask a Kubernetes question or describe an incident. The agent puts it to Klaudia, who
investigates across the clusters your Komodor account already covers, and relays the answer back —
as prose for a question, or as a structured root-cause analysis when that is what she produces.

Unlike the in-cluster investigators, it is not bound to one cluster. Its reach is whatever your
Komodor account's agent already sees.

## What it reads

It reads nothing directly. Its entire surface is a small, fixed set of tools for holding a
conversation with Klaudia — asking a question, collecting the result, and nothing else. The
investigation happens on Komodor's side.

Because that surface is fixed by the agent itself, the wizard's tool checklist has no effect on it:
what it can do is decided by the implementation, not by what you tick.

## Before you deploy

| Requirement                     | Detail                                                            | Where to set it up                                                     |
| ------------------------------- | ----------------------------------------------------------------- | ---------------------------------------------------------------------- |
| Model access                    | The managed model gateway, or your own Claude API key             | [Credentials & secrets](/manage-your-agents/build/credentials-secrets) |
| MCP group with a Komodor server | The agent reaches Klaudia through a group-scoped gateway endpoint | [Integration groups](/manage-your-agents/build/integration-groups)     |

<Note>
  There is no Komodor connection to create. The Komodor MCP server authenticates itself on the gateway
  server object, configured once in gateway administration, so the Integrations step has nothing to
  collect for this agent — only the MCP group needs binding.
</Note>

## Ask it for

In chat, or as a run's prompt:

```text theme={null}
The payments deployment in the prod-eu cluster has been unhealthy since 12:15 UTC.
What happened, and what changed before it?
```

## How a pause reaches you

Klaudia can stop mid-investigation to ask for an approval or a choice. When she does, the agent does
not answer on your behalf — the pause is surfaced back as a decision waiting for a person, and the
investigation resumes once someone answers it.

See [Approvals](/security-and-governance/controls/approvals) for where those decisions land and who
may make them.

## Defaults and limits

|             |                                        |
| ----------- | -------------------------------------- |
| Catalog ID  | `klaudia-investigator`                 |
| Model       | `claude-sonnet-5`                      |
| Time budget | 300 seconds, adjustable 60–900 per run |
| Deployment  | Komodor cloud or self-hosted           |
| Chat        | Yes                                    |

<Warning>
  The time budget bounds the agent's own run, not Klaudia's work. An investigation that pauses for a
  human decision is waiting on a person, and that wait is not something a budget can shorten.
</Warning>

## In a workflow

It is the multi-cluster counterpart to the in-cluster investigators: where a step needs a Kubernetes
answer but the cluster is not known in advance, this is the specialist to route to. An orchestrator
can also use it as a first pass, then delegate to a cluster-bound investigator once the affected
cluster is identified.

See [Orchestration](/manage-your-agents/run/orchestration) for how a step delivers work to it.

## What it will not do

It cannot answer an approval or a choice on your behalf. That is enforced in the agent rather than
by configuration, so a gate Klaudia raises always comes back to a human.

It also performs no investigation of its own. Everything it reports comes from Klaudia, so what it
can see is exactly what your Komodor account covers — no more, and no less.

## Next steps

<CardGroup cols={2}>
  <Card title="Approvals" href="/security-and-governance/controls/approvals">
    Where a paused decision lands, and who may answer it.
  </Card>

  <Card title="Remediation Executor" href="/manage-your-agents/build/catalog/remediation-executor">
    Hand a finished investigation to Klaudia to act on.
  </Card>

  <Card title="Kubernetes RCA" href="/manage-your-agents/build/catalog/kubernetes-rca">
    In-cluster investigation with no Komodor backend.
  </Card>

  <Card title="Agent catalog" href="/manage-your-agents/build/catalog/overview">
    Every catalog agent, side by side.
  </Card>
</CardGroup>


## Related topics

- [Agent catalog](/manage-your-agents/build/catalog/overview.md)
- [Remediation Executor](/manage-your-agents/build/catalog/remediation-executor.md)
- [Kubernetes RCA](/manage-your-agents/build/catalog/kubernetes-rca.md)
- [Cluster Investigator](/manage-your-agents/build/catalog/cluster-investigator.md)
- [Grafana Investigator](/manage-your-agents/build/catalog/grafana-investigator.md)