databricks-agent-bricks

Develop conversational AI applications on Databricks with pre-built Agent Bricks.

38|12|Updated Apr 24, 2026
One-click install
npx skills add https://github.com/databrickslabs/coding-agents-databricks-apps --skill databricks-agent-bricks-databrickslabs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-agent-bricks
Source: https://github.com/databrickslabs/coding-agents-databricks-apps/tree/main/.claude/skills/databricks-agent-bricks
Command: npx skills add https://github.com/databrickslabs/coding-agents-databricks-apps --skill databricks-agent-bricks-databrickslabs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the need to build conversational AI components from scratch on Databricks, cutting development time for document Q&A, SQL exploration, and multi-agent orchestration use cases.

Core Features & Use Cases

  • Knowledge Assistants (KA): Create document-based Q&A systems that use RAG to answer questions from PDFs and text files stored in Unity Catalog Volumes.
  • Genie Spaces: Build natural language to SQL agents for exploring Unity Catalog tables, no custom query logic required.
  • Supervisor Agents (MAS): Orchestrate multiple specialized agents (KAs, Genie Spaces, custom model endpoints, Unity Catalog functions, external MCP servers) into a single unified conversational interface with intelligent query routing.
  • Use Case Example: Build an enterprise support assistant that routes policy questions to a document Q&A agent, analytics queries to a Genie Space, and ticket operations to an external MCP server.

Quick Start

Use the databricks-agent-bricks skill to create a Supervisor Agent that routes customer support queries to specialized policy, analytics, and ticketing agents.

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 multi-agent supervisor for routing queries on Databricks?

Build a multi-agent supervisor on Databricks by using pre-built Agent Bricks to orchestrate Knowledge Assistants, Genie Spaces, and custom endpoints into a unified conversational interface with intelligent query routing.

How do I create a RAG knowledge assistant from documents stored in Unity Catalog Volumes?

Create a RAG knowledge assistant from Unity Catalog Volumes by deploying pre-built Agent Bricks designed for document Q&A, which directly parse PDFs and text files to answer enterprise support questions.

Can I use natural language to query SQL data in Unity Catalog without writing custom logic?

Yes, you can query SQL data in Unity Catalog using natural language by configuring Genie Spaces, which act as agents to explore tables and generate insights without requiring custom query logic.

Does the Databricks agent framework support integrating external MCP servers into a conversational AI interface?

Yes, Databricks agent orchestration supports integrating external MCP servers alongside Unity Catalog functions and model serving endpoints into a single conversational AI interface for automated workflows.

What is the best way to orchestrate document Q&A, SQL exploration, and ticketing operations in one AI assistant?

The best way to orchestrate document Q&A, SQL exploration, and ticketing is a Supervisor Agent that routes policy questions to Knowledge Assistants, analytics to Genie Spaces, and operations to external servers.

Do I need to develop custom infrastructure to connect Databricks model serving endpoints to a conversational agent?

No, you do not need custom infrastructure to connect Databricks model serving endpoints, as pre-built Agent Bricks provide unified integration for conversational AI and multi-agent orchestration out of the box.