skills.rest
databricks-solutions
databricks-solutionsOFFICIAL
Explore all skills by this author →
GitHub

agent-bricks

Create and manage Databricks agent bricks for conversational AI applications.

1.8k|404|Updated Dec 17, 2025
Search Tags:#workflow#RAG#Genie Space#Databricks#agent-bricks#MAS#Knowledge Assistant
One-click install
npx skills add https://github.com/databricks-solutions/ai-dev-kit --skill agent-bricks
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-bricks
Source: https://github.com/databricks-solutions/ai-dev-kit/tree/main/databricks-skills/agent-bricks
Command: npx skills add https://github.com/databricks-solutions/ai-dev-kit --skill agent-bricks

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams accelerate the development of conversational AI applications by bundling three pre-built Databricks components—Knowledge Assistants (KA), Genie Spaces, and Multi-Agent Supervisors (MAS)—into reusable agent bricks.

Core Features & Use Cases

  • KA integration: Build document-based Q&A experiences using Knowledge Assistants backed by Unity Catalog data volumes.
  • Genie Space guidance: Convert natural language queries into SQL against Unity Catalog tables for exploratory analysis.
  • MAS orchestration: Route questions to specialized agents and endpoints, enabling scalable, multi-agent workflows.
  • End-to-end workflow: Provision KA, Genie Space, and MAS with tool-based operations and provisioning status monitoring.

Quick Start

Begin by creating a KA with create_or_update_ka, then create a Genie Space with create_or_update_genie, and finally assemble a MAS with create_or_update_mas. Monitor provisioning status and add sample questions once endpoints are ONLINE.

Frequently Asked Questions about agent-bricks

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build conversational AI applications with Databricks Agent Bricks?▼

Build conversational AI applications by orchestrating Knowledge Assistants for document Q&A, Genie Spaces for SQL exploration, and Multi-Agent Supervisors. Use create_or_update tools to provision these agent bricks and monitor their endpoint status within Databricks.

How do I create a document Q&A assistant using Unity Catalog data?▼

Create a document Q&A assistant by using the create_or_update_ka tool to provision a Knowledge Assistant. This requires Unity Catalog data volumes as the source, allowing the assistant to query and retrieve information from your provisioned documents.

Can I convert natural language to SQL for exploratory analysis in Databricks?▼

Convert natural language to SQL by creating a Genie Space using the create_or_update_genie tool. This enables exploratory analysis directly against your Unity Catalog tables, translating user queries into executable SQL statements.

How do I route questions to specialized agents in a multi-agent workflow?▼

Route questions to specialized agents by assembling a Multi-Agent Supervisor (MAS) with the create_or_update_mas tool. This orchestrates scalable multi-agent workflows by directing queries to dedicated endpoints and managing provisioning status.

Do I need to provision model endpoints before creating Agent Bricks?▼

Provision model endpoints, Unity Catalog, and Volumes before creating Agent Bricks. The workflow requires these data sources and model endpoints to be active, after which you monitor provisioning status and add sample questions once endpoints are ONLINE.

Related Skills

Explore More Software Engineering Skills→
RamVegirajuRamVegiraju
4

databricks-agent-bricks

Create and manage Databricks Agent Bricks for conversational AI apps.

Community
Advanced
aaronachermannaaronachermann

databricks-agent-bricks

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

Community
Advanced
juanlamadrid20juanlamadrid20

databricks-genie

Create and query Databricks Genie Spaces using natural language.

Community
Advanced
alessandro9110alessandro9110
4

databricks-agent-bricks

Create and manage Databricks Agent Bricks for RAG-based Q&A and multi-agent orchestration.

Community
Advanced