Cool stuff Google Cloud customers built, Oct. edition: Research agents, a World Series hit, agentic "teams" & more

AI and cloud technology are reshaping every corner of every industry around the world. Without our customers, there would be no Google Cloud, as they are the ones building the future on our platform. In this regular round-up, we dive into some of the exciting projects redefining businesses, shaping industries, and creating new categories. 

For our latest edition, we look into new research agents from Deutsche Bank and The Max Planck Institute; helping devs strut their stuff with new databases for Rent the Runway; mortgage lender Mr. Cooper’s “team” of AI agents answering tough customer questions; an AI assistant for doctors at Seattle Children’s; FOX Sports brings AI to the World Series broadcast booth & SmarterX helps customers build custom LLMs

Be sure to check back in September to see how more industry leaders and exciting startups are putting Google Cloud technologies to use. And if you haven’t already, please peruse our list of 1,001 real-world gen AI use cases from our customers.

Deutsche Bank reimagines research with AI agents

Who: At Deutsche Bank Research, the core mission of analysts is delivering original, independent economic and financial analysis. However, creating research reports and notes relies heavily on a foundation of painstaking manual work.

What they did: To enhance the research analyst experience and reduce the reliance on manual processes and outsourcing, the team at Deutsche Bank created DB Lumina — an AI-powered research agent that helps automate data analysis, streamline workflows, and deliver more accurate and timely insights — all while maintaining the stringent data privacy requirements for the highly regulated financial sector. DB Lumina’s core conversational interface enables analysts to interact with Google’s state-of-the-art AI foundation models , including the multimodal Gemini models orchestrated through Vertex AI.

Why it matters: DB Lumina is already in the hands of around 5,000 users across Deutsche Bank Research, with plans to roll out to 10,000 by year end. Analysts reported significant time savings, saving 30 to 45 minutes on preparing earnings note templates and saving up to two hours when writing research reports and roadshow updates. Analysts are also reporting increased depth in their work, with one analyst achieving 50% more detail, adding additional sections by region and activity.

Learn from us: “DB Lumina has proved the value of combining RAG, gen AI, and conversational AI, but this is just the start of our journey. We believe the future lies in embracing and refining the ‘agentic’ capabilities that are inherent in our architecture. We envision building and orchestrating a system where various components act as agents — all working together to provide intelligent and informed responses to complex financial inquiries.” – Max Sommerfeld, Head of Applied AI Engineering , Deutsche Bank, & Crispin Velez, Global AI incubation, Google Cloud

Rent the Runway supercharges developer speed and insights

Who: Rent the Runway gives customers a “Closet in the Cloud” — on-demand access to designer clothing without the need for ownership. To address both our operational complexity and the high expectations of customers, Rent the Runway is investing heavily in building modern, data-driven services that support every touchpoint.

What they did: The team migrated to CloudSQL with the help of Database Migration Service. The new platform offered the benefits of a managed service — automated backups, simplified disaster recovery, no more patching – while preserving compatibility with the MySQL stack Rent the Runways systems already relied on.

Why it matters: A big win was the developer experience. With built-in query insights and tight integration with Google Cloud, Cloud SQL made it easier for engineers to own what they built. With better visibility and guardrails, our teams are shipping higher-quality code and catching issues earlier in the lifecycle. Meanwhile, our DBAs can focus on strategic initiatives — things like automation and platform-wide improvements — rather than being stuck in a ticket queue. The migration also saved $180,000 annually.

Learn from us: “We’re building toward a platform where engineering teams can move fast without trading off safety or quality. That means more automation, more ownership, and fewer handoffs. With Cloud SQL, we’re aiming for a world where schema updates are rolled out as seamlessly as application code.” – Marcus Creavin, Senior Director, Head of Data, Rent the Runway

Mr. Cooper’s “team” of agents solves complex mortgage questions

Who: Mortgage lender Mr. Cooper’s mission is to “Keep the dream of homeownership alive,” aiming to keep rates and services affordable in one of the most expensive consumer markets there is. We partnered with Google Cloud Consulting to develop an agentic AI system designed to complement and support our team. We call it the Coaching Intelligent Education & Resource Agent, or CIERA.

What they did: Rather than a single agent, CIERA is just like any effective team, with individual agents contributing discreet skills that work together synergistically. There’s a head agent interpreting and overseeing the initial prompt, an orchestrator agent, task and data specialists, a memory agency with recall of past actions, and an evaluation agent that tests accuracy and detects hallucinations. CIERA was built with Vertex AI.

Why it matters: For customers, Mr. Cooper projects a reduction in wait times and a higher rate of first-contact resolution. By automating tedious research for human agents, CIERA will free them to focus on sensitive and complex customer relationships that require a human touch and create better tools and resources for more engaging work. The company anticipates a major reduction in average handling times for a large segment of inquiries and faster, more accurate resolutions.

Learn from us: "The architectural patterns developed with CIERA are not limited to mortgage servicing. This agentic approach — of using an orchestrator to manage a team of specialized AI agents—is a powerful blueprint that can be applied to any industry, including healthcare, logistics and manufacturing, by grappling with information and task complexity." – Meenakshi Subramanian, Senior Principal Architect, Mr. Cooper & Shrihari Srinivasa Murthy, Lead Software Development Engineer, Mr. Cooper

Seattle Children’s AI assistant helping doctors work faster and better

Who: Seattle Children’s is the largest pediatric healthcare system in the world, with 48 hospitals across Alaska, Montana, Idaho, and Washington. With so much ground to cover and diverse patient populations to treat, Seattle Children’s created its pediatric clinical pathways, a set of standardized protocols designed to help clinicians make quicker and more reliable decisions. It’s a critical tool, but cumbersome and PDF- or paper-based.

What they did: Using  Vertex AI and Gemini, Seattle Children’s was able to quickly develop its Pathways Assistant. After processing a question, Pathway Assistant searches its PDF metadata, which contains semi-structured data in JSON format that’s been extracted from the PDFs by Gemini and curated by clinicians. It then selects the most relevant PDFs, parses the information — including any complex flowcharts, diagrams, and illustrations embedded in them — and answers the clinician’s question in just a few seconds. 

Why it matters: Pathways Assistant has greatly increased the speed and effectiveness with which clinicians get to the right decisions at the point of care, drastically reducing research time and improving patient safety and outcomes. Ultimately, clinicians can spend more time with more patients, not with more PDFs.

Learn from us: "Ultimately, Pathway Assistant is not a decision-making tool but rather an information-finding tool. Research into critical, evidence-based guidelines that used to take hours now takes minutes." – Dr. Darren Migita, Medical Director, Clinical Effectiveness, Seattle Children’s Hospital & Jérôme Massot, Gen AI Cloud Architect, Google Cloud

FOX Sports pitches AI-powered player insights at The World Series

Who: Since 2000, FOX Sports has been the broadcast home of the MLB World Series. The production team is always looking to keep storylines fresh for commentators and analysts like Joe Davis, John Smoltz, and Alex Rodriguez.

What they did: The new FOX Foresight tool is an AI platform built with Vertex AI that was trained on data from many seasons of major league play, down to the smallest details. This allows the production team to ask incredibly specific questions and get answers in seconds. For example, if a certain left-handed hitter is coming up to bat, they could ask: “Who are the top five left-handed batters who played in this year’s playoffs? Now who was best in the ninth inning, and what about when the bases are loaded?

Why it matters: Had they relied on traditional research methods alone, this kind of cross-referencing could have taken minutes or more — long enough that an entire inning might have passed by. But with FOX Foresight, this task takes seconds.

Learn from us: “It helps us spot the big stories — like who’s heating up, who’s struggling and which performances are shaping this postseason,” – Alex Rodriguez, FOX Sports MLB Analyst and former Yankees All-Star

Max Planck Institute shares expert skills with multimodal agents

Who: The Max Planck Institute of Biochemistry in Germany is one of the world’s leading research labs. Part of what makes scientific work so difficult and time consuming is the years it can take to develop expertise, for example on mass spectrometry equipment used for studying cells.

What they did: Researchers at the institute and Google Cloud built a Proteomics Lab Agent that simplifies performing complex scientific procedures through personalized AI guidance — making them easier to execute while automatically documenting the process for others to study. The agent was built using the Agent Development Kit (ADK), Google Cloud infrastructure, and Gemini models, which offer advanced video and long-context understanding uniquely suited to the needs of advanced research. 

Why it matters: By making it easier to spot mistakes and offering personalized guidance, the agent can reduce troubleshooting time and build towards a future where real-time AI guidance can help prevent errors from happening. In early tests, the agent successfully identified 74% of all procedural errors (a metric known as recall) with an overall accuracy of 77% when comparing 28 recorded lab procedures against their reference protocols. Researchers also reported creating reference protocols 10-times faster, in about 2.6 minutes.

Learn from us: "This approach helps us capture and share the practical knowledge that is often lost when a researcher leaves the lab. This collected experience will not only accelerate the training of new team members but also creates the data foundation we need for future innovations like predictive instrument maintenance for mass spectrometers and automated protocol harmonization within individual labs and across different labs." – Matthias Mann, Director, Research Department Proteomics and Signal Transduction, Max Planck Institute

SmarterX delivers custom LLMs for its customers

Who: SmarterX is an AI consultancy that helps retailers, manufacturers, and logistics companies minimize regulatory risk, maximize sales, and protect consumers and the environment by giving them AI-driven tools to safely and compliantly sell, ship, store, and dispose of their products

What they did: SmarterX uses BigQuery, Gemini models, and Vertex AI to collect, process, and analyze vast amounts of unstructured regulatory and product data from across the web, using it to train custom, highly accurate large language models for customers. Many don’t have the resources for their own data scientists and programers, so these SmarterX is helping these large consumer packaged goods brands and retailers sell, ship, store, and dispose of regulated products compliantly, for example.

Why it matters: SmarterX has found that built-in grounding — the ability to connect model output to verifiable information sources — makes Gemini a safer, more conscientious way to assemble data for SmarterX customers. And retrieval-augmented generation, or RAG, allows SmarterX to connect Gemini with customers’ proprietary databases, enhancing the LLMs’ accuracy and relevance while helping ensure the security of his customers’ data.

Learn from us: “In the past, you’d need to know how to use a modeling tool, a database tool, and an API deployment tool, as well as understand the math underlying a particular model and how to write code in order to build and deploy a model. Having it all in a single environment with familiar user interfaces enables people without a data science background to be much more productive. It’s incredibly freeing and empowering for them.” – Russell Foltz-Smith, executive vice-president for product and technology, SmarterX