databricks-agent-bricks

Create and orchestrate Databricks Agent Bricks for conversational AI workflows.

Updated Mar 19, 2026
One-click install
npx skills add https://github.com/Blackkadder/databricks-apps-and-agents-workshop --skill databricks-agent-bricks-blackkadder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-agent-bricks
Source: https://github.com/Blackkadder/databricks-apps-and-agents-workshop/tree/main/.claude/skills/databricks-agent-bricks
Command: npx skills add https://github.com/Blackkadder/databricks-apps-and-agents-workshop --skill databricks-agent-bricks-blackkadder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Agent Bricks enable rapid composition of end-to-end conversational AI apps on Databricks by combining Knowledge Assistants (KA), Genie Spaces, and Supervisor Agents (MAS). These reusable building blocks simplify integration of document Q&A, SQL-based exploration, and multi-agent orchestration into a single, scalable workflow.

Core Features & Use Cases

  • KA: create document-based Q&A assistants that retrieve and answer questions from Unity Catalog volumes.
  • Genie Space: enable natural language to SQL interactions over Unity Catalog data.
  • Supervisor Agent (MAS): orchestrate multiple specialized agents (KA, Genie, endpoints) into a unified interface.
  • End-to-end workflows: mix and match agents to build multi-domain AI assistants for enterprise use cases.

Quick Start

Create KA, Genie Space, and MAS bricks using manage_ka and manage_mas, then provision and test in the Databricks UI.

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 conversational AI apps on Databricks using Agent Bricks?

Build conversational AI apps on Databricks by orchestrating Knowledge Assistants, Genie Spaces, and Supervisor Agents to combine document Q&A, natural language SQL exploration, and multi-agent routing into scalable end-to-end workflows.

What is a Supervisor Agent in Databricks and when do I need it?

A Supervisor Agent (MAS) in Databricks orchestrates multiple specialized agents like Knowledge Assistants and Genie Spaces into a unified interface. You need it when building scalable multi-domain enterprise AI assistants that require multi-agent routing.

How do I create a Knowledge Assistant for document Q&A in Databricks?

Create a Knowledge Assistant using the manage_ka tooling guidance to retrieve and answer questions from documents stored in Unity Catalog volumes, then provision and test the KA directly within the Databricks UI.

Can I use Genie Spaces for natural language to SQL queries over Unity Catalog data?

Yes, Genie Spaces enable natural language to SQL interactions over Unity Catalog data. You provision them as reusable building blocks to allow conversational data exploration within your end-to-end Databricks AI workflows.

What are the limitations of mixing Knowledge Assistants and Genie Spaces in a single workflow?

Mixing Knowledge Assistants and Genie Spaces requires a Supervisor Agent for orchestration. You must provision each brick individually using manage_ka and manage_mas, ensuring proper multi-agent routing configuration before testing in the Databricks UI.