skills.rest
Paldom
PaldomCOMMUNITY
Explore all skills by this author →
GitHub

agent-bricks

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

1|1|Updated Nov 9, 2025
Search Tags:#rag#agent#multi-agent#orchestration#genie#knowledge assistant
One-click install
npx skills add https://github.com/Paldom/databricks-apps-streamlit-vibe-coding-starter --skill agent-bricks-paldom
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-bricks
Source: https://github.com/Paldom/databricks-apps-streamlit-vibe-coding-starter/tree/main/.agents/skills/agent-bricks
Command: npx skills add https://github.com/Paldom/databricks-apps-streamlit-vibe-coding-starter --skill agent-bricks-paldom

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill simplifies the creation and management of sophisticated conversational AI applications on Databricks by providing pre-built, composable AI components.

Core Features & Use Cases

  • Knowledge Assistants (KA): Build document-based Q&A systems over your data using RAG.
  • Genie Spaces: Enable natural language querying over structured data in Unity Catalog.
  • Multi-Agent Supervisors (MAS): Orchestrate multiple specialized agents into a single, unified conversational interface.
  • Use Case: Combine a KA that answers HR policy questions with a Genie Space that provides sales metrics, all managed under a single MAS that intelligently routes user queries.

Quick Start

Use the agent-bricks skill to create a Knowledge Assistant named 'Product Documentation Assistant' using documents from '/Volumes/main/default/product_docs'.

Frequently Asked Questions about agent-bricks

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

FAQPage Schema
How do I orchestrate multiple AI agents into a single conversational interface?▼

You can orchestrate multiple AI agents by using a Multi-Agent Supervisor to route user queries to specialized agents, creating a unified conversational interface. This approach manages distinct tasks like document Q&A and SQL translation under one supervisor.

How do I build a RAG-based document Q&A system over my data?▼

To build a RAG-based document Q&A system, you can create a Knowledge Assistant that references your documents stored in Databricks Volumes. This abstracts complex provisioning tasks to enable conversational querying over your unstructured data.

Can I translate natural language to SQL over structured data in Unity Catalog?▼

Yes, you can translate natural language to SQL by creating Genie Spaces. This feature enables natural language querying directly over your structured data stored in Unity Catalog without writing manual SQL queries.

What is the best way to combine unstructured document search with structured data querying?▼

The best way to combine unstructured and structured querying is deploying a Multi-Agent Supervisor. It intelligently routes requests between a Knowledge Assistant for documents and a Genie Space for structured data metrics.

Do I need to manually provision resources to create conversational AI applications on Databricks?▼

No, you do not need to manually provision resources. This Skill abstracts complex provisioning and integration tasks, providing pre-built composable AI components to simplify creating conversational applications on Databricks.

Related Skills

Explore More Software Engineering Skills→
databrickslabsdatabrickslabs
38

databricks-agent-bricks

Develop conversational AI applications on Databricks with pre-built Agent Bricks.

Official
Intermediate
thgtertothgterto

intelligent-routing

Analyze user requests and route them to specialist agents across domains.

Community
Advanced
JingyiWngJingyiWng

databricks-unity-catalog

Guide Unity Catalog governance for system tables, volumes, and lineage.

Community
Intermediate
eyadsibaieyadsibai
7

rag-frameworks

Compare RAG frameworks like LangChain and LlamaIndex for document QA.

Community
Intermediate