Event Schedule

Join the comprehensive exploration of Google Cloud's revolutionary GenAI technology, with a special focus on Gemini. This session will take you through the capabilities of Gemini for Google Cloud, Gemini for Workspace, Vertex AI, Foundation Models on Vertex AI, Model Garden, Vertex AI Agent Builder, and Vertex AI Search & Conversion. I'll showcase live demos highlighting Gemini-powered multimodal experiences on Vertex AI, explore industry use cases, and delve into the world of Gemini code assist. ==> Key takeaways: --> Gemini for Google Cloud: Understand how Gemini is transforming the landscape of AI on Google Cloud --> Gemini for Workspace: Discover how Gemini is enhancing productivity and collaboration within Google Workspace --> Vertex AI: Learn how Vertex AI provides a unified platform for building and deploying machine learning models --> Foundation Models: Explore the foundation models available on Vertex AI and their potential for diverse applications --> Model Garden: Navigate the Model Garden to access a wide array of pre-trained models for various tasks --> Agent Builder: Learn how to create intelligent agents using Vertex AI Agent Builder --> Search & Conversion: Harness the power of Vertex AI Search & Conversion for efficient information retrieval and transformation Gemini-powered Multimodal Experiences: Witness the innovative ways Gemini is enabling multimodal interactions --> Industry Use Cases: Gain insights into how GenAI is being applied across different industries to solve real-world challenges --> Gemini Code Assist: Explore how Gemini is revolutionizing the coding experience ==> Who should attend: --> Developers and data scientists eager to leverage the latest in generative AI --> Business leaders seeking to understand the transformative potential of GenAI --> Technology enthusiasts curious about Google Cloud's cutting-edge AI offerings Don't miss this opportunity to unlock the power of generative AI with Google Cloud GenAI!

Learn how W&B Weave is driving deeper understanding of AI apps! In this exciting era of AI agents, Weave provides fantastic tracing, experimentation, and essential guardrails, giving you confidence in your AI applications. Get ready to supercharge your workflow with powerful evaluation tools, incredible debugging capabilities, and comprehensive support for building and managing sophisticated AI agents. Let's build amazing AI, together!

Every tier-2 city has someone who could cure cancer, colonize Mars, or build the next Google. They just need someone who believes in them. Flow Community® champions these "Dark Talent"—brilliant minds invisible to traditional systems. We transform overlooked talent into global leaders. We build bridges so others don't have to swim across alone. Ten years back Flow Community® started with three words: "Why not us?" Today, we're 15,000+ developers across 100+ countries, with 1,000+ now placed at NASA FDL, CERN Openlab, Mozilla Outreachy, Microsoft, and leading global startups. A Facebook group that became a global community success platform.

In this live session, you'll explore the powerful synergy between Gemini and GitHub Copilot within the Visual Studio Code environment. Designed for developers and tech enthusiasts, the session offers a hands-on demonstration of how AI is transforming coding workflows through intelligent assistance. You'll learn how to leverage Copilot Chat’s three core capabilities—Ask, Edit, and Agent—to boost productivity, write cleaner code, and solve complex problems in real time. Whether you're seeking to understand AI-assisted development or looking to integrate these tools into your daily workflow, this session offers practical insights, live examples, and interactive Q\&A to help you get the most out of Gemini-powered GitHub Copilot.

A session by Global Firebase Team

Every article says the same thing: ✨ "AI is just a tool." ✨ "Use it to co-create the future." ✨ "The questions you ask matter more than the answers." Yes, all that is true. But here's what we often forget: AI is not just about consuming, it’s also about building, It’s about shaping the intent, designing the interactions,and bringing humanity into the loop. This talk will touch upon How can design play a role in building AI interactions. Here is the medium article "Layers of AI" which talk about how design can contribute in each stage of AI development process. https://medium.com/design-bootcamp/layers-of-ai-fe2aac494b57

This session will walk you through how to build reasoning-first AI agents by combining Google’s Gemini models with knowledge stored in GCP. We’ll cover how to store structured and unstructured data in GCP Storage, index it in a vector database, and use it in real-time to power intelligent workflows. You'll learn how to integrate external tools, add memory, and enable multi-step reasoning using Gemini—all through Agno’s open-source framework. Whether you’re a developer exploring agentic design or looking to build practical AI systems, this session will give you the foundation and hands-on experience to get started.

In this session, we’ll dive into the fundamentals of Grafana, focusing on how to efficiently monitor your systems, set up alerts for proactive management, and explore the integration of AI and machine learning capabilities for advanced insights. Whether you’re new to Grafana or looking to sharpen your skills, this beginner-friendly guide will walk you through the essential steps of visualizing your data, setting up alerts, and enhancing your monitoring strategy with smart, data-driven predictions.

In this session, you'll learn how to build intelligent, event-driven workflows using Google Cloud Functions and the Natural Language API. We’ll explore a fully serverless architecture that automates sentiment analysis from customer feedback, processing data in real time, scaling effortlessly, and eliminating manual effort. By combining the power of serverless computing with AI-driven NLP, this approach delivers cost-effective, actionable insights with zero infrastructure management enabling smarter decisions and enhanced customer experiences at scale.

As the open-source AI movement accelerates, Google’s Gemma models stand out for their balance of performance, transparency, and accessibility. In this session, we’ll explore about the Open Models, how Gemma is architected, what sets it apart from other open models, and why it matters in the broader push for responsible AI innovation. We’ll take a technical deep dive into Gemma’s architecture, including key design choices in its Transformer stack, training process, and optimization techniques like knowledge distillation. This analysis will highlight how Gemma achieves efficiency while maintaining high-quality language understanding, making it well-suited for research and lightweight real-world applications. The session also explores multimodal applications powered by open models, illustrating how Gemma can be extended or integrated to handle tasks that span text, vision, and structured inputs. We will showcase practical examples and use cases that demonstrate the model’s versatility.

In the fast-paced world of research and content creation, generative AI has become an indispensable tool. However, it comes with a significant and frustrating flaw: GenAI models frequently hallucinate, fabricating non-existent sources or misattributing information. This makes them highly unreliable for tasks that demand factual accuracy and proper citation, like writing grants, academic articles, or crucial research papers. This session directly confronts this pervasive pain point. We'll demonstrate how to build a specialized, AI-powered research assistant that moves beyond generic AI's limitations to deliver genuinely trustworthy and verifiable citations. This is crucial for establishing credibility and ensuring the integrity of your work.

Discover how Firebase Studio empowers developers to swiftly prototype, build, and deploy full-stack AI applications directly from the browser. This session will guide you through leveraging Firebase Studio's App Prototyping agent to transform natural language prompts, images, or sketches into functional Next.js applications. With integrated AI assistance from Gemini, you'll learn how to iterate on your app using conversational prompts, refine code within a familiar IDE environment, and deploy seamlessly using Firebase App Hosting. Whether you're a seasoned developer or exploring AI-driven development for the first time, this talk will showcase how Firebase Studio streamlines the app development lifecycle—from concept to deployment.

In this talk, we'll dive into how to bring policy-as-code to your Terraform workflows using Open Policy Agent (OPA). As infrastructure scales, enforcing security, compliance, and best practices becomes critical. With OPA, you can define granular rules to ensure your Terraform configurations are secure before deployment—even in CI/CD pipelines. We'll cover: Why policy enforcement matters in Terraform Introduction to OPA and Rego (its policy language) Writing custom policies for real-world Terraform use cases Integrating OPA into GitHub Actions for shift-left security Live demo: Preventing insecure infrastructure with OPA policies

In fast-paced performance marketing, data is abundant, but insights are often delayed or fragmented. At Headout, we manage campaigns across various geographies, platforms (including Google Ads, Criteo, and Travel Ads), and formats (such as Search, PMax, Brand, and Remarketing). To stay ahead, we needed to unify this complexity into a single source of truth and drive decisions daily. In this lightning talk, I’ll share how we built a scalable marketing analytics pipeline using BigQuery and Looker, designed for agility, clarity, and impact.

Designing and deploying distributed AI applications is an exciting endeavor, often accompanied by unexpected challenges and lessons that shape how we design complex distributed systems. In this session, I will share hard-earned insights gained from building a distributed AI application, focusing on key failure points and how to address them effectively. From security vulnerabilities to AI hallucinations, real-time failures, and the critical need for keeping humans in the loop, this presentation explores the pitfalls and solutions that every AI developer and system architect should understand. Security in distributed AI systems is a constant concern, with sensitive data and communication channels vulnerable to breaches and adversarial attacks. I will discuss real-world examples of how security failures can occur and share strategies for building robust, secure systems. Additionally, I'll delve into the phenomenon of AI hallucinations-when models generate plausible but incorrect outputs-and explain how these errors propagate in a distributed environment, creating downstream issues. Real-time failures are another key challenge, where latency, synchronization issues, and system reliability can significantly impact performance. Drawing from my experience, I'll highlight best practices for optimizing real-time AI systems to maintain efficiency and consistency. Finally, I'll emphasize the importance of keeping humans in the loop in decision-making processes. While AI systems are powerful, they are not infallible, and removing human oversight can lead to ethical, operational, and trust-related failures. I'll provide actionable tips for designing workflows that combine the strengths of human judgment with AI capabilities. By the end of this session, attendees will walk away with a clearer understanding of the challenges involved in distributed AI systems and practical strategies to mitigate them, ensuring more secure, reliable, and human-centered AI applications.

Learn how the Model Context Protocol (MCP) helps you add AI features to your app in a simple and clean way. I’ll walk through building AI tools using fastmcp. It would be an intermediatry session with a bit of python knowledge

Participants will explore how to preprocess customer data, identify key behavioral patterns, and implement K-means clustering for precise customer group identification. The Hands-On Workshop will guide participants through setting up a BigQuery Studio environment, integrating it with Vertex AI, and utilizing Gemini to gain deeper insights into customer demographics, purchasing trends, and lifetime value. By the end of this session, participants will understand how to transform raw customer data into actionable insights, enabling businesses to craft highly targeted marketing campaigns, reduce churn, and improve customer retention. Whether you’re a data scientist, marketer, or business analyst, this session will help you with the skills to harness the full potential of AI-driven customer segmentation on Google Cloud.

In today's cloud-native landscape, Kubernetes has become the backbone of modern application deployments—but with great power comes great responsibility. As more organizations migrate to Google Kubernetes Engine (GKE), ensuring a strong security posture becomes non-negotiable. From misconfigured workloads to supply chain vulnerabilities, container environments are an attractive target for attackers. This talk dives into why Kubernetes security is crucial and how Google Cloud's ecosystem provides robust tools to help secure your containerised workloads end-to-end. We'll walk through actionable best practices, demo powerful GKE-native security features, and provide a blueprint for building secure-by-default Kubernetes environments. Whether you're a developer, platform engineer, or cloud architect, you'll leave with practical strategies to level up your container security game on GKE.

In this session, I will walk through real-world DevOps and data engineering use cases implemented on Google Cloud using Kubernetes (GKE), BigQuery, and various native tools. We’ll start by demonstrating how DBT workflows can be automated on GCP using GKE and BigQuery, enabling scalable and auditable transformations for data teams. Next, we’ll shift to DevOps automation by showcasing a case study where we implemented automatic GCP health checks and alerting mechanisms for service resilience. Finally, the session will cover security and networking in Kubernetes environments. This includes a walkthrough of how to implement Kubernetes Network Policies to enforce pod-level security and traffic controls. Whether you’re a DevOps engineer, data engineer, or cloud architect, this session will provide actionable insights into building secure, automated, and production-ready workflows on GCP.