> For the complete documentation index, see [llms.txt](https://docs.walnutai.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.walnutai.ai/development-and-infrastructure/cloud-agent/cloud-machine-setup-and-agent-deployment.md).

# Cloud Machine Setup and Agent Deployment

Before an agent can run, you must prepare the remote Machine that will host it.

Steps to create a remote Machine:

* Navigate to Admin Settings and click 'Compute Configuration'
* Click 'Add Compute'. 

<figure><img src="/files/UIX553295hN4rNDLX4wB" alt=""><figcaption></figcaption></figure>

* Fill in the details:

  * Name & Type: Fill in the Compute Name and select the type.
  * Connection: Enter the Host / IP (internet address) and the SSH Port (usually 22).
  * Authentication: Provide the Username and Password/SSH Key so the system can access the server.

  <figure><img src="/files/mKzSmNMSvGywvtm0P1ao" alt=""><figcaption></figcaption></figure>
* **Define the Environment:** Enter the Docker Image path (e.g., `walnut-cloud-agent:latest`). If the image is private, provide the Registry Server, Username, and PAT.
* **Assign a Subdomain:** Assign a unique URL (e.g., `agent2.walnut.ai`) for browser-based access. Ensure the domain's A record points to your VM IP.
* **Validate & Provision:**

  * Click Test to confirm the credentials and network settings are correct.
  * Click Update VM: This autonomously installs Docker, configures, performs DNS mapping, and pulls the latest Code Editor Docker images.

  <figure><img src="/files/wW7oow8VZJTC5QaQdnao" alt=""><figcaption></figcaption></figure>

**Steps to Create a Cloud Agent**

Once the machine status is Active and the environment is fully provisioned, you can deploy the agent.

* Go to the Agents and click 'New Agent'.

<figure><img src="/files/AIYyNq3lvar2whaT3dsy" alt=""><figcaption></figcaption></figure>

* Provide a name for the agent and select the Compute Instance you just created from the dropdown menu.

<figure><img src="/files/0646QFL7AEfTXyBPLoH0" alt=""><figcaption></figcaption></figure>

* Click 'Create'.

<figure><img src="/files/aDnA2tEIe1znqZ5MIDW8" alt=""><figcaption></figcaption></figure>

**What Happens Next?**

Once created, your agent will sit in an Idle state. It consumes minimal resources while waiting for a task to be assigned. As soon as a task enters its queue, it will wake up and begin execution.

<figure><img src="/files/QcEJhIS7MhtjrE5od14m" alt=""><figcaption></figcaption></figure>


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.walnutai.ai/development-and-infrastructure/cloud-agent/cloud-machine-setup-and-agent-deployment.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.