databricks-agent-bricks

Name: databricks-agent-bricks
Availability: InStock
Author: teegin-g

Build and orchestrate conversational AI apps with Databricks Agent Bricks.

Updated Jan 30, 2026

Search Tags:#routing #ai-orchestration #databricks #agent-bricks #knowledge-assistants #genie-space #supervisor-agent

Ready to run

npx skills add https://github.com/teegin-g/Slopcast --skill databricks-agent-bricks-teegin-g

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: databricks-agent-bricks
Source: https://github.com/teegin-g/Slopcast/tree/main/.agents/skills/databricks-agent-bricks
Command: npx skills add https://github.com/teegin-g/Slopcast --skill databricks-agent-bricks-teegin-g

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Databricks Agent Bricks simplify building end-to-end conversational AI apps by providing ready-made components for knowledge retrieval, data exploration, and multi-agent orchestration.

Core Features & Use Cases

KA (Knowledge Assistant): document-based Q&A using Retrieval-Augmented Generation (RAG) from PDFs/text in Unity Catalog Volumes.
Genie Space: natural language to SQL over Unity Catalog data for analytics and exploration.
Supervisor Agent (MAS): orchestrates multiple specialized agents (KA, Genie Space, model endpoints, UC functions, external MCPs) and routes queries accordingly.
Prerequisites & Workflows: guidance on data preparation, agent creation, provisioning timelines, and example-driven evaluation.
Best Practices: structured descriptions, explicit routing instructions, and a scalable workflow for multi-brick AI apps.

Quick Start

Create a KA, a Genie Space, and a MAS by using manage_ka and manage_mas to assemble your first integrated agent.

Frequently Asked Questions about databricks-agent-bricks

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

FAQPage Schema

How do I orchestrate multiple Databricks agents for conversational AI?▼

You can orchestrate multiple Databricks agents by using a Supervisor Agent (MAS) to route queries across specialized Knowledge Assistants, Genie Spaces, and model endpoints. This provides structured integration and multi-agent routing within your workspace.

What is the best way to build a RAG knowledge assistant in Databricks?▼

Building a RAG knowledge assistant in Databricks involves using the Knowledge Assistant (KA) component to perform document-based Q&A. You provision a KA endpoint using text and PDFs stored in Unity Catalog Volumes.

Can I use natural language to query SQL data in Unity Catalog?▼

Yes, you can use natural language to query SQL data in Unity Catalog by creating a Genie Space. It translates natural language queries into SQL, enabling data exploration and analytics directly over your catalog data.

How do I provision and manage a multi-agent routing system in Databricks?▼

To provision a multi-agent routing system, use the manage_ka and manage_mas workflows to assemble the components. This codifies the required prerequisites, data preparation, and example-driven evaluation for production deployment.

What prerequisites are needed to deploy multi-brick AI apps in a Databricks workspace?▼

Deploying multi-brick AI apps requires data preparation in Unity Catalog Volumes, structured agent descriptions, and explicit routing instructions. Following the provided provisioning timelines and best practices ensures a scalable workflow.

When should I use a Supervisor Agent instead of individual Databricks AI components?▼

Use a Supervisor Agent when you need to orchestrate multiple specialized agents like Knowledge Assistants, Genie Spaces, and external MCPs together. It handles query routing, whereas individual components only perform isolated retrieval or analytics tasks.