Jesse Hall

Ever wondered what it takes to power millions of voice conversations at ChatGPT's scale?When OpenAI needed infrastructure for ChatGPT's Advanced Voice Mode, they turned to LiveKit's open source Agents framework. Not a proprietary black box. Not a closed platform. Open source software that anyone can use, modify, and deploy.In this talk, I'll take you behind the scenes of building production voice AI infrastructure that handles millions of conversations:Why Open Source for Production AI – The technical and business reasons behind the choiceArchitecture Decisions – How we built for scale, reliability, and low latencyScaling to Millions of Calls – The challenges you don't anticipate until you hit themLessons Learned – What we'd do differently knowing what we know nowWhat's Possible Now – How you can use the same infrastructure for your projectsThis isn't a sales pitch, it's a technical deep dive with real production metrics, architectural diagrams, and honest discussions about trade-offs. You'll see the actual stack, understand the scaling challenges, and learn from our mistakes.Whether you're building your first voice agent or scaling to production, you'll walk away with insights from one of the largest voice AI deployments in the world. Because the infrastructure powering ChatGPT's voice mode is open source, and it's available to everyone.

Traditional chat interfaces only return text, but what if your AI assistant could render custom React components directly in the conversation? In this lightning talk, we’ll explore generative UI - where chat applications stream contextually appropriate React components instead of plain text responses. When users ask about sales data, they get interactive charts. When they search for properties, they get rich product cards. Through code examples, you’ll see how to build chat interfaces where AI intelligently selects and renders React components populated with real-time data from semantic search and vector databases. You’ll walk away with practical patterns for implementing this technique and understanding how modern data platforms enable these dynamic, visual conversational experiences that go far beyond simple text responses.

Explore the integration of OpenAI's GPT into React applications to create dynamic, intelligent user interfaces. This session offers practical insights into leveraging GPT's powerful NLP capabilities for chatbots, content generation, and personalized user experiences. Dive into the technical setup with Next.js 14, LangChain, Vercel's AI SDK, and MongoDB's Vector Search to optimize and customize your applications. Join us to transform your React projects with AI.

In this talk, attendees will learn how to integrate OpenAI's GPT-4 language model into their React applications, exploring practical use cases and implementation strategies to enhance user experience and create intelligent, interactive applications.

In this talk, attendees will learn how to integrate OpenAI's GPT-4 language model into their React applications, exploring practical use cases and implementation strategies to enhance user experience and create intelligent, interactive applications.