The emergence of LLMs for coding has shaken up the development life cycle for devs. This is a chance for developers to share their experience with the new normal and  come up with some better practices for breaking through process bottlenecks. There will be a short slide or two and then we'll open it up for a roundtable discussion.

Come learn what coding is. Learn how to create your own software with the help of an AI coding assistant! Coding assistants let you build whole projects while you learn what's going on. Along the way we'll teach you * what software is * what programming languages are * what an AI coding assistant does * how to create and test an app Bring your own app idea or let us suggest one (Wordle clone? Home inventory tool? Trippy music visualizer?)

Ever want to be able to send secret messages to friends? In this class, we're going to do just that! We'll learn about how to create secret codes, how to read them, and maybe even how to crack them. The fancy word for this in computer science is "cryptography", but we'll be starting from scratch in this class, and only a basic familiarity with coding is recommended. We'll also be doing plenty of hands-on, off-keyboard exploration, teaching how to crack puzzles and make you an escape room whiz!

This hands-on workshop introduces the core ideas behind Large Language Models and AI agents, then quickly moves from theory into working code. We'll explore how agentic systems work in practice, including prompt engineering, observability, token management, tool calling, typed inputs and outputs, external state, reasoning loops, termination, structured responses, and tracing. Along the way, we'll look at practical patterns for embedding AI agents into real product workflows and applications. The workshop is designed to be roughly 80% hands-on and 20% theory, with two parallel implementation tracks: Python + PydanticAI TypeScript + Vercel AI SDK Students can choose the stack they're most comfortable with while learning the same underlying agentic concepts and architecture. By the end of the workshop, students should have a clearer understanding of where LLMs and agents can meaningfully improve product workflows, how to implement those capabilities using sound software engineering practices, and a strong foundation for exploring more advanced topics such as RAG, memory, multi-agent systems, MCP, evaluation, and production-grade agent architectures.

This hands-on workshop introduces the core concepts behind Retrieval-Augmented Generation (RAG) and shows how they come together in a working application. We'll start by breaking down the RAG pipeline step by step: embeddings, semantic search, chunking, vector databases, retrieval, ranking, context construction, and generation. Through working code, we'll explore how each stage affects the quality and reliability of the final response, along with common failure modes and practical considerations when building RAG systems. We'll then add a conversational interface on top of the retrieval pipeline to show how RAG can be used inside real product experiences rather than as a standalone search demo. The workshop is approximately 80% hands-on and 20% theory, with two parallel implementation tracks: Python: Sentence Transformers + ChromaDB + PydanticAI TypeScript: Sentence Transformers + ChromaDB + Vercel AI SDK By the end of the workshop, students will understand the major components of a RAG system, the tradeoffs involved in designing one, and the engineering practices needed to build more reliable AI-powered search and conversational product features.

Passion projects have always moved me forward. In this talk, I’ll share some stories of burnout, getting stuck, and how a few random projects for friends challenged my assumptions about what software should and could be. While accidentally fueling a new era of curiosity, self-discovery, and finally making the things I want to make, in the way I want to make them. This isn’t a talk about launching a product or finding a market. It’s about what happens when you have an audience of one: yourself. Along the way, you might make your day a little better, learn some new tools, and rediscover some of the curiosity and joy that got you interested in making software in the first place. If I’ve done my job, the next time we talk, you’ll be telling me about the thing you made that changed things for you.