'AI is going to change women's performance research from the bottom up' - Kristen Faulkner inputs 4,400 hours of personal training history and gains 'actionable' output

There is nothing artificial about Faulkner's talents. Olympic champion on the track, Olympic champion on the road, Grand Tour stage winner, gold medals at Pan American and US National Championships, what else can Kristen Faulkner do on a bike?

With help from Artificial Intelligence, Faulkner is now confident that her computer science background from Harvard University will lead to more racing success.

"The research I needed about my own body did not exist. So I built it with AI," Faulkner led on a post to her LinkedIn account.

"For nine years, I collected biometric data that I struggled to synthesize. Heart rate. HRV. Sleep. Weight. Power. Temperature. Training load. Menstrual cycle phases. Bloodwork. DEXA scans.

"Every app gave me one piece of the story, but the answer was never in one app. It was in how it all interacted. So I built a system that pulls in the data sources I actually use as an athlete and runs them against 4,400 hours of my own training history. It does not just show me dashboards. It builds personal models of my physiology.

"Every model is trained on my body. Every finding is specific to my history. And every output is actionable, not just interesting."

She explained in the post that she dedicated the last two months to coding all her various data, sometimes head down at the computer for 10 hours at a time. She had lots of questions and decided to invest her time and talents to discover the answers. And it paid immediate benefits.

"I used this to help me prepare for the Pan Am Championships, where I won 3 gold medals this year. Today, I produced my best 20-minute power ever with training help from this app," she noted in the post on Tuesday.

The Alaska native won her first Grand Tour stages in 2022 at the Giro d'Italia Donne, wearing the leader's jersey after the prologue and then taking the mountain classification title after winning stage 8. On a Continental team in 2024, she had her big breakout season, winning a stage at Vuelta España, the first of two USPro road titles and then double golds at the Paris Games, one in Team Pursuit and one in the elite women's road race.

Her 2025 season ended with a crash at the Tour de France Femmes, which led to shoulder surgery and recovery time. But she wasted no time in proving her fitness was back at its best this year, earning three gold medals in four races at Pan American Championships in Chile, track victories in Team Pursuit and Individual Pursuit and then a week later with a time trial win on the road.

The passion for performance was fueled by a lack of analytics. And she noted that this is common in the sport for women.

"So little performance research is done on women, particularly regarding the needs of elite female athletes. So I took matters into my own hands, and I started writing the research myself. I did not want to keep waiting for someone else to study the questions that matter to my body," she noted.

"AI is going to change women’s performance research from the bottom up, and I want to be a part of it."

It's not just training numbers which Faulkner scrutinises. She has also been attentive and vocal about health issues, especially racing weight for expectations for energy output, watts per kilogram. She shared last year on a new Instagram account, @f.e.e.d_powr (Fuelling for Endurance, Energy, and Durability), set up by her teammate Cédrine Kerbaol, that she won a pair of gold medals at the Paris Olympic Games "by not changing her body, but by working with it". Now she's digging deeper for optimal performance.

Now, a new process could lead to her first stage at the Tour de France Femmes. But ultimately, she said she was training not to defend her Olympic gold in two years' time.

"I worked in venture capital. I actively invest in AI companies. I race on the Women’s WorldTour. I am training to defend Olympic gold on home soil in LA 2028. I’ve applied all of that knowledge to building this.

"I came into cycling late. I did not win because I had the deepest race history or the most experience. I won because I used my brain as much as I could. Before my first European race, I made flashcards of the riders, I studied every corner of every course, and I analyzed my data rigorously. I am doing the same thing now, with AI."