Between Uber’s partnership with NVIDIA and speculation around the U.S.'s President Donald Trump enacting policies that allow fully autonomous vehicles, it’s more important than ever to ensure the accuracy of machine learning models. Yet, the public’s confidence in AVs is shaky due to scary accidents caused by gaps in the tech that Sama is looking to fill. As one of the industry’s top leaders, Duncan Curtis, SVP of Product and Technology at Sama, would be delighted to share how we can improve the accuracy, speed, and cost-efficiency of ML algorithms for ​A​Vs. Sama’s machine learning technologies minimize the risk of model failure and lower the total cost of ownership for car manufacturers including Ford, BMW, and GM, as well as four of the five top OEMs and their Tier 1 suppliers. This is especially timely as Tesla is under investigation for crashes due to its Smart Summon feature and Waymo recently had a passenger trapped in one of its driverless taxis.

Breaking the Demo Barrier and Getting Agents Shipped Deploying Large Language Models (LLMs) in production brings a host of challenges well beyond prompt engineering. Once they're live, even the smallest oversight—like a malformed API call or unexpected user input—can cause failures you never saw coming. In this talk, Vaibhav Gupta will share proven strategies and practical tooling to keep LLMs robust in real-world environments. You'll learn about structured prompting, dynamic routing with fallback handlers, and data-driven guardrails—all aimed at catching errors before they break your application. You'll also hear why the naïve use of JSON can reduce a model's accuracy, and discover when it's wise to push back on standard serialization in favor of more flexible output formats. Whether you're processing 100+ page bank statements, analyzing user queries, or summarizing critical healthcare data, you'll not only understand how to prevent LLMs from failing but also how to design AI-driven solutions that scale gracefully alongside evolving user needs. Modal: ML Infra That Does Not Suck Building an application on the cloud doesn't have to suck. Even if it uses GPUs and foundation models! In this talk, I'll present Modal, the serverless Python infrastructure you didn't know you always wanted.

Traditional product development cycles require extensive consumer research and market testing, resulting in lengthy development timelines and significant resource investment. We've transformed this process by building a distributed multi-agent system that enables parallel quantitative evaluation of hundreds of product concepts. Our system combines three key components: an Agentic innovation lab generating high-quality product concepts, synthetic consumer panels using fine-tuned foundational models validated against historical data, and an evaluation framework that correlates with real-world testing outcomes. We can talk about how this architecture enables rapid concept discovery and digital experimentation, delivering insights into product success probability before development begins. Through case studies and technical deep-dives, you'll learn how we built an AI powered innovation lab that compresses months of product development and testing into minutes - without sacrificing the accuracy of insights.