# Development

AppKit provides multiple development workflows to suit different needs: local development with hot reload, AI-assisted development with Agent Skills, and remote tunneling to deployed backends.

## Prerequisites[​](#prerequisites "Direct link to Prerequisites")

* [Node.js](https://nodejs.org) v22+ environment with `npm`
* Databricks CLI (v1.0.0 or higher): install and configure it according to the [official tutorial](https://docs.databricks.com/aws/en/dev-tools/cli/tutorial).
* A new Databricks app with AppKit installed. See [Bootstrap a new Databricks app](./docs.md#quick-start-options) for more details.

## Development flows[​](#development-flows "Direct link to Development flows")

There are multiple supported development flows available with AppKit:

1. **[Local development](./docs/development/local-development.md)**: Run the development server with hot reload for both UI and backend code. This is the default development flow and is suitable for most use cases.
2. **[AI-assisted development](./docs/development/ai-assisted-development.md)**: Use an AI coding assistant with Agent Skills to explore data, run CLI commands, and scaffold your app interactively.
3. **[Remote Bridge](./docs/development/remote-bridge.md)**: Create a remote bridge to a deployed backend while keeping your queries and UI local. This is useful for testing against production data or debugging deployed backend code without redeploying your app.

## See also[​](#see-also "Direct link to See also")

* [App management](./docs/app-management.md): Manage your AppKit application throughout its lifecycle using the Databricks CLI
* [Architecture](./docs/architecture.md): Learn about the architecture of AppKit