How the USA Team of Olympic Skiers and Snowboarders Got the Edge on Google AI

Team USA skiers and snowboarders took home new hardware, including several gold medals, from the 2026 Olympics. Along with years of hard work to become an Olympic athlete, this year’s team had an added edge in training thanks to a custom AI tool from Google Cloud.

US Ski and Snowboard, the governing body for US national teams, oversees the training of top skiers and snowboarders in preparation for major events, such as national championships and the Olympics. The organization partnered with Google Cloud to build an AI tool to provide more insight into how athletes train and perform on the slopes.

Video review is a big part of winter sports training. The coach will stand on the sidelines and record the athlete’s run, then review the video with him afterward to spot mistakes. But the process is antiquated, Anouk Patty, chief sports officer at US Ski and Snowboard, told me. That’s where Google stepped in, bringing new AI-powered data insights to the training process.

Google cloud engineers hit the slopes with skiers and snowboarders to understand how to build a useful AI model for athletic training. They used the video recording as the basis for an as-yet-uninvented AI tool. Gemini performed a frame-by-frame analysis of the video, which was then fed into spatial intelligence models from Google DeepMind. Those models were able to take a 2D rendering of the athlete in the video and turn it into a 3D skeleton of the athlete as they twist and turn on the run.

The final touch from Gemini is helping the AI ​​tool analyze the physics at the pixels, according to Ravi Rajamani, global head of Google’s AI Blackbelt group. who worked on the project. Coaches and athletes told engineers specific metrics they wanted to track — speed, rotation, trajectory — and Google engineers coded the model to make it easier to monitor and compare between different videos. There is also a forum to ask Gemini questions about performance.

“From just video, we can actually recreate it in 3D, so you don’t need expensive equipment, [like] nerves, which interfere with the athlete playing,” said Rajamani.

Trainers are undoubtedly experts on the mountain, but AI can act as a kind of gut check. The data can help confirm or deny what coaches are seeing and give them more insight into the specifics of each athlete’s performance. It can capture things that would be difficult for humans to see with the naked eye or with low video quality, such as where the athlete was looking while performing a trick and the exact speed and angle of rotation.

“It’s data they wouldn’t have,” Patty said. The 3D skeleton is especially useful because it makes it easier to see movement obscured by puffy jackets and athletic pants, he said.

For elite skiers and snowboarders, making small adjustments can mean the difference between a gold medal and no medal at all. Technological advances in training are intended to help athletes get all the tools available to improve.

“You always try to find that 1% that can make the difference for an athlete to get on the podium or win,” said Patty. It can also teach about democracy. “It is a way for every coach who is in the club that works with young athletes to have that level of understanding of what an athlete should do for the athletes of the national team.”

For Google, this purpose-built AI tool is “the tip of the iceberg,” Rajamani said. There are many possible future use cases, including extending the base model to be customized for other games. It also lays the foundation for a career in sports medicine, physical therapy, robotics and ergonomics — disciplines where understanding body posture is important. But for now, there’s satisfaction in knowing that AI is designed to help real athletes.

“This was not a case of technical engineers building something in a lab and shipping it,” Rajamani said. “This is a real-world problem we’re solving. For us, the motivation was to create a tool that provides a real competitive advantage to our athletes.”