NVIDIA VIA is a framework to build AI agents capable of processing large amounts of live or archived videos and images with Vision-Language Models (VLM) - whether deployed at the edge or cloud. This new generation of visual AI agents will help nearly every industry summarize, search, and extract actionable insights from video using natural language. This demo shows how VIA can be used to build an AI agent to quickly summarize sport videos and get your favorite highlight videos of the game.