# AI-Assisted development

## 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.

AppKit integrates with AI coding assistants through the Agent Skills.

## Installing Agent Skills[​](#installing-agent-skills "Direct link to Installing Agent Skills")

To install the Databricks Agent Skills for your preferred AI assistant, run:

```bash
databricks aitools install

```

## Skills capabilities[​](#skills-capabilities "Direct link to Skills capabilities")

The Agent Skills expose the following capabilities for AI assistants:

* **Data exploration**: Query catalogs, schemas, tables, and execute SQL
* **CLI command execution**: Deploy and manage apps, and run other workspace operations
* **Workspace resource discovery**: Inspect and navigate workspace resources

## Example prompts[​](#example-prompts "Direct link to Example prompts")

Here are some basic examples you can use to explore your app and workspace:

1. Creating a new basic app

```text
Create a new Databricks app that displays a dashboard of the users table in main.default.

```

1. Introspecting a table schema

```text
Show me the schema of the users table in main.default.

```

1. Creating a new query

```text
Create a new query to find users created in the last 7 days.

```

1. Deploying an app

```text
Deploy the app to Databricks with the name "my-app".

```

Possibilities are virtually endless. Ask your AI assistant to help you with your app and workspace.

## LLM resources[​](#llm-resources "Direct link to LLM resources")

AppKit provides specialized guidance files to help AI coding assistants work more effectively with the projects.

If you're building applications using AppKit packages, reference the `llms.txt` file. There are two ways to access the documentation:

1. Use the [hosted llms.txt file](https://databricks.github.io/appkit/llms.txt)
2. Use the `npx @databricks/appkit docs` command to view the documentation in the terminal.

```bash
npx @databricks/appkit docs            # documentation index with section overview
  npx @databricks/appkit docs <query> # for specific documentation file or section

```

Examples of documentation queries:

```bash
npx @databricks/appkit docs "appkit-ui API reference"  # view a specific section
npx @databricks/appkit docs --full     # full index with all API entries
npx @databricks/appkit docs ./docs.md  # view a specific documentation file

```

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

To learn more about Agent Skills, see the [Agent Skills repository](https://github.com/databricks/databricks-agent-skills).