Don’t let Python developers have all of the fun with LLMs.

This talk is a gentle introduction to Generative AI and Large Language Models for front-end developers looking to build intelligent chatbots and applications. We’ll dive into Langchain.js, an open-source orchestration framework for building AI Applications.

We will start by exploring the basics of Generative AI (GenAI) and Large Language Models (LLMs), how they work, and cover some common pitfalls and how they can be avoided. We’ll take a closer look at vectors, retrievers, and how to build an agent capable of choosing tools to perform specific tasks.

About Adam: Adam Cowley is a dedicated developer with a keen interest in data and graph databases. Serving as the Senior Developer Advocate at Neo4j, Adam produces educational content for GraphAcademy, Neo4j’s free, self-paced, online learning platform. His technical experience spans two decades, developing websites, mobile apps and mixed reality experiences for budding startups to the world’s biggest companies

Recently, Superhuman (formerly Grammarly) launched Superhuman Go, an AI assistant that works alongside you on every platform. To build it, we needed a scalable solution that supports an unlimited number of agents that dynamically shapes the user interface and looks similar across all supported desktop and mobile platforms. Join me to find out how we discovered solutions for this innovative new product.

Retrieval-augmented generation (RAG) is powering a new breed of AI interfaces — but with great flexibility comes messy state. In this talk, we’ll dive into the real-world challenge of managing UI state in apps powered by generative backends. You’ll learn practical patterns to track sources, follow user intent, and tame AI responses, all without reinventing your frontend architecture.

Letting AI generate your UI is fast and fun right up until you need it to implement something specific. Throw in strict design systems, your company's existing component library and responsive breakpoints, and the whole process usually falls apart. The good news is that there is a solution. We'll explore what works and what doesn't with agentic coding.