The U.S. Open is using artificial intelligence (AI) to enhance the experience of both players and fans. AI technology is being used to analyze matches in real time, offering insights into key moments, players' chances of winning, and a new metric called "serve quality." This metric evaluates the efficiency, accuracy, and consistency of a player's serve, based on data collected from cameras around Arthur Ashe Stadium. These cameras track the ball, racket, and players' limbs, gathering information such as the angle of the elbow and knee, as well as the speed of the wrist during a serve. IBM's Watsonx platform processes this data, generating a score out of 100 that can be viewed in the U.S. Open app after a match. For example, Coco Gauff's winning serves were described as having "controlled racket preparation and deep knee bend during her setup," according to the serve quality summary. By the end of the tournament, over a billion data points are expected to be generated, according to Tyler Sidell, IBM's technical program director for sports and entertainment partnerships. Fans can access these AI insights through the U.S. Open app, which has around 14 million users, according to IBM. Players are also using the technology to improve their performance. For instance, Jessica Pegula uses AI to analyze patterns in her opponents' serves before matches. Pegula noted that while data can be helpful, it's not always reliable during a match, and players must rely on their instincts. The "likelihood to win" feature has been part of the U.S. Open digital experience for about six years, but this is the second year fans can track these odds in real time as a match progresses. This feature is based on data from trusted media sources and recent performances, which are combined to predict a player's chances of winning. For example, Gauff was predicted to win her match by 72%, a number that increased as she gained momentum in the first set. Another AI-powered feature, called "key moments," provides brief analysis blurbs as a game unfolds. For instance, during the second set of Gauff's match, it noted, "Gauff has three opportunities to win the match, with Sonmez needing a heroic response." A dramatic shift in the "likelihood to win" prediction occurred during a match between Alexander Zverev and Lorenzo Sonego, where Zverev had an 87% chance of winning at the start, but Sonego's chances rose to 93% toward the end of the fourth set. Zverev eventually made a comeback. Additionally, the app includes "Match Chat," an AI assistant that can answer questions about players, matches, and the venue. When asked where to find the signature cocktail "Honey Deuce," it provided locations of the bars and even asked, "Do you want the nearest Honey Deuce bar to your gate?" These AI features are part of a broader effort to make the U.S. Open more interactive and informative for fans while also providing players with tools to analyze their performance. As the tournament continues, the integration of AI is expected to offer new ways to engage with the sport and understand the nuances of each match.