The most influential figure at the 2026 World Cup never touched the ball. It wore no boots, appeared on no team sheet, and most fans in the stadium never saw it. It lives in millions of lines of code — and unlike a player, it never waits for permission.
Artificial intelligence has quietly become football's newest signing. The interesting question is no longer whether it belongs in the game. That argument is over. The question is what football becomes once the machines are this deep inside it.
Editor's note: This is an opinion piece. The technologies described — semi-automated offside, the connected match ball, limb-tracking cameras, referee body cameras, predictive analytics — are real and in use, and the specifications cited are drawn from the sources at the foot of the article. The conclusions are ours.
The Invisible Teammate
For most of its history, football sold itself on being beautifully simple. Twenty-two players, one ball, one referee, and a great deal of instinct. That version of the game is quietly disappearing.
AI now sits in places fans rarely think about. It helps clubs scout and recruit by surfacing players who fit a system before a human analyst watches any tape. It helps medical teams flag injury risk from workload and movement data. It helps coaches model the opposition, and it helps referees rule on the tightest margins in the game.
Football is no longer only being played. It is being processed.
What the Technology Actually Does
The vague talk about "AI in football" obscures how specific — and how fast — the machinery has become. FIFA has published the numbers, and they are worth sitting with.
Semi-automated offside technology (SAOT) works by fusing two data streams. FIFA's own description of the system introduced at Qatar 2022 specifies:
- 12 dedicated tracking cameras mounted under the stadium roof.
- Up to 29 data points per player — every limb and extremity relevant to an offside call.
- Sampled 50 times per second.
- A sensor inside the match ball reporting position 500 times per second.
The ball is the part most fans underestimate. Inside it sits an inertial measurement unit (IMU) that measures motion, rotation and acceleration in three dimensions. That is what pins down the exact instant the ball is played — historically the hardest variable in any offside call, and the one human officials could only estimate.
The effect on speed is dramatic. FIFA's testing put offside decisions at 15 to 25 seconds, against an average of around 70 seconds for the VAR checks that preceded them.
At the 2026 tournament the match ball was the Adidas Trionda, carrying the same class of sensor, and FIFA extended the tech further: reporting from the tournament indicated that referee body cameras were used across all 104 matches — a World Cup first — giving broadcasters a pitch-level view from the official's perspective, and that clear offside alerts were routed directly to assistant referees' earpieces rather than through the video booth, so flags could go up immediately instead of after a delayed review.
The Guardiola Problem
Imagine handing every coach unlimited information. That is roughly what modern football has done. Recruitment departments run predictive models on talent. Analysts dismantle an opponent's weaknesses using data the opponent can also see. Sports scientists use machine learning to anticipate muscle strain before it happens — the same pattern-finding described in our explainer on what machine learning actually is.
In theory, smarter inputs make smarter football. In practice it raises an awkward question: if everyone drinks from the same data, where does an edge — or originality — come from?
Football's defining moments were rarely the calculated ones. No model forecast Maradona's run against England, and no algorithm would have drawn up Messi drifting through a defence in Doha. The magic tends to live in the unpredictable, and unpredictability is famously hard to code.
The Referee's New Assistant — or New Burden
Referees may be AI's biggest winners. They may also be its biggest victims. Every tool that promises fewer mistakes raises the bar for what counts as a mistake.
Fans once accepted human error as part of the bargain. Now that a decision can be resolved to 29 tracked body points sampled fifty times a second, every call is held to that standard — and the outrage when technology still gets one wrong is louder, not quieter.
There is a subtler cost too. When a system draws an offside line at a margin finer than the human eye can perceive, it produces decisions that are technically correct and emotionally unacceptable: a goal disqualified by an armpit, rendered in confident 3D animation. Accuracy and legitimacy turn out to be different things.
The strange result is that AI has not killed controversy. It has moved the target.
The Worry Nobody Wants to Say Out Loud
Football has always belonged to people — the scout who spotted a talent on a muddy pitch, the coach who trusted a hunch over the spreadsheet, the player who ignored the instruction and made something nobody planned.
As AI grows more influential, the game inherits the dilemma every industry eventually meets: how much judgement should humans hand over? The honest answer is that nobody in football has decided. The technology arrived faster than the philosophy, which is how these things usually go.
Because football's greatest asset was never efficiency. It was imagination.
Frequently Asked Questions
How does semi-automated offside technology work?
It fuses two data streams. Twelve tracking cameras mounted under the stadium roof follow up to 29 points on each player's body — every limb relevant to an offside decision — sampling 50 times per second. Simultaneously, a sensor inside the match ball transmits its position 500 times a second, which fixes the precise moment the ball is played. Software combines both to determine whether an attacker was beyond the last defender at that instant, then alerts the video officials.
Is the World Cup ball really full of electronics?
Yes. The match ball contains an inertial measurement unit, a sensor package that measures motion, rotation and acceleration in three dimensions and transmits hundreds of times per second — 500 times per second in FIFA's specification. The 2026 tournament used the Adidas Trionda. The sensor's most valuable job is identifying the exact instant of contact, which was historically the least reliable element of any offside judgement.
Has technology actually made offside decisions faster?
Substantially. FIFA's testing put semi-automated offside decisions at 15 to 25 seconds, compared with an average of roughly 70 seconds for the VAR checks that came before. At the 2026 World Cup, reporting indicated clear offside alerts were sent directly to assistant referees' earpieces rather than routed through the video operation room first, allowing flags to go up in real time rather than after play continued.
Where else does AI operate in football besides refereeing?
Four main areas. Scouting and recruitment, where models identify players matching a tactical system before human analysts review footage. Injury prevention, where workload and movement data flag elevated risk. Opposition analysis, where automated reports break down an opponent's patterns. And broadcast, where tracking data powers graphics and statistics. Refereeing is simply the most visible use, because it is the one that changes results in front of an audience.
Does AI make football less exciting?
That is the genuine debate, and reasonable people disagree. The case for is that fewer wrong decisions means outcomes better reflect what happened on the pitch. The case against is that football's appeal rests partly on ambiguity and argument, and that decisions made at margins finer than human perception feel arbitrary even when they are correct. Accuracy and legitimacy are not the same thing, and technology has improved one more than the other.
Will AI ever replace referees entirely?
Unlikely in the near term, and the terminology reflects why: the system is "semi-automated" because a human still makes the final call. Offside is unusually suited to automation — it is a geometric question with a factual answer. Most refereeing decisions are not. Whether a challenge was reckless, whether contact was sufficient, whether an offence merits a card: these are judgements about intent and degree, and no current system decides them.
Offside
AI is not coming to football. It is here — in the ball, in the twelve cameras above the pitch, in the recruitment meeting, in the medical room, and now on the referee's head. The debate about whether it belongs is finished.
The more interesting question is one we will be answering for years: as football gets smarter, can it stay surprising? Fans do not fill stadiums to watch perfect decisions. They come to witness the moment nobody saw coming.
If the game ever trades that uncertainty away for accuracy, not even the smartest machine in the world will be able to hand it back.
Sources
- Semi-automated offside technology — FIFA
- Semi-automated offside technology to be used at FIFA World Cup 2022 — FIFA media release
- Semi-automated offside approved for World Cup after successful VAR trials — ESPN
- How semi-automated offside technology will change the Qatar 2022 World Cup — Forbes
- FIFA eyes referee body cameras for the 2026 World Cup — Reuters via AOL
Related on PrimusSource: Expected Goals (xG) Explained, What Is Machine Learning?, AI Agents Explained: A Practical Beginner's Guide and more in our football topic hub.
