Generative AI is transforming how applications are built, with developers leading the way. Securing these new AI-powered experiences requires careful attention to identity. This keynote explores the core identity requirements for GenAI applications, and introduces Auth for GenAI, a solution designed to simplify the development of secure and scalable AI-powered experiences, bridging the gap between innovation and security.

Children today are going online earlier than ever, building their identity and community in digital worlds often head of the real world. This session will unearth the complexities involved in building the environment to support youth identity and digital wellness, from data privacy and consent, to social features, to parent engagement.

Human in the loop is a critical part of building AI applications. However, the current solutions to the problem lack the ability to validate the identity of a human and allow agents to securely communicate. In this talk Abhishek will talk about how to build a Financial Grade human in the loop system which can accommodate authentication, authorization and rich consent. In the end you’ll be able to build apps, the can request approval from users for any scenario, in a way that’s user friendly, and conforms to the strongest requirements of assurance levels, ensuring that your apps are secure.

MCP has quickly become the standard for connecting AI agents to real-world tools and services. But until recently, MCP was limited to local development. This talk covers the shift from local to remote MCP servers, including the technical challenges of deploying them at scale and recent transport layer improvements that address these challenges.I'll share best practices for building reliable MCP servers based on learnings from working with customers and internal teams, and explore the benefits of building a stateful MCP server. Finally, the session will include a live demo showing how to deploy a remote MCP server to production.

Retrieval-Augmented Generation (RAG) enables powerful AI-driven insights but without the right guardrails, it can expose sensitive data to the wrong users. In this talk, we’ll explore how to implement fine-grained access control in RAG architectures to ensure AI agents only retrieve documents the user is authorized to see. You’ll learn how to prevent data leakage, enforce Zero Trust principles, and integrate fine-grained access control into your RAG pipelines. Whether you're building internal copilots or customer-facing AI assistants, this session will help you make “who can see what” a first-class citizen in your AI stack.

Generative AI unlocks incredible potential, but how do you securely manage users and control the actions your AI takes, especially when calling external tools or APIs? If you're a developer building GenAI applications and concerned about protecting user data and controlling AI actions, this 90-minute workshop is for you. We’ll have a hands-on session implementing authentication and tool calling capabilities in a Next.js application. Come ready to code.

Generative AI is no longer just a curiosity. It’s transforming how developers code, collaborate, and create. This panel brings together leading voices from LlamaIndex, LangChain, and Vercel to explore how GenAI is fundamentally reshaping the developer experience. From copilots and auto-documentation to intent-driven coding and infrastructure automation, we’ll dive into the tools, trends, and tensions defining this new era. We’ll examine what’s working (and what’s not), how teams are measuring impact beyond productivity and what it takes to design AI-first APIs and workflows developers actually love. Whether you're still experimenting or already shipping AI-powered features, this session will offer practical insights, future-looking perspectives and a dose of healthy debate about what’s next. Panelists: - Laurie Voss | VP of Developer Relations, LlamaIndex - Nuno Campos | Founding Engineer, LangChain - Gaspar Garcia | Head of AI Research and API, Vercel Join us as we unpack the promise and pitfalls of a world where developers don’t just write code, they co-create it with AI.