On this wave of GenAI, aggressive benefit gained’t come from the fashions you hire—it’s going to come from the info you personal. But most organizations wrestle to operationalize their knowledge into production-grade brokers as a result of they lack the standard, governance, and suppleness to scale.
Databricks Agent Bricks closes this hole, enabling each group to appreciate knowledge intelligence with brokers that perceive, purpose, and act on structured and unstructured data. With built-in analysis by way of MLflow, unified governance by way of Unity Catalog, and open help for any mannequin or framework with AI Gateway, Agent Bricks helps enterprises like AstraZeneca and Edmunds transfer from pilots to manufacturing with confidence.
This week, we’re introducing new capabilities throughout Agent Bricks, advancing every of its three pillars of belief: accuracy, governance, and openness. Welcome to a different Week of Brokers.
“With Agent Bricks, our groups have been in a position to parse by way of 400,000+ medical trial paperwork and extract structured knowledge factors, with out writing a single line of code. In slightly below 60 minutes, we had a working agent that would rework advanced, unstructured knowledge into usable analytics. Agent Bricks (Info Extraction) is a invaluable device to drive from knowledge to insights rapidly!” — Joseph Roemer, Head of Knowledge & AI, Industrial IT, AstraZeneca
Construct Any Agent—Your Means
Agent Bricks is open by design, giving groups the pliability to construct high-quality brokers on ruled knowledge and trusted MCP servers.
- Customized-Code Brokers. Construct with any framework, MCP server, or mannequin—GPT-5, Claude Sonnet, Gemini, Llama—and run on Databricks’ serverless infrastructure. Each interplay is routinely traced, evaluated, and ruled by way of MLflow observability and AI Gateway.
- Declarative Brokers. Allow technical and non-technical groups to construct and refine brokers by way of pure language and pre-configured templates for duties reminiscent of data extraction, information help, and multi-agent coordination—with built-in analysis for steady enchancment.
- Agentic AI Capabilities. Apply capabilities reminiscent of ai_parse_document immediately in your paperwork to parse, enrich, and embed unstructured content material at scale—automating handbook workflows and revealing insights that have been as soon as out of attain.
“Databricks provides us a safe, ruled basis to run a number of fashions, like GPT-5, Claude Sonnet, and Llama, and change suppliers as our wants evolve, all whereas protecting prices in examine. That flexibility lets us automate evaluation moderation and enhance content material high quality quicker, so automotive customers get trusted insights sooner.” — Greg Rokita, Vice President of Know-how, Edmunds
New in Agent Bricks
To assist enterprises transfer from pilots to manufacturing, we’re deepening Agent Bricks throughout its three pillars of belief:
- Accuracy. MLflow for Agent High quality and Observability (GA) traces each agent interplay, scores outputs with customized judges, and gives an app for accumulating subject-matter-expert suggestions—making MLflow the usual for evaluating brokers throughout any atmosphere.
- Governance. With AI Gateway (GA) and the MCP Catalog in Databricks Market (Public Preview), enterprises can govern each mannequin and exterior MCP server by way of Unity Catalog. All mannequin exercise is logged, rate-limited, and auditable to fulfill compliance necessities, whereas launch companions—together with Glean, You.com, Dun & Bradstreet, Moody’s, and S&P International—broaden entry to trusted knowledge and instruments.
- Openness and Interoperability. Agent Bricks helps any mannequin, framework, or MCP server so enterprises can compose multi-step workflows throughout inside and exterior programs. Multi-Agent Supervisor (Beta) orchestrates advanced workflows throughout brokers and instruments, and ai_parse_document (Public Preview) extracts insights from unstructured content material—multi functional ruled atmosphere.
“Databricks’ ai_parse_document reduces configuration overhead, enabling knowledge scientists to spend much less time on setup and extra time advancing advanced, customer-focused options.” — Meiling He, Sr. Knowledge Science Supervisor, Rockwell Automation
What You Can Construct with Agent Bricks
Agent Bricks powers a spread of agent patterns—from knowledge copilots to manufacturing automations—serving to groups flip enterprise knowledge into intelligence and motion.
- Information Assistants: Cause over structured and unstructured knowledge to reply domain-specific questions, reminiscent of an HR chatbot that explains firm insurance policies or a technician assistant that searches manuals to resolve points quicker.
- Doc Intelligence: Parse PDF contracts or stories to transform unstructured content material into structured knowledge for downstream evaluation or integration with Information Assistants.
- Course of and Workflow Brokers: Execute ruled actions reminiscent of updating information, submitting tickets, or triggering pipelines—for instance, figuring out churn dangers and routinely sending retention gives.
- Product Intelligence – Embed reasoning or content material technology into purposes, reminiscent of a personalised well being assistant and appointment scheduler.
Every agent sort will be applied utilizing customized code, declarative workflows, or agentic AI capabilities, giving groups the pliability to start out easy, scale securely, and standardize over time.
“MCP marks an necessary step towards open, interoperable enterprise AI – one thing that has been core to our method at Glean from day one. The brand new MCP Catalog in Databricks Market is a crucial a part of that evolution. By way of the MCP Catalog in Databricks Market, prospects can now prolong Glean’s Enterprise Graph to construct work brokers that purpose over ruled knowledge and unstructured information, powering use circumstances like buyer 360, renewal threat, and marketing campaign insights with confidence.” — Emrecan Dogan, Head of Product, Glean
“The brand new MCP catalog in Databricks Market permits prospects to provision our high-quality net index as a ruled device with a single click on. When mixed with Agent Bricks, this instantly empowers brokers to make real-world choices grounded within the freshest data, basically accelerating the journey from knowledge to motion.” — Bryan McCann, Co-Founder and CTO, You.com
The Path to AI Agent Manufacturing Begins Right here
Agent Bricks establishes the enterprise customary for constructing, governing, and scaling trusted AI brokers.
Keep tuned all through the Week of Brokers as we publish deep-dive blogs on every of those launches.
Construct Actionable Brokers: Leverage the Agent Bricks Multi-Agent Supervisor to deploy multi-step, ruled workflows.