 |
Agent Bricks automatically optimizes AI agents on customers' unique data to deliver cost-efficient, trustworthy agents
SAN FRANCISCO, June 11, 2025 /PRNewswire/ -- Data + AI Summit -- Databricks, the Data and AI company, today introduced 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.
Why a New Approach to Agents is Needed
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.
Agent Bricks: Instantly Build and Optimize AI Agents with Your Enterprise Data
First, Agent Bricks automatically generates the task-specific evaluations and LLM judges to assess quality. Next, synthetic data is created that looks like the customer's data to substantially supplement the agent's learning. Last, Agent Bricks searches across the full gamut of optimization techniques to refine the agent. At the end of this automated workflow, the customer simply needs to select the iteration that matches the balance of quality and cost that they want the agent to achieve. The result: a production-grade, domain-specific AI agent that delivers consistent, intelligent output — fast.
Agent Bricks addresses several common customer use cases across key industries:
- Information Extraction Agent turns documents, like emails, PDFs and reports into structured fields like names, dates and product details. Retail organizations can easily pull product details, prices and descriptions from supplier PDFs, even if the documents are complex or formatted differently.
- Knowledge Assistant Agent solves the issue of getting vague or flat-out wrong answers from chatbots, with fast, accurate answers grounded in your enterprise data. Manufacturing organizations can empower technicians to get instant, cited answers from SOPs and maintenance manuals without needing to dig through binders.
- Multi-Agent Supervisor enables you to build multi-agent systems that seamlessly stitch together agents across Genie spaces, other LLM agents and tools such as MCP. Financial Services organizations can orchestrate multiple agents to handle intent detection, document retrieval, and compliance checks, creating complete, personalized responses for advisors and clients.
- Custom LLM Agent transforms text for custom tasks such as content generation or custom chat, optimized for your industry. Marketing teams can build customized agents to generate marketing copy, blogs or press releases that respect their organization's brand.
"Agent Bricks is a whole new way of building and deploying AI agents that can reason on your data," said Ali Ghodsi, CEO and Co-founder of Databricks. "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."
Customer Momentum
"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." — Joseph Roemer, Head of Data & AI, Commercial IT, AstraZeneca
"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." — Chris Nishnick, Director of AI, Lippert
"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." — Roman Bugaev, CTO, Flo Health
"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." — Ryan Jockers, Assistant Director of Reporting and Analytics at the North Dakota University System
"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." — Joel Wasson, Manager Enterprise Data & Analytics, Hawaiian Electric
Additional Mosaic AI Features Launching at Data + AI Summit
- Support for serverless GPUs: Databricks now offers support for serverless GPUs, enabling teams to fine-tune models, run classic machine learning or deep learning workloads and experiment with LLMs, all without the need to provision or manage GPU infrastructure. With serverless GPU compute, users gain fast, on-demand and scalable access to high-performance compute resources, so they can build AI applications faster and without the operational overhead or cost inefficiencies of traditional GPU clusters.
- MLflow 3.0: A unified platform for managing the AI lifecycle: Databricks today released MLflow 3.0, the latest version of the world's most popular AI development framework. Entirely redesigned for GenAI, MLflow 3.0 lets users monitor, trace and optimize AI agents hosted on any platform. With integrated prompt management, quality metrics, human feedback and LLM-based evaluation, teams can easily visualize, compare and debug the performance of AI agents across environments. MLflow traces and evaluation results can be integrated with any existing data lakehouse, letting users leverage production trace data to improve the accuracy of their agents. MLflow is open source and downloaded more than 30 million times each month.
Together with Agent Bricks, these innovations make Databricks the most complete platform for production-grade GenAI, from building and tuning to evaluating, comparing and securely deploying.
Availability
Agent Bricks and Serverless GPU Compute are available starting today in Beta. MLflow 3.0 is generally available. Visit this page to learn more about Agent Bricks.
About Databricks
Databricks is the Data and AI company. More than 15,000 organizations worldwide — including Block, Comcast, Condé Nast, Rivian, Shell and over 60% of the Fortune 500 — rely on the Databricks Data Intelligence Platform to take control of their data and put it to work with AI. Databricks is headquartered in San Francisco, with offices around the globe and was founded by the original creators of Lakehouse, Apache Sparkâ„¢, Delta Lake, MLflow, and Unity Catalog. To learn more, follow Databricks on X, LinkedIn and Facebook.
CONTACT: Press@databricks.com
Agent Bricks automatically optimizes AI agents on customers' unique data to deliver cost-efficient, trustworthy agents
SAN FRANCISCO, June 11, 2025 /PRNewswire/ -- Data + AI Summit -- Databricks, the Data and AI company, today introduced 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.
Why a New Approach to Agents is Needed
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.
Agent Bricks: Instantly Build and Optimize AI Agents with Your Enterprise Data
First, Agent Bricks automatically generates the task-specific evaluations and LLM judges to assess quality. Next, synthetic data is created that looks like the customer's data to substantially supplement the agent's learning. Last, Agent Bricks searches across the full gamut of optimization techniques to refine the agent. At the end of this automated workflow, the customer simply needs to select the iteration that matches the balance of quality and cost that they want the agent to achieve. The result: a production-grade, domain-specific AI agent that delivers consistent, intelligent output — fast.
Agent Bricks addresses several common customer use cases across key industries:
- Information Extraction Agent turns documents, like emails, PDFs and reports into structured fields like names, dates and product details. Retail organizations can easily pull product details, prices and descriptions from supplier PDFs, even if the documents are complex or formatted differently.
- Knowledge Assistant Agent solves the issue of getting vague or flat-out wrong answers from chatbots, with fast, accurate answers grounded in your enterprise data. Manufacturing organizations can empower technicians to get instant, cited answers from SOPs and maintenance manuals without needing to dig through binders.
- Multi-Agent Supervisor enables you to build multi-agent systems that seamlessly stitch together agents across Genie spaces, other LLM agents and tools such as MCP. Financial Services organizations can orchestrate multiple agents to handle intent detection, document retrieval, and compliance checks, creating complete, personalized responses for advisors and clients.
- Custom LLM Agent transforms text for custom tasks such as content generation or custom chat, optimized for your industry. Marketing teams can build customized agents to generate marketing copy, blogs or press releases that respect their organization's brand.
"Agent Bricks is a whole new way of building and deploying AI agents that can reason on your data," said Ali Ghodsi, CEO and Co-founder of Databricks. "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."
Customer Momentum
"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." — Joseph Roemer, Head of Data & AI, Commercial IT, AstraZeneca
"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." — Chris Nishnick, Director of AI, Lippert
"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." — Roman Bugaev, CTO, Flo Health
"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." — Ryan Jockers, Assistant Director of Reporting and Analytics at the North Dakota University System
"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." — Joel Wasson, Manager Enterprise Data & Analytics, Hawaiian Electric
Additional Mosaic AI Features Launching at Data + AI Summit
- Support for serverless GPUs: Databricks now offers support for serverless GPUs, enabling teams to fine-tune models, run classic machine learning or deep learning workloads and experiment with LLMs, all without the need to provision or manage GPU infrastructure. With serverless GPU compute, users gain fast, on-demand and scalable access to high-performance compute resources, so they can build AI applications faster and without the operational overhead or cost inefficiencies of traditional GPU clusters.
- MLflow 3.0: A unified platform for managing the AI lifecycle: Databricks today released MLflow 3.0, the latest version of the world's most popular AI development framework. Entirely redesigned for GenAI, MLflow 3.0 lets users monitor, trace and optimize AI agents hosted on any platform. With integrated prompt management, quality metrics, human feedback and LLM-based evaluation, teams can easily visualize, compare and debug the performance of AI agents across environments. MLflow traces and evaluation results can be integrated with any existing data lakehouse, letting users leverage production trace data to improve the accuracy of their agents. MLflow is open source and downloaded more than 30 million times each month.
Together with Agent Bricks, these innovations make Databricks the most complete platform for production-grade GenAI, from building and tuning to evaluating, comparing and securely deploying.
Availability
Agent Bricks and Serverless GPU Compute are available starting today in Beta. MLflow 3.0 is generally available. Visit this page to learn more about Agent Bricks.
About Databricks
Databricks is the Data and AI company. More than 15,000 organizations worldwide — including Block, Comcast, Condé Nast, Rivian, Shell and over 60% of the Fortune 500 — rely on the Databricks Data Intelligence Platform to take control of their data and put it to work with AI. Databricks is headquartered in San Francisco, with offices around the globe and was founded by the original creators of Lakehouse, Apache Sparkâ„¢, Delta Lake, MLflow, and Unity Catalog. To learn more, follow Databricks on X, LinkedIn and Facebook.
CONTACT: Press@databricks.com
** The press release content is from PR Newswire. Bastille Post is not involved in its creation. **
Databricks Launches Agent Bricks: A New Approach to Building AI Agents
Multi-phase, multi-region rollout will deliver advanced AMD AI silicon and the open AMD ROCm software stack to frontier-model, enterprise, and sovereign AI customers across global markets
SINGAPORE, May 27, 2026 /PRNewswire/ -- OneQode, a global provider of mission-critical digital infrastructure, today announced a collaboration with AMD to deploy AMD Instinct™ GPUs, as well as announcing plans to deploy AMD Helios rack-scale solution as the platform foundation for OneQode's global AI infrastructure rollout.
OneQode plans a phased rollout anchored by AMD Instinct™ MI355X GPUs in initial deployments and incorporating AMD Helios solution in the future. The deployment will run on the open AMD ROCm™ software stack, giving customers a standards-based, vendor-neutral foundation for large-scale AI training and inference.
The announcement follows OneQode's recently announced 110MW AI infrastructure agreement with Bitzero in Norway, and reflects the company's broader strategy to deploy high-performance AI capacity across Europe and Asia-Pacific. It leverages their existing cloud and telecommunications footprint deployed across 5 continents over the last 7 years, and will also incorporate their unique low-latency, sovereignty-focused product offerings.
OneQode expects to support a range of high-performance AI workloads, powered by AMD AI solutions, including frontier-model training and inference, enterprise AI, and sovereign AI for governments, research institutions, and AI-first organisations.
"Demanding AI workloads require high-performance compute, scalable infrastructure and an open software ecosystem," said Negin Oliver, corporate vice president, Business Development for AI, AMD. "AMD Instinct GPUs and the unifying AMD ROCm open software stack are designed to help customers accelerate large-scale AI training and inference with the performance, efficiency and flexibility they need. We're pleased to work with OneQode as it expands access to AMD AI solutions for customers globally."
"AMD is shipping some of the most compelling AI hardware in the market," said Matthew Shearing, Founder and CEO of OneQode, "The challenge now is putting that silicon in the right places - close to the customers, sovereign workloads, and AI-first organisations that need it. That's what OneQode does. We've spent nearly a decade building performance infrastructure across Europe, Asia-Pacific, and the global south, serving the kinds of workloads where uptime, latency and sovereignty actually matter. We're aiming to be AMD's partner of choice for extending AMD Instinct silicon at scale into the regions that need it most."
"We're genuinely pumped to be working with AMD," said Joe Swinn, Head of Product at OneQode. "We've been deploying infrastructure at scale globally for seven years, including some blazing-fast AMD EPYC processor-based private cloud builds, and this is one we've been waiting for. The AMD Instinct MI355X is a serious piece of silicon, and AMD Helios is built for the kinds of AI workloads our customers actually want to run. The AMD team have been brilliant to deal with, and we can't wait to get this kit in front of customers."
About OneQode
OneQode is a global provider of performance digital infrastructure. With a vertically-integrated platform that spans cloud compute, low-latency networking and sovereign technology across over 30 datacentres in 5 continents, they enable enterprises, governments and performance-hungry businesses to run AI & mission-critical workloads at scale, across the globe. Learn more at oneqode.com.
** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **
OneQode to Deploy AMD Instinct GPUs and Plans for AMD Helios Rack-Scale Solution for Global AI Infrastructure
