databricks-agent-bricks

Create and manage Databricks Agent Bricks for KA, Genie Space, and MAS.

11|3|Updated Jun 10, 2025
One-click install
npx skills add https://github.com/Paldom/databricks-apps-fastapi-starter --skill databricks-agent-bricks-paldom
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-agent-bricks
Source: https://github.com/Paldom/databricks-apps-fastapi-starter/tree/main/.gemini/skills/databricks-agent-bricks
Command: npx skills add https://github.com/Paldom/databricks-apps-fastapi-starter --skill databricks-agent-bricks-paldom

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Agent Bricks provide a modular framework to create and orchestrate Databricks AI components—Knowledge Assistants (KA), Genie Spaces, and Supervisor Agents (MAS)—to accelerate building conversational AI applications.

Core Features & Use Cases

  • Knowledge Assistants (KA): document Q&A with retrieval-augmented generation over Volumes
  • Genie Spaces: SQL-based data exploration over Unity Catalog tables
  • Supervisor Agents (MAS): multi-agent orchestration across KA, Genie, and model endpoints
  • Use Case: Quickly assemble an AI assistant that answers policy questions from documents and performs data-driven actions via endpoints

Quick Start

Create KA, Genie Space, and MAS bricks using the Agent Bricks workflow with manage_ka and manage_mas.

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 Databricks conversational AI app with Knowledge Assistants and Genie Spaces?

Build conversational AI apps on Databricks by orchestrating Knowledge Assistants for document Q&A, Genie Spaces for SQL data exploration, and Supervisor Agents for multi-agent routing using the manage_ka and manage_mas APIs.

What is a Databricks Supervisor Agent and how does it orchestrate multi-agent workflows?

A Databricks Supervisor Agent (MAS) orchestrates multi-agent workflows by routing decisions across Knowledge Assistants, Genie Spaces, and model endpoints to handle end-to-end conversational AI tasks.

Can I use Genie Spaces with Unity Catalog tables for SQL-based data exploration?

Yes, Genie Spaces support SQL-based data exploration directly over Unity Catalog tables, enabling conversational querying and data-driven actions within your Databricks AI applications.

Do I need specific frontmatter to deploy Databricks Agent Bricks?

Deploying Databricks Agent Bricks requires frontmatter containing a name and description, with optional scripts, references, and assets directories for managing resources via the manage_ka and manage_mas APIs.

How do Knowledge Assistants handle document retrieval in Databricks?

Knowledge Assistants (KA) perform document Q&A using retrieval-augmented generation over Databricks Volumes, allowing your conversational AI to answer policy and document-based questions accurately.

What's the best way to assemble a multi-agent AI assistant in Databricks?

Assemble a Databricks multi-agent AI assistant by creating KA, Genie Space, and MAS bricks through the Agent Bricks workflow, combining document Q&A with data-driven endpoint actions.