databricks-agent-bricks

Manage Databricks conversational AI bricks for document Q&A, SQL exploration, and multi-agent orchestration.

31|18|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/ThomazRossito/data-agents --skill databricks-agent-bricks-thomazrossito
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-agent-bricks
Source: https://github.com/ThomazRossito/data-agents/tree/main/skills/databricks/databricks-agent-bricks
Command: npx skills add https://github.com/ThomazRossito/data-agents --skill databricks-agent-bricks-thomazrossito

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Databricks Agent Bricks simplify the creation and management of conversational AI components in Databricks by providing prescriptive workflows for document Q&A, natural-language-to-SQL exploration, and multi-agent orchestration.

Core Features & Use Cases

  • Knowledge Assistants (KA): Index documents in Unity Catalog volumes and provide retrieval-augmented Q&A for policies, manuals, and reports.
  • Genie Spaces: Expose curated SQL exploration spaces for natural-language analytics and data discovery.
  • Supervisor Agents (MAS): Route user queries across KAs, Genie spaces, model endpoints, Unity Catalog functions, and external MCP servers to implement end-to-end workflows such as support desks, billing automation, and operational tooling.

Quick Start

Create a Knowledge Assistant named HR Policy Assistant backed by /Volumes/my_catalog/hr_docs using manage_ka create_or_update and provide a clear description and instructions.

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 in Databricks using Unity Catalog?

To build a RAG knowledge assistant in Databricks, index documents stored in Unity Catalog volumes and use the manage_ka create_or_update workflow to provide retrieval-augmented Q&A for policies, manuals, and reports.

Can I route natural language SQL queries to Genie Spaces using a supervisor agent?

Yes, Supervisor Agents route user queries across Genie Spaces for natural-language SQL exploration, model endpoints, and external MCP servers to implement end-to-end multi-agent orchestration workflows.

What permissions do I need to connect Databricks conversational AI to external MCP servers?

Connecting to external MCP servers requires appropriate service principal permissions, specifically EXECUTE on Unity Catalog functions and USE CONNECTION for the underlying Databricks connections.

Does Databricks Agent Bricks support multi-agent orchestration for operational tooling?

Yes, Supervisor Agents support multi-agent orchestration by routing queries across Knowledge Assistants, Genie Spaces, endpoints, and MCP servers to implement operational tooling, support desks, and billing automation workflows.

How do I set up natural-language SQL exploration in Databricks?

Set up natural-language SQL exploration by exposing curated Genie Spaces that allow users to perform analytics and data discovery directly through conversational natural-language queries.

What is required to create a Knowledge Assistant backed by Unity Catalog volumes?

Creating a Knowledge Assistant backed by Unity Catalog volumes requires deployed model serving endpoints, appropriate service principal permissions, and a clear description with instructions for the assistant.