databricks-agent-bricks

Create and manage Databricks Knowledge Assistants, Genie Spaces, and Supervisor Agents.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provisioning, connecting, and managing Databricks conversational components (Knowledge Assistants, Genie Spaces, and Supervisor Agents) is operationally complex and error-prone; this Skill centralizes patterns, tooling, and best practices to reduce setup time and misconfiguration.

Core Features & Use Cases

  • Knowledge Assistants (KA): Index documents in Unity Catalog volumes, ingest example Q&A pairs, and create document-backed RAG endpoints for policy, support, or compliance Q&A.
  • Genie Spaces: Create and manage natural-language-to-SQL exploration spaces for analytics and ad-hoc data discovery without manual SQL plumbing.
  • Supervisor Agents (MAS): Compose multi-agent supervisors that route queries among KAs, Genie Spaces, model endpoints, UC functions, and external MCP connections; includes provisioning guidance, status checks, and example ingestion workflows.
  • Use Case: Build an enterprise support supervisor that routes invoice analytics to a Genie Space, policy questions to a KA indexed from HR documents, and approval actions to an MCP-backed external ticketing system.

Quick Start

Create a Knowledge Assistant named "HR_Policy_Assistant" pointing at /Volumes/my_catalog/hr_docs and instruct it to always cite the originating document and section when answering.

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 Knowledge Assistant for document Q&A from Unity Catalog volumes?

To build a Knowledge Assistant, you index documents stored in Unity Catalog volumes, ingest example Q&A pairs, and create document-backed RAG endpoints for policy, support, or compliance Q&A.

Can I route natural-language queries to SQL exploration and external MCP servers using a Supervisor Agent?

Yes, Supervisor Agents compose multi-agent supervisors that route queries among Genie Spaces, model endpoints, UC functions, and external MCP connections for integrated enterprise support.

What is the best way to set up natural-language-to-SQL exploration in Databricks without manual SQL plumbing?

The best way to enable natural-language-to-SQL exploration is by creating and managing Genie Spaces, which allow analytics and ad-hoc data discovery directly through conversational queries.

Do I need Unity Catalog to configure Databricks agent bricks for RAG and multi-agent orchestration?

Yes, Unity Catalog is required for provisioning Knowledge Assistants from volume indexing and integrating UC functions with Supervisor Agents for multi-agent orchestration.

How does a Supervisor Agent route queries across different model endpoints and connections?

A Supervisor Agent routes queries by composing multi-agent supervisors that direct questions among Knowledge Assistants, Genie Spaces, model endpoints, UC functions, and HTTP connections for external MCP servers.

Why does provisioning Databricks conversational components fail without centralized patterns and tooling?

Provisioning fails because connecting and managing Databricks conversational components is operationally complex and error-prone without centralized patterns, tooling, and best practices to reduce misconfiguration.