An app for experiencing race day before it arrives. It cross-references the course GPX, the weather and the runner's goals and training history, then works out which points to watch, how to pace and where to drink. The advice comes back as a generated video with captions, helping runners picture the course and judge well.
Judges found it a fresh idea to show course and weather as footage rather than figures. With little chance to run the route in advance, a visual simulation was seen as easier to picture, and they hoped it could adapt to each runner's ability.
Generated video is eye-catching, which makes the real question whether the team can say why video was needed. Starting from a race nobody can walk in advance, they merge the course GPX, the forecast and the runner's own training history and render the result as footage, so the video becomes a way of understanding the course rather than demo decoration. The advice, which hill to watch, what pace to hold, where to drink, also stays within what a runner can recall on the day.
See all winners of 第3回 AI Agent Hackathon with Google Cloud →
Summaries are written by this site. Project pages include demo videos, screenshots and the team's own write-up (videos may autoplay).