Agent Bricks

This article describes what Agent Bricks is, how it works, and the use cases it supports.

What is Agent Bricks?

Agent Bricks offers a streamlined approach for both technical and non-technical teams to operationalize their data into production-grade AI agents. Declarative agents can be built and refined using natural language and pre-configured templates for tasks like information extraction, knowledge assistance, and multi-agent coordination.

With built-in evaluation through MLflow, unified governance using Unity Catalog, open support for any model or framework with AI Gateway, and an integrated MCP catalog, Agent Bricks provides everything needed to deploy AI solutions.

As a Databricks Designated Service, Agent Bricks uses Databricks Geos to manage data residency when processing customer content.

Requirements

• A workspace that includes the following:
  • Mosaic AI Agent Bricks Preview (Beta) enabled. See Manage Databricks previews.
  • Serverless compute enabled. See Serverless compute requirements.
  • Unity Catalog enabled. See Enable a workspace for Unity Catalog.
  • Access to foundation models in Unity Catalog through the system.ai schema.
  • Access to a serverless budget policy with a nonzero budget.
• A workspace in one of the supported regions: us-east-1 or us-west-2.

How does Agent Bricks work?

Agent Bricks is powered by Databricks Mosaic AI to allow users to deploy comprehensive AI agent systems customized with their unique data quickly and easily.

1. Specify your problem.

   Specify your use case and point to your data.

2. Agent Bricks automatically builds out the entire AI agent system for you.

   Agent Bricks will automatically try various AI models, fine-tune them using your data, optimize the systems using innovative AI techniques, and evaluate them to offer you the best built-out systems.

3. Further refine the system for continuous improvement.

   When you use Agent Bricks, Databricks will run additional methods and hyperparameter sweeps in the background to continually optimize your model result. If our evaluations indicate a different model would achieve better results, Databricks will notify you without additional charge.

Agent Bricks is seamlessly integrated with the rest of the Databricks Data Intelligence Platform. This means you have everything you need to deploy AI solutions, from security and governance to data integration, vector indexes, and quality evaluation. This is all available as a one-button optimized deployment.

Supported use cases

Agent Bricks currently supports the following use cases:

Beta

Some Agent Bricks features are in Beta. Workspace admins can control access to these features from the Previews page. See Manage Databricks previews.

Agent Bricks	Use case
Information Extraction (Beta)	Transform documents and unstructured text into structured insights via information extraction, classification, and more.
Custom LLM (Beta)	Custom text generation tasks, such as summarization and text transformation.
Knowledge Assistant	Turn your documents into a high-quality chatbot that can answer questions and cite its sources.
Multi-Agent Supervisor (Beta)	Design a multi-agent AI system that brings Genie spaces and agents together.
AI/BI Genie	Turn your tables into an expert AI chatbot.
Code your own agent	Build your own agent with OSS libraries and Agent Framework.