databricks-agent-bricks

Create and manage Databricks Agent Bricks for RAG, SQL, and multi-agent orchestration.

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/slysik/databricks-claude-coding --skill databricks-agent-bricks-slysik
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-agent-bricks
Source: https://github.com/slysik/databricks-claude-coding/tree/main/.agents/skills/databricks-agent-bricks
Command: npx skills add https://github.com/slysik/databricks-claude-coding --skill databricks-agent-bricks-slysik

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the creation of sophisticated conversational AI applications on Databricks by providing pre-built components for document Q&A, SQL exploration, and multi-agent orchestration, significantly reducing development effort.

Core Features & Use Cases

  • Knowledge Assistants (KA): Enable document-based Q&A over files in Unity Catalog Volumes using RAG.
  • Genie Spaces: Provide natural language to SQL interfaces for data exploration.
  • Supervisor Agents (MAS): Orchestrate multiple specialized agents (KAs, Genie Spaces, model endpoints, UC Functions, external MCP servers) into a unified conversational experience.
  • Use Case: Create a unified customer support interface that can answer policy questions from documents (KA), provide data insights from tables (Genie), and perform actions in an external system (MAS with MCP).

Quick Start

Use the databricks-agent-bricks skill to create a knowledge assistant named 'HR Policy Assistant' using documents from '/Volumes/my_catalog/my_schema/raw_data/hr_docs'.

Frequently Asked Questions about databricks-agent-bricks

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a RAG-based document Q&A assistant on Databricks?

You can build a RAG-based document Q&A assistant on Databricks by creating a Knowledge Assistant using files stored in Unity Catalog Volumes. This provides a conversational interface for querying your stored documents directly.

Can I orchestrate multiple specialized agents into a single conversational interface?

Yes, you can orchestrate multiple specialized agents into a single conversational interface using Supervisor Agents. They coordinate Knowledge Assistants, Genie Spaces, model endpoints, and external MCP servers for unified multi-agent orchestration.

Does Databricks support natural language to SQL for data exploration?

Databricks supports natural language to SQL for data exploration through Genie Spaces. This feature allows users to interact conversationally with their data tables to generate insights without writing manual SQL queries.

What's the best way to connect external systems to a Databricks conversational AI agent?

The best way to connect external systems to a Databricks conversational AI agent is via UC HTTP Connections with external MCP servers. This integrates external actions into your Supervisor Agent orchestration.

Can I use Unity Catalog Functions within a Databricks conversational AI application?

Yes, you can use Unity Catalog Functions within Databricks conversational AI applications. Supervisor Agents support orchestration of UC Functions alongside Knowledge Assistants and Genie Spaces to execute specific logic.

Do I need model serving endpoints to create production-ready conversational AI on Databricks?

Yes, model serving endpoints are supported for integration when creating production-ready conversational AI on Databricks. They facilitate deploying the underlying models for your Knowledge Assistants and Supervisor Agents.