Databricks, the Data and AI company, announced Agent Bricks, a new, automated way to create high-performing AI agents tailored to your business. Just provide a high-level description of the agent’s task, and connect your enterprise data — Agent Bricks handles the rest. Agent Bricks are optimized for common industry use cases, including structured information extraction, reliable knowledge assistance, custom text transformation and orchestrated multi-agent systems. Agent Bricks is available starting today in Beta.
Agent Bricks uses novel research techniques developed by Mosaic AI Research to automatically generate domain-specific synthetic data and task-aware benchmarks. Based on these benchmarks, it automatically optimizes for cost and quality, saving enterprises from the tedious trial-and-error of current approaches. Now, teams can achieve production-level accuracy and cost efficiency right from the start. Built-in governance and enterprise controls let teams move from concept to production quickly, without stitching together separate tools.
Quality and cost are the main barriers keeping most agentic experiments from reaching production. Without high-quality evaluation, most teams are left to judge agents by gut checks, leading to inconsistent quality and costly experiments that are impossible to scale. The complexity of AI, with new models and techniques emerging constantly, only adds to the challenge. Customers need domain-specific, repeatable, objective and continuous evaluations to ship AI agents that they can trust and afford. And they need to be able to leverage the latest technology without breaking the bank and reskilling the team. Databricks built Agent Bricks to deliver on these important customer requirements that are currently unmet by the industry.
Ali Ghodsi, CEO and Co-founder of Databricks
Agent Bricks is a whole new way of building and deploying AI agents that can reason on your data. For the first time, businesses can go from idea to production-grade AI on their own data with speed and confidence, with control over quality and cost tradeoffs. No manual tuning, no guesswork and all the security and governance Databricks has to offer. It’s the breakthrough that finally makes enterprise AI agents both practical and powerful.
Joseph Roemer, Head of Data & AI, Commercial IT, AstraZeneca
With Agent Bricks, our teams were able to parse through more than 400,000 clinical trial documents and extract structured data points — without writing a single line of code. In just under 60 minutes, we had a working agent that can transform complex unstructured data usable for Analytics.
Chris Nishnick, Director of AI, Lippert
With Agent Bricks, we can quickly productionize domain-specific AI agents for tasks like extracting insights from customer support calls—something that used to take weeks of manual review. It’s accelerated our AI capabilities across the enterprise, guiding us through quality improvements in the grounding loop and identifying lower-cost options that perform just as well.
Roman Bugaev, CTO, Flo Health
Agent Bricks enabled us to double our medical accuracy over standard commercial LLMs, while meeting Flo Health’s high internal standards for clinical accuracy, safety, privacy, and security. By leveraging Flo’s specialized health expertise and data, Agent Bricks uses synthetic data generation and custom evaluation techniques to deliver higher-quality results at a significantly lower cost. This enables us to scale personalized AI health support efficiently and safely, uniquely positioning Flo to advance women’s health for hundreds of millions of users.
Ryan Jockers, Assistant Director of Reporting and Analytics at the North Dakota University System
Agent Bricks allowed us to build a cost-effective agent we could trust in production. With custom-tailored evaluation, we confidently developed an information extraction agent that parsed unstructured legislative calendars—saving 30 days of manual trial-and-error optimization.
Joel Wasson, Manager Enterprise Data & Analytics, Hawaiian Electric
With over 40,000 complex legal documents, we needed high precision from our internal 'Regulatory Chat Tool’. Agent Bricks significantly outperformed our original open-source implementation (built on LangChain) in both LLM-as-judge and human evaluation accuracy metrics.
