> 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/walnutai-coder/working-with-new-applications-and-existing-repositories.md).
# Working with New Applications and Existing Repositories
The WalnutAI Agent adapts its workflow based on whether you are building a new application or working with an existing repository. The agent remains the default interface, dynamically transitioning between modes as required by the task.
**Building a New Application**
To start a project from scratch:
* Create a folder on your local machine and open it in VS Code.
* Activate the WalnutAI extension and select the project.
* Provide the Agent with your high-level requirement (for example, “Build a Task Management API”). Once submitted, the Agent proceeds through the following structured workflow:
* **Analyze:** The Agent reviews your request and automatically enters [**Plan Mode**](#user-content-fn-1)[^1] to create a structured technical roadmap.
* **Clarify:** If any information is unclear or incomplete, WalnutAI triggers a Q\&A mechanism to gather the necessary details, ensuring it avoids assumptions and does not hallucinate.
* **Implement:** After you approve the proposed plan, the Agent begins implementation, requesting explicit permission before running terminal commands or making significant changes.
**Working with an Existing Repository**
To enhance or maintain an existing project:
* Clone the repository manually using VS Code.
* Open the project folder to allow the Agent to scan dependencies, frameworks, and architectural patterns.
* Start prompting for specific use cases like bug fixes, refactoring, or documentation.
[^1]: Converts high-level ideas into a clear, step-by-step technical plan before any code is written.
