AI for Business

Gold Medal Tech: How a Custom Google AI Tool Sharpened Team USA's Skiers and Snowboarders

The 2026 Winter Olympics have concluded, and Team USA's skiers and snowboarders are returning with a celebrated haul of medals. Behind the podium finishes, alongside immense athletic dedication,...

Share:

The 2026 Winter Olympics have concluded, and Team USA's skiers and snowboarders are returning with a celebrated haul of medals. Behind the podium finishes, alongside immense athletic dedication, was a novel technological partner: a bespoke artificial intelligence tool developed by Google Cloud.

US Ski and Snowboard, the national governing body, sought to modernize a training staple: video review. Coaches traditionally record runs and analyze footage, a method chief of sport Anouk Patty described as limited. Partnering with Google, they built a system to extract unprecedented detail from simple training videos.

Google engineers spent time on the mountain to grasp the athletes' needs. Their solution uses Google's Gemini models to perform a frame-by-frame analysis of video. This data feeds into spatial intelligence models that reconstruct a two-dimensional video into a dynamic, three-dimensional skeleton model of the athlete in motion.

"From just a video, we are actually able to recreate it in 3D," said Ravi Rajamani, global head of Google's AI Blackbelt team. "You don't need expensive equipment, [like] sensors, that get in the way."

Coaches specified key metrics—speed, rotation angle, trajectory—which the model tracks and compares across sessions. A chat interface allows for natural language queries about performance. The 3D model proves particularly valuable, cutting through bulky winter gear to reveal precise body mechanics invisible to the naked eye.

For elite athletes, minuscule adjustments separate gold from fourth place. This AI acts as a data-driven second opinion, confirming a coach's instinct or revealing hidden flaws. Patty emphasized its broader potential: "It's a way for every coach who's out there in a club working with young athletes to have that level of understanding."

While future applications in sports medicine and robotics are evident, the project's immediate success was its grounded approach. "This was not a case of tech engineers building something in the lab and handing it over," Rajamani noted. "This is a real-world problem that we are solving." For the athletes on the podium, that solution translated into a tangible, and golden, edge.

Source: CNET

Ready to Modernize Your Business?

Get your AI automation roadmap in minutes, not months.

Analyze Your Workflows →