Agent Bricks
Recent items mentioning Agent Bricks across the Databricks ecosystem — releases, news, videos, and community Q&A. Updated hourly.
Agent Bricks, a new Databricks offering, is now available on the Free Edition, providing developers with a complete toolkit for building end-to-end data and AI projects 28. Databricks highlights Agent Bricks' ability to give developers choice, context, and control, as demonstrated in a recent video 4. The technology is already in use, with Kythera Labs leveraging AI agents built on Databricks to provide health system leaders with governed answers from 339 billion claims 5, and Mercedes-Benz Korea using Agent Bricks with Genie to provide consistent answers from a trusted "Talk to Data" solution 10.
Generated daily from the 10 most recent items mentioning Agent Bricks. Click any [N] to jump to the source.
NewsWhat’s coming next to Free Edition
Databricks announces the availability of Genie, GPUs, Agent Hooks, Lakehouse, and Lake Flow Designer on its Free Edition. This update provides virtually all of Databricks' production platform features for free, enabling users to learn and build data and AI projects.
Agentbricks Knowledge Assistant - Facing Issue with Agent Creation and Source Visibility
What if the answer was already in your data?
Kythera Labs' AI agents, built on Databricks, now provide health system leaders with governed, trustworthy answers to strategic questions from 339 billion claims. A Louisiana health system saw 150% more visibility into patient encounters and $3.8M in estimated annualized value in 10 days.
EventsRecap of product announcements from Data + AI Summit 2026 | Day 1
Databricks announced several new products and features at the Data + AI Summit 2026, Day 1, including the Genetic Data Foundation, Lakehouse RT, Lake Base with disaster recovery, Lake Flow, Genie Ontology, Unity AI Gateway, Omnigent, and various Genie agents (Genie 1, Genie Code, Genie Agents). They also introduced new applications like Lake Watch for SIM and Customer Lake for CP.
What’s coming next to Free Edition
Databricks Free Edition now includes every core practitioner feature, expanding with Genie Code, GPUs, Lakebase, Lakeflow Designer, and Agent Bricks. This gives users a complete, free toolkit for building end-to-end data and AI projects.
Agent Bricks: Data + AI Summit 2026
Last year at the Data + AI Summit, we launched Agent Bricks, ushering in a new way...
Unlocking semantics for AI: How Mercedes-Benz Korea built trusted “Talk to Data” at scale
Mercedes-Benz Korea built a trusted "Talk to Data" solution at scale by making 500+ KPI definitions available in an AI-ready semantic layer on Unity Catalog metric views, accelerating the transition with an automated DAX-to-Metric-View transpiler. This governed semantic layer supports both existing BI and new "Talk to Data" experiences, with Genie and Agent Bricks providing consistent answers and shaping a playbook for persona-based AI agents across markets.
Self Learning Testing Framework using Experiment Tab in Agent Bricks
3x Faster Search: Parallel Test-Time Scaling with Instructed-Retriever-1
Instructed-Retriever-1 now delivers 3x faster search for Agent Bricks Knowledge Assistant. This parallel test-time scaling update also improves quality for Databricks practitioners.
Bring Databricks into Kiro IDE with the AI Dev Kit Power
The Databricks AI Dev Kit Power now offers a one-click setup to integrate Kiro IDE with the full Databricks platform, providing AI-assisted development grounded in your workspace's Unity Catalog metadata. This new path, alongside a lighter PAT-based option, ensures your AI assistant writes SQL with actual columns and respects all row, column, and tag-based grants.
NewsBanks' Secret Weapon Against Money Laundering: Multi-Agent AI
Databricks demonstrates a multi-agent AI solution for Anti-Money Laundering (AML) operations, significantly reducing false positives and accelerating investigation cycles from hours to minutes. The platform unifies siloed systems, employs specialized AI agents for analysis and recommendations, and offers AI-assisted SAR generation and executive-level reporting with natural language chat.
Multi-Agent Supervisor for Hybrid Retrieval with Agent Bricks and MLflow
You can now manage Git credentials for service principals and permissions for Agent Bricks resources. Key fixes include proper updates for metastore external access, reliable destruction of UC objects, and an increased timeout for vector search index creation.
Announcing Lakebase Change Data Feed (CDF)
Lakebase Change Data Feed (CDF) is now in Public Preview, eliminating pipeline sprawl from operational databases by exposing every table's changes through Unity Catalog Managed Tables. This enables native CDC governed end-to-end without sidecar infrastructure, allowing operational data to function as the native Bronze layer in the medallion architecture.
Document Intelligence on Databricks
80% of enterprise data is locked inside PDFs, scans, emails and contracts and most teams still treat it as someone else's problem. Document Intelligence on Databricks changes that. One SQL function (ai\_parse\_document), governed by Unity Catalog, integrated with Lakeflow for ingestion, Agent Bricks for structured extraction, and Vector Search for RAG. No stitched-together OCR vendors, no brittle Python glue, no separate platform to govern. I put together with [Archika Dogra](https://www.linkedin.com/in/archikadogra/) a walkthrough showing how it actually works end-to-end from a folder of raw PDFs to queryable Delta tables and downstream agents. ▶️ [https://youtu.be/sdG73gI143c](https://youtu.be/sdG73gI143c) Curious to hear what use cases you're tackling invoices, contracts, claims, technical docs? Drop them in the comments.
TutorialsBuilding Enterprise-Ready Agents using Agent Bricks
Databricks Agent Bricks is a unified platform designed to help enterprises build and manage AI agents, addressing challenges like low-quality reasoning on proprietary data, lack of governance, and fragmented toolchains. It demonstrates how to create knowledge assistants for unstructured data and AI Genies for structured data, integrating with Unity Catalog for governance and MLflow for observability and evaluation.
From "What Happened?" to "What Will Happen?"
Conversational BI now delivers predictive answers in seconds, not days, by fusing Genie for dynamic feature engineering with TabPFN for zero-training prediction, orchestrated by Agent Bricks. This self-assembling pipeline eliminates data science bottlenecks for business users, providing a governed experience backed by Unity Catalog and MLflow.
TutorialsHow to Build an AI Security Governance Hub with Agent Bricks
Databricks Agent Bricks enables building an AI Security Governance Hub by transforming static security playbooks into adaptive multi-agent systems. The video demonstrates combining a knowledge assistant for unstructured documents and a Genie space for structured data into a supervisor agent, then details how to tune and monitor these agents for improved performance and data privacy.
NewsDatabricks in 3 minutes. The unified data and AI platform, explained.
Databricks unifies diverse data sources into a single data lake, providing a governed platform for analytics and AI. It offers capabilities like fine-grained access control, natural language querying with AI, and company-wide intelligent agents.
How to transform document activation workflows with Genie and Agent Bricks
Databricks shipped a solution combining AI/BI Genie, Agent Bricks, and Unity Catalog to automate document activation workflows. This enables multi-agent orchestration for extracting, processing, and activating data from diverse documents, improving efficiency and governance.
NewsDatabricks Apps vs Model Serving: Authentication, Cost, and Performance Compared
Databricks Apps are now the recommended first choice for deploying agents due to their flexibility in handling full-stack applications with multiple components, offering faster iteration and local testing compared to Model Serving. Model Serving remains suitable for use cases prioritizing high QPS, governance features like AI Gateway, inference tables, and guardrails, or when scaling to zero is acceptable for cost optimization.
NewsTurbo-Charge your Agents with instant MCP in Databricks
The video demonstrates how to use Model Context Protocol (MCP) in Databricks to give AI agents "superpowers" by enabling them to interact with various tools and data sources. It shows how to easily set up MCP servers within Databricks to connect agents to Unity Catalog functions, vector search, external APIs, and even marketplace MCP services, all without extensive coding.
EventsDAIS25 Keynote Day 2 Sizzle
Databricks announced a free edition of its platform, allowing users to access a slice of Databricks forever without a credit card. The company also showcased Agent Bricks for building production-ready AI agents and Databricks Apps for secure data intelligence applications.
TutorialsBuild a Databricks Knowledge Assistant in less than 10 steps! with Agent Bricks | Advancing AI
The video demonstrates building a Databricks knowledge assistant using Agent Bricks, a no-code platform for creating agentic systems. It shows how to upload company policy PDFs to Unity Catalog, configure a knowledge assistant to answer questions based on these documents, and deploy it as a Streamlit chatbot application.
Events[Demo] Introducing Agent Bricks: Auto-Optimized Agents Using Your Data
Agent Bricks demonstrates an auto-optimized agent that uses company data to generate a comprehensive launch report for a new product. The agent autonomously queries different internal agents (e.g., marketing, R&D, BizOps) to gather information on market trends, existing recipes, development timelines, costs, and more, culminating in a CEO-ready report.
