LEARN FROM THE BEST
TRAINERS WORLDWIDE

LLMs are not just fancy search engines: they lay the ground for building autonomous and intelligent pieces of software, aka agents.
Companies are investing massively in generative AI infrastructures. To get their money's worth, they need developers that can make the best out of an LLM, and that could be you.
Discover the TypeScript stack for LLM-based development in this 3 hours workshop. Connect to your favorite model with the Vercel AI SDK and turn lines of code into AI agents with Mastra.ai.

Craft immersive XR educational experiences through declarative 3D rendering with this advanced workshop. Leverage React Three Fiber's component-based architecture to build a gamified solar system explorer featuring dynamic orbital mechanics, interactive raycasting, and WebGL optimizations. Master performance-critical techniques including InstancedMesh implementation, reactive state management, and WebXR integration while creating engaging STEM visualizations. This workshop bridges theoretical physics concepts with practical front-end development, demonstrating how Three.js can transform educational content through spatial computing paradigms.

Agenda:

1. Introduction to React Three Fiber and Three.js: Setting up the project environment
2. Building the Solar System Scene: Creating planets, orbits, and space backgrounds with animations
3. Interactivity and Gamification: Raycasting for object selection and interaction
4. Performance Optimization: Using InstancedMesh for efficient rendering
5. WebXR Integration: Enabling AR/VR experiences in the browser

In this workshop, we will incrementally augment an existing React application with AI. I'm sure most of you probably already maintain a React app, so rather than starting from the ground-up, let's take something that already works, and develop some patterns for adding practical, real-world AI features without making them feel "bolted on" just for the sake of chasing the hype. We'll explore questions such as "which model should I use?", "should the LLM run on-device or on the cloud?", "am I risking vendor lock-in by picking a proprietary model over an open-source one?", and we'll dive into the deeper topics of using AI frameworks, creating agents, and the clients and servers of the Model Context Protocol (MCP). By the end of this workshop, you should have some applicable knowledge and skills which you can bring to your own applications, and hopefully, you'll walk away with a greater understanding of how and when to actually use AI 

Much like the promise of cake in Portal, login forms are everywhere in web development. While they may seem functional at first glance, many users with disabilities encounter a maze of invisible walls, from keyboard traps to inaccessible CAPTCHAs. It's as if GLaDOS designed these forms herself to test us!

In this practical walkthrough, we will debug the accessibility issues of a real React login component live, similar to traversing those test chambers: Using an actual screen reader, we'll show how minor improvements, such as proper ARIA implementation and effective focus management, can transform a complex test chamber into a smooth user experience. Additionally, we will address the common pitfalls that GLaDOS might throw at us in both the Portal universe and the real world of accessibility, especially concerning authentication processes and its special needs. So grab your portal gun—let's work together to break down these barriers and ensure that authentication truly works for everyone. The cake might be a lie, but accessibility doesn't have to be!

This hands-on workshop teaches developers how to build privacy-first, on-device AI applications using React Native and Apple’s Foundation Models. Participants will implement real-world LLM features like text generation, streaming responses, and structured outputs with type-safe schemas.

Goals:

• Understand on-device LLM fundamentals and trade-offs
• Set up React Native with Apple’s new Foundation Models
• Build a sample app using text generation and streaming responses
• Integrate structured outputs and experiment with schema validation (Zod)
• Explore advanced topics like adapters, privacy, and Vercel AI integration

Server-side rendering (SSR) is back in the spotlight – and React is evolving fast. In this workshop, we’ll go deep into the mechanics, performance trade-offs, and modern techniques of SSR with React.js. You'll start by building an SSR app from scratch – no frameworks, just raw renderToString and hydrateRoot—to truly understand how React renders on the server and hydrates on the client. From there, we'll upgrade to React 18’s streaming capabilities using renderToPipeableStream, implement selective hydration using Suspense, and integrate data fetching directly into the server render cycle. We’ll look at React Server Components (RSC), showing how they complement SSR. We'll also cover hydration strategies, how to prevent mismatches, and how to cache or stream HTML effectively for real-world performance. Finally, we’ll bridge our manual SSR work into production frameworks like Next.js.