## Query Lakehouse with AI agents

URL: https://docs.atlan.com/platform/lakehouse/how-tos/ai-agents

> Query Lakehouse metadata using natural language in AI coding agents like Claude Code. Install the atlan-lakehouse skill, which detects your platform and generates appropriate SQL queries.

The atlan-lakehouse skill enables natural language queries on Lakehouse metadata in AI agents like [Claude Code](https://docs.anthropic.com/en/docs/claude-code/overview). The skill detects your platform ([Snowflake via Cortex Code](https://docs.snowflake.com/en/user-guide/ai-powered-cortex-code), [Databricks via Genie Code](https://docs.databricks.com/en/genai/genie/), or [Python via PyIceberg](https://py.iceberg.apache.org/)) and generates SQL automatically, letting you explore your catalog metadata without writing SQL manually.

## Prerequisites

Before you begin, make sure you have:

- Installed [Claude Code](https://docs.anthropic.com/en/docs/claude-code/overview) on your machine.
- Access to clone the [Lakehouse Solutions](https://github.com/atlanhq/lakehouse-solutions) repository from GitHub.

## Install Agent skill

1. Clone the Lakehouse Solutions repository to your machine:

 ```bash
 git clone https://github.com/atlanhq/lakehouse-solutions.git
 ```

2. Create the Claude Code skills directory if it doesn't already exist:

 ```bash
 mkdir -p ~/.claude/skills
 ```

3. Symlink the skill into your Claude Code skills directory:

 ```bash
 ln -s /path/to/lakehouse-solutions/skills/atlan-lakehouse ~/.claude/skills/atlan-lakehouse
 ```

 Replace `/path/to/lakehouse-solutions` with the actual path where you cloned the repository.

## Query Lakehouse using natural language

Once the skill is installed, Claude Code activates it automatically when you ask Lakehouse-related questions.

1. Open Claude Code in your terminal:

 ```bash
 claude
 ```

2. Ask a question in natural language. For example:

 - *"What percentage of my Snowflake tables have descriptions?"*
 - *"Which assets are missing owners?"*
 - *"Show me lineage gaps in the sales domain."*

 The skill identifies your platform and runs the appropriate SQL query in your Lakehouse.

## See also

- [Lakehouse use cases](https://docs.atlan.com/llms/governance/lakehouse/overview/llms.txt): Explore what you can analyze with Lakehouse data
- [Gold namespace reference](https://docs.atlan.com/llms/governance/lakehouse/gold-layer/llms.txt): Learn about the curated views the skill queries
- [Lakehouse Solutions repository](https://github.com/atlanhq/lakehouse-solutions): Browse all available skills and solutions

---