databricks-agent-bricks

Create and orchestrate Databricks AI bricks for conversational AI workflows.

Updated Sep 9, 2017
One-click install
npx skills add https://github.com/mirakui/dotfiles --skill databricks-agent-bricks-mirakui
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: databricks-agent-bricks
Source: https://github.com/mirakui/dotfiles/tree/main/claude/skills/databricks-agent-bricks
Command: npx skills add https://github.com/mirakui/dotfiles --skill databricks-agent-bricks-mirakui

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Agent Bricks provide ready-made AI tiles to accelerate building conversational AI apps on Databricks by packaging Knowledge Assistants (KA), Genie Spaces for SQL exploration, and Supervisor Agents (MAS) into a single, reusable building block.

Core Features & Use Cases

  • Knowledge Assistant (KA): document-based Q&A from PDFs/text stored in Volumes using RAG.
  • Genie Space: natural language to SQL over Unity Catalog tables for data exploration.
  • Supervisor Agent (MAS): multi-agent orchestration that routes queries across KA, Genie Spaces, and model endpoints.
  • Use Case: rapidly assemble end-to-end conversational AI workflows by composing KA, Genie Space, and MAS tiles without rebuilding from scratch.

Quick Start

Create and organize KA, Genie Space, and MAS tiles to enable an integrated conversational AI experience on Databricks.

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 Knowledge Assistants and Genie Spaces?

To build conversational AI apps on Databricks, you compose AI bricks like Knowledge Assistants for document Q&A and Genie Spaces for SQL exploration into a unified workflow without rebuilding from scratch.

What is a Databricks Supervisor Agent and how does it route queries?

A Databricks Supervisor Agent is a multi-agent orchestration tile that routes user queries across Knowledge Assistants, Genie Spaces, and model endpoints to manage complex conversational workflows.

Can I use natural language to query Unity Catalog tables on Databricks?

Yes, you can use Genie Space AI bricks to translate natural language into SQL queries over Unity Catalog tables, enabling seamless data exploration directly within your conversational app.

How do I set up document-based Q&A for PDFs stored in Databricks Volumes?

You set up document-based Q&A by deploying a Knowledge Assistant AI brick, which uses RAG to process and answer questions from PDFs and text stored in Databricks Volumes.

What is the best way to orchestrate multi-agent workflows on Databricks?

The best way to orchestrate multi-agent workflows is using Supervisor Agent (MAS) tiles to route queries across Knowledge Assistants and Genie Spaces, rapidly assembling end-to-end conversational solutions.

Do I need Unity Catalog to use Genie Space for natural language SQL exploration?

Yes, Genie Space requires Unity Catalog tables to function, as it translates natural language inputs into SQL queries specifically over Unity Catalog data for exploration.