databricks-agent-bricks

Create and manage Databricks Agent Bricks for conversational AI workflows.

Updated May 20, 2026

Search Tags:#rag #mcp #databricks #unity catalog #knowledge assistant #supervisor agent #genie space

Ready to run

npx skills add https://github.com/ice-droid-99/BI-Dashboard-Generation-Agent-in-Databricks- --skill databricks-agent-bricks-ice-droid-99

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: databricks-agent-bricks
Source: https://github.com/ice-droid-99/BI-Dashboard-Generation-Agent-in-Databricks-/tree/main/.gemini/skills/databricks-agent-bricks
Command: npx skills add https://github.com/ice-droid-99/BI-Dashboard-Generation-Agent-in-Databricks- --skill databricks-agent-bricks-ice-droid-99

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of setting up reusable Databricks conversational building blocks by giving you a single, standardized way to create and manage Knowledge Assistants, SQL Genie Spaces, and Supervisor Agents.

Core Features & Use Cases

Knowledge Assistant (KA) creation for document Q&A: Turn files in a Unity Catalog Volume into a RAG-based Q&A endpoint, with optional example ingestion from JSON companions.
Genie Space orchestration for natural-language to SQL: Enable analytics conversations that translate questions into SQL over Unity Catalog data.
Supervisor Agent (MAS) orchestration for multi-agent routing: Route user requests to the right specialized agent (KA, Genie, model serving endpoints, UC functions, or external MCP servers) using clear descriptions and routing instructions.
Use case: Create an enterprise support assistant that answers from HR policy documents (KA), runs analytics queries for operational metrics (Genie), and triggers actions through an external MCP connection for ticket operations.

Quick Start

Create a Knowledge Assistant from your document volume by calling manage_ka with action create_or_update, name, volume_path, and a description of what users can ask.

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 knowledge assistant over documents in a Databricks Unity Catalog Volume?▼

To build a RAG knowledge assistant, you create a Databricks Knowledge Assistant by calling the manage_ka tool with the create_or_update action, specifying a name, volume_path, and a description of what users can ask.

How do I set up natural-language to SQL analytics conversations in Databricks?▼

You set up natural-language to SQL analytics by orchestrating a Genie Space, which translates conversational questions into SQL queries over your Unity Catalog data for analytics exploration.

How does multi-agent orchestration route requests across Genie Spaces and external MCP connections?▼

A Supervisor Agent acts as a multi-agent routing system, directing user requests to specialized agents like Knowledge Assistants, Genie Spaces, model serving endpoints, UC functions, or external MCP servers based on routing instructions.

Can I use one agent to handle document Q&A, SQL queries, and external ticket operations?▼

Yes, you can configure a Supervisor Agent to route requests across a Knowledge Assistant for document Q&A, a Genie Space for SQL queries, and an external MCP connection for ticket operations.

Why is my Databricks Agent Brick not responding after creation?▼

Your Databricks Agent Brick may not be responding if its provisioning status is not yet ONLINE, requiring you to wait for the endpoint to reach full readiness before handling conversational requests.