Looking to impress, young soccer players sprinted and dribbled around purple cones on the patchy grass. Their speed, control, and footwork were all carefully evaluated, but not by veteran scouts.
Nor is it caused by humans.
Instead, Brazilian players were evaluated by a mobile app powered by artificial intelligence (AI). It’s part of a handful of new tools that promise to revolutionize the way talent is discovered in the soccer-mad nation.
“We’re talking about millions of undiscovered boys and girls,” said Roger Wittmann, the German sports agent who created Cuju, one of Brazil’s most popular scouting apps. “This is a huge opportunity for them to get noticed.”
Platforms like Cuju quickly attracted hundreds of thousands of users in a country where playing professional soccer is a common dream for many. The tool has also attracted the attention of major soccer clubs, some of whom are now using the app to recruit players.
Brazil, where soccer is so intertwined with everyday life, exports more star players than any other country in the world, some earning millions of dollars with Europe’s top clubs.
AI scouting platforms are already common in Europe, and the evaluation of soccer talent has long been rooted in metrics and statistics. However, in Brazil, severe economic and regional disparities have historically made it difficult to standardize scouting operations.
Instead, it is left to the country’s renowned scouts to discover Brazil’s soccer talent. These veteran talent hunters, known in Portuguese as “olheiros,” have spent decades scouring amateur matches, neighborhood leagues, and school tournaments from the Amazon rainforest to the dusty depths of Brazil, looking for the next big star.
But now, powerful AI technology can identify up-and-coming talent faster and more accurately than the human eye alone. It also has the potential to reach more ambitious athletes across Brazil’s vast territory, giving players in remote parts of the country a chance to get noticed, where there may be few scouts.
Most AI scouting platforms work by analyzing user-uploaded videos and drills recorded directly into the app. Assess and score a wide range of abilities, from speed to ball control, and add athletes to your database. There, human agents looking for talent can find talent, and apps can market athletes directly to specific clubs.
For now, at least some of the recruiting process remains in human hands. However, advances in AI have led to a growing debate about how many functions should be left to machines.
On a crisp Sunday morning at a modest stadium in rural Sao Paulo state, dozens of teenagers, clutching well-worn, muddy spikes, lined up in rows of faded concrete seats.
Many traveled from towns hundreds of miles away to try out for roster spots on local teams in Aguay, a sleepy town of 30,000 people. The players, all between the ages of 14 and 19, were selected based on their scores on an AI-powered mobile app. Now, they wanted to show off their skills in real life.
Some of the boys practiced for a minute while an app captured and scored their movements in real time. Later, on the field, the teenagers raced to control the ball under the watchful eye of a team of trainers.
Davi Barossi, 18, made an immediate impression. He evaded two defenders and smashed the ball into the corner of the goal. Barossi had traveled 10 hours by car from the southern state of Santa Catarina. “I’m here chasing a dream,” he said a day after watching Brazil’s national team play at the World Cup.
Nathan Moraes, an 18-year-old from the Amazonian state of Pará, had an even more difficult time. After a failed tackle, he limped off the field, wincing in pain. “Every time you get a chance, you have to give it your all,” he said, massaging his cramping shin.
During breaks, players grilled each other, ate chopped fruit and guzzled water. Moraes boasted, “I’m second in the app.” “What is your rank?”
Barossi showed off his metrics on a beat-up cell phone. He was worried because he is shorter than many players his age. However, as a result of continuing to train every day using the app, he was able to rank among the top 30 nationally in his age group. “I’m always kicking the ball and recording it,” he said.
Most experts agree that AI tools can help set accurate, standardized criteria for players, but caution that the technology may have blind spots.
Metrics may favor taller or stronger athletes and ignore less traditional talent. While much of Brazil is online, these apps remain inaccessible to poor athletes without a proper connection or a quality cell phone camera. Users can also delete or replace uploaded videos as many times as they like, allowing them to earn higher scores that do not necessarily reflect their abilities.
Others believe that no matter how advanced it is, artificial intelligence will never be able to surpass the trained eye of a professional olheiro.
“This is a gift that God gives you,” said Brazilian scout João Maradona. His job exploring Brazil’s remote northeastern region discovered several athletes who went on to play for the Brazilian national team. “No one can teach you how to spot really special raw talent in just 15 or 20 minutes.”
Perhaps unsurprisingly, the people building AI scouting apps have different views. On a recent afternoon in a small startup office in Sao Paulo, analysts working for the app Footbao scrutinized videos posted by athletes. With a quick click of the mouse, we scored each player across 24 different categories.
The grainy clip was selected by artificial intelligence as the most promising among tens of thousands of clips uploaded to the app by players across Brazil. After analysts reviewed the video, AI technology used a formula to rank the players and create a detailed report for the club.
The AI was still being trained. However, the ultimate goal was to automate evaluations, reduce human error, and make the scouting process more data-driven.
“We’re not trying to take jobs away from scouts,” said Nick LaPorte, the startup’s chief operating officer. “We make scouting more efficient and economical.”
Advanced technology is already transforming football in many ways, with top clubs experimenting with the use of AI to analyze matches, prevent player injuries and develop match strategies. Advocates of AI argue that recruiting is just the next frontier.
The expanding role of technology was evident at Santos FC’s training facility on a recent morning. The club’s youth team darted up and down the field as drones hovered overhead. The recorded footage could be analyzed by AI and used to measure player performance.
Santos, which got its start with Brazilian legends such as Pele and Neymar Jr., is partnering with Futabao and using the app to recruit talent and aim to stay one step ahead of rival clubs.
“We can’t be everywhere at once,” said Carlos Antonio Annunciação, the club’s player recruitment coordinator. “Today, with the help of technology, we can go even further.”
Still, he was prepared to travel more than 600 miles the next day just to meet the promising player in person. Anunsiason was tipped off through a WhatsApp message from a veteran scout, he said. “I can’t help but watch it live,” he added.
Back at the tryout in rural Sao Paulo, the final match ended just before noon. Teenagers leaned against a rusty chain-link fence, sweaty and exhausted, waiting to see if they could join their local team.
Barossi and Moraes were also among the six players selected for the squad. The rest slumped their shoulders and began to scatter.
The new recruits headed to the locker room with cheerful faces. “This is the opportunity I was looking for,” Barossi said. – ©2026 The New York Times Company
This article was originally published in The New York Times.
