Lean teams often struggle to manage the overwhelming volume of unstructured content. This session explores how Gemini, Google’s cutting-edge AI, can help you easily structure and analyze this data. Learn how Box AI is utilizing Gemini with their customer solutions, and examine a real-world use case from Fundwell. Get insights on how to automate data extraction, enhance customer interactions, streamline operations, and gain a significant competitive edge. Discover how AI can empower your team to unlock the true value within your data.

It’s never a dull day in the world of models. Join us in this session to learn about the latest advancements in Gemini 2.5. We’ll explore its breakthrough capabilities and performance, and the new use cases enabled by our flagship model.

Join this Cloud Talk to explore how Large Language Models (LLMs) can revolutionize your data workflows. Learn to automate SQL query generation and stream results into Confluent using Vertex AI for real-time analytics and decision-making. Dive into integrating advanced AI into data pipelines, simplifying SQL creation, enhancing workflows, and leveraging Vertex AI for scalable machine learning. Discover how to optimize your data infrastructure and drive insights with Confluent’s Data Streaming Platform and cutting-edge AI technology.

This Session is hosted by a Google Cloud Next Sponsor.
Visit your registration profile at g.co/cloudnext to opt out of sharing your contact information with the sponsor hosting this session.

App life cycles with Google Cloud databases and runtimes have gotten smarter. This session takes you through the life cycle of building and optimizing scalable, high-performance generative AI apps. We’ll use Google’s latest natural language and vector search technologies to build the “art of the possible” for AI-powered software. We’ll also cover various app design patterns using Gemini Code Assist, foundation models, agentic retrieval-augmented generation (RAG), and orchestration frameworks, and show you how it all comes together in a live demo.

The world of data security and privacy is changing. Quantum computing threatens traditional encryption, but you can stay ahead. Learn how to protect your AI and machine learning (ML) models and your sensitive data with cutting-edge techniques and tools like Gemini. This session covers end-to-end privacy, confidential computing with Google Cloud, navigating the post-quantum cryptography (PQC) landscape, the challenges and opportunities of PQC, and how Google Cloud is preparing you for the future.

Join fellow Google Kubernetes Engine and ML engineers to share experiences building scalable, flexible, and resource-efficient machine learning platforms on GKE. Let's discuss strategies to best leverage GKE's features for serving open LLM models and orchestrating TPU/GPU’s at scale. Come prepared to share, ask questions, connect with others, and help each other succeed with GKE for ML.

Google Workspace is essential to getting work done but many don’t realize they can extend Google Docs, Sheets, and Slides with Apps Script. This lightning talk will show how to get more out of Workspace with Apps Script and take it even further with Gemini. Master automation by generating code snippets, automating tedious tasks, all using AI to handle the busywork so focus stays on what truly matters. Whether beginning your journey or refining your skills, you will train in the ways of AI-driven automation and take your workflow to hyperspeed.

Launching LLM-powered products is transformative but requires strategic execution. This session shares lessons from embedding AI solutions (built with Gemini on Google Cloud) into real use cases. Learn how we avoided pitfalls, tackled automation myths, and delivered real value. Gain insights on identifying high-impact AI opportunities, validating solutions, and iterating for successful product launches.

This Session is hosted by a Google Cloud Next Sponsor.
Visit your registration profile at g.co/cloudnext to opt out of sharing your contact information with the sponsor hosting this session.

This hands-on lab introduces Gemini 2.0 Flash, the powerful new multimodal AI model from Google DeepMind, available through the Gemini API in Vertex AI. You'll explore its significantly improved speed, performance, and quality while learning to leverage its capabilities for tasks like text and code generation, multimodal data processing, and function calling. The lab also covers advanced features such as asynchronous methods, system instructions, controlled generation, safety settings, grounding with Google Search, and token counting.

If you register for a Learning Center lab, please ensure that you sign up for a Google Cloud Skills Boost account for both your work domain and personal email address. You will need to authenticate your account as well (be sure to check your spam folder!). This will ensure you can arrive and access your labs quickly onsite. You can follow this link to sign up!

Learn how generative AI can enhance data workflows and analysis. This session demonstrates how to access and use Gen AI models in BigQuery, including new features like open source model support and structured output from Gemini. Accelerate your data analysis with the latest AI innovations available directly in BigQuery.

Empower your teams to innovate and drive digital transformation with AppSheet, and discover how business users can easily create AI-enabled solutions that address their needs without coding skills. Learn how Gemini in AppSheet can accelerate AI adoption and the digitization of labor by empowering users to rapidly create apps that bring their ideas to life and automate complex tasks. Then join a fireside chat with customers to hear how they’re using Gemini in AppSheet to drive innovation and reduce risk in a secure environment.

Discover the transformative power of Gemini in BigQuery, which is revolutionizing data analytics with AI-driven innovations. This session showcases capabilities designed to enhance workflows – streamlining data preparation and migrations, enabling advanced code generation, facilitating conversational data exploration, and optimizing workloads intelligently. Learn how these advancements simplify complex tasks, elevate productivity, and empower teams to unlock the full potential of their data.

Having difficulty translating desired outcomes into optimal cloud architecture for your apps? Join the session to learn about Application Design Center and its integration with Gemini Cloud Assist. We will showcase how it helps platform engineers and application architects translate ideas into deployable applications with unprecedented speed and simplicity. Explore with us its intuitive interface for designing, customizing, and deploying applications on Google Cloud with AI assistance, and leave with practical skills and tips for your next project.

Want to deploy generative AI across your organization but not sure how to keep your sensitive data secure and compliant? Join this session to hear from industry practitioners and Google experts about the best practices and lessons learned when embarking on this journey. We will demo how you can use built-in controls to identify sensitive data in your organization and restrict access to it and share insights, admin control recommendations, and lived customer experiences.

Incidents occur across time and topology. Customers using multiple GCP services spend hours troubleshooting. Learn about Gemini Cloud Assist Investigations, which provides the full range of troubleshooting and support, including structured workflows, signal analysis, and ability to recommend solutions across your applications, services and workloads, as well as its components such as compute, networking, storage, databases and data processing pipelines. With Gemini Cloud Assist Investigations, you can understand your environmental data patterns better, perform root cause analysis on your applications faster, and improve efficiency with warm handoffs between Gemini Cloud Assist and Google Support.

Discover the groundbreaking automated pipeline, seamlessly integrating rapid evaluation with the nuanced judgment of an LLM. This innovative solution delivers precise auto-alignment scores for LLMs, eliminating the need for repetitive prompt tuning. Effortlessly adapt to your LLM evaluation and migration requirements while minimizing hallucinations, ensuring repeatable and accurate results.

Hear from nonprofit Google Workspace customers Erika's Lighthouse and Climate Ride, as they share their experiences and best practices for successfully deploying and using Gemini across their teams. They'll discuss their evaluation criteria, rollout strategies, and key success metrics, offering valuable insights for other nonprofits considering AI adoption. Discover how these nonprofits are leveraging AI to drive productivity and efficiency to supercharge their social impact.

Learn how to speed up popular data science libraries such as pandas and scikit-learn by up to 50x in Google Colab using pre-installed NVIDIA RAPIDS Python libraries. Boost both speed and scale for your workflows by simply selecting a GPU runtime in Colab – no code changes required. In addition, Gemini helps Colab users incorporate GPUs and generate pandas code from simple natural language prompts.

This Session is hosted by a Google Cloud Next Sponsor.
Visit your registration profile at g.co/cloudnext to opt out of sharing your contact information with the sponsor hosting this session.

Explore how to design a customer service chatbot that prioritizes privacy and security using a multi-agent system and Gemini. We’ll cover the benefits of multi-agent architecture and share 10 best practices to safeguard user data and privacy. Experience a live demo that illustrates agent collaboration and external tool integration in action. Don’t miss this session to see how Gemini can help you deliver a secure, customer-friendly chatbot solution.

This session showcases an end-to-end generative AI application on Google Cloud. We’ll demonstrate how to use Gemini 2.0 Flash to analyze user-uploaded images, extract features, and generate descriptions stored in AlloyDB. Then we’ll show you how to fine-tune Gemini 2.0 Flash with BigQuery and generate outfit recommendations with AlloyDB low-latency querying. Finally, we’ll use the output from Gemini 2.0 Flash and Imagen 3 to create visuals of the outfits and deploy the entire solution on Cloud Run.