> For the complete documentation index, see [llms.txt](https://docs.origintrail.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.origintrail.io/for-agents/setup.md).

# Set Up and Verify

**Inputs:** intended runtime, local/remote node location, network, existing installation if any, and the task's write/sharing scope. Use the [integration selector](/connect-agents-and-systems/integrations.md).

1. Inspect the existing node first. Use `dkg doctor --json` for installation ambiguity and status for the running version. Do not change the network/home of an existing node to satisfy a tutorial.
2. For a fresh installation, follow the chosen runtime guide. Explicitly select the intended network. Framework/model installation and credentials are separate prerequisites.
3. Confirm daemon and store health. Confirm the runtime can discover DKG tools and call status. A Node UI chat reply alone does not prove memory integration; Prime Agent's bridge currently provides that narrower capability.
4. If sample writes are authorized, follow the [Atlas quickstart](/start-here/quickstart.md), using its five-triple fixture, exact graph ID, and KA name. Keep the sample in WM unless sharing is authorized.
5. Retrieve the KA through tools. Expected evidence: Atlas uses Oxigraph, with source `https://example.org/dkg-tutorial/source`, from WM. Show the actual relationships returned.
6. In a fresh conversation under the same authorized identity, repeat the read. Do not use the prior conversation as the evidence.

**Done:** report the node version, runtime, exact graph/KA, retrieved answer/source/layer, and whether the fresh-session check actually ran. Never mark an unavailable framework or unexecuted conversation test as passed.

**Recover:** if tools are missing, inspect setup and restart the appropriate client/gateway. If the graph is absent, check node/home/identity and exact ID. If another identity cannot read WM, do not broaden access implicitly; use the [collaboration procedure](/for-agents/collaborate.md) when sharing is intended.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.origintrail.io/for-agents/setup.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
