> 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.md).

# Cloud Agent

The **Cloud Agent** feature enables you to provision remote machines and deploy AI-powered agents that automatically execute development tasks in a secure cloud environment. After configuring a compute instance, the system prepares the remote machine by installing the required dependencies, configuring the environment, and deploying the agent.

Once deployed, Cloud Agents remain in an idle state until tasks are assigned. Tasks created from any module in WalnutAI are automatically queued and executed by the assigned Cloud Agent. During execution, the agent launches a browser-based development environment, analyzes the codebase, applies fixes, and generates pull requests with the required code changes. If review comments are added to the pull request, the agent can process the feedback and apply the necessary updates, enabling an efficient, end-to-end automated development workflow.

**Why Use Cloud Agents?**

* Automates the execution of development tasks on remotely provisioned machines.
* Eliminates the need for manual environment setup and task execution.
* Automatically applies code changes and generates pull requests.
* Helps resolve pull request review comments by applying the required fixes.
* Reduces manual effort, accelerates development, and improves overall productivity.