Why the Best Coaches in the World Are Obsessed With Data Right Now

Guessing got too expensive. I’m Cassandra Toroian, and I’ve spent 25 years in technology and entrepreneurship, so when I look at why the best coaches in the world are obsessed with data right now, I don’t see coaches becoming less human – I see the good ones refusing to let memory run the whole room.

That’s the shift.

The best coaches are not obsessed with data because they stopped trusting their eyes. They’re obsessed because data keeps their eyes honest. It shows the rep they forgot. The fatigue pattern nobody wanted to admit. The spacing problem happening again and again. The player who looked fine but was slowing down. The tactical habit opponents had already figured out. The “one-time mistake” happening 17 times.

Once you see it, you can’t unsee it.

A great coach still has the eye.

Data just makes the eye prove its work.

Guessing Got Too Expensive

The best coaches don’t wake up wanting more dashboards. Nobody wants more dashboards. Most dashboards are just fancy clutter if the room doesn’t know what decision it’s trying to make.

What coaches want is simpler.

They want to know who is ready. Who is tired. Who is improving. Who keeps making the same mistake. Who is quietly creating value. Who looks good in the box score but is hurting the shape of the team. Who looks average but keeps doing the little things that win games.

That’s not a spreadsheet problem.

It’s a decision problem.

This is why the INEOS Grenadiers story matters. Reuters reported on April 28, 2026, the cycling team signed a five-year AI partnership with Netcompany, putting its PULSE AI-driven platform at the center of the team’s push to improve race and performance decision-making. Dave Brailsford’s point was the one that actually matters – the challenge is not just having data, it’s turning data into simple, practical actions and faster decisions when it counts.

That’s the whole thing.

The best coaches are not chasing numbers because numbers are cute. They’re trying to make better calls under pressure.

Who attacks?
Who rests?
Who gets pushed?
Who gets protected?
Who is carrying hidden fatigue?

Who is about to crack open the game, the match, the race, the season?

Data doesn’t answer all of it by itself. But it gives the room something better than vibes.

The Coach’s Eye Still Matters – But It Needs Backup

I don’t want a sport where the coach stares at a screen and waits for the machine to approve the next move.

That’s boring. Also wrong.

The coach’s eye still matters because sport is full of things that don’t behave neatly. Confidence. Pressure. trust. fear. timing. chemistry. A player who is physically ready but mentally cooked. A player who looks messy but is actually doing the hard job nobody else wants. A player who is slow on one rep because the assignment forced it.

Data can miss context.

But coaches miss context too.

The best setup is not coach versus data. It’s coach plus data – and then the room has to explain the gap.

NFL Next Gen Stats is a good example of how much evidence is now available around every game. NFL Football Operations says the system captures location, speed, distance traveled, and acceleration 10 times per second, charts player movement within inches, and creates more than 200 new data points on every play of every game.

Think about it.

More than 200 data points on every play.

The coach can still say, “I know what I saw.”

Fine. But now the next question is – ok, does the evidence back it up? That’s healthy. That’s not anti-coaching. It’s coaching with accountability.

The old version of coaching could lean too hard on memory. The new version can’t. The season is leaving a trail now. Every rep has fingerprints.

And the best coaches are willing to look.

Data Makes Feedback Specific

This is one of the biggest reasons coaches are obsessed with data right now – it makes feedback harder to dodge.

“Work harder” is not coaching.

“Be quicker” is not coaching.

“Stay locked in” might be true, but it’s not enough.

Athletes need specifics. Coaches need specifics too. The more competitive the level, the less useful vague feedback becomes.

AWS says Catapult’s AI-driven analytics can generate 600 unique metrics per player per game, giving teams insight into athlete performance, workload management, and injury prevention. AWS also says connecting those metrics with video helps coaches align physical output with actual game footage.

This connection matters.

Because now a coach can say – here’s where your sprint distance dropped, here’s the clip where it changed the recovery angle, here’s the moment your deceleration load spiked, here’s why we’re adjusting your training load, and here’s what we need fixed before the next match.

That’s coaching.

Not the motivational poster version. The real version.

And athletes respect it more, even when they don’t love hearing it. Because it’s harder to argue with clean evidence tied to film.

It’s not “I feel like you were late.”

It’s “you were late here, here, and here – and this is the pattern.”

Big difference.

The Best Coaches Use Data to Self-Scout First

It’s easy to use data to judge players.

The harder part is using data to judge yourself.

That’s where the best coaches separate. They’re willing to ask whether their own habits are hurting the team. Whether their rotations are predictable. Whether their training loads are creating fatigue. Whether their tactical preferences are leaving space exposed. Whether their “identity” is real or just something they say because it sounds good.

Data gets uncomfortable fast when it points back at the staff.

Good.

This is where the value is.

Are we really disciplined?
Are we actually fast?
Are we really developing players?
Are we asking athletes to cover too much ground because our system is messy?
Are we blaming effort when the structure is the problem?

These are not fun questions. They are useful questions.

And this is the difference between coaches who use data as decoration and coaches who use it as a mirror.

The mirror matters.

Because sometimes the player everyone is blaming is just trapped inside a bad instruction. Sometimes the “low effort” issue is actually workload. Sometimes the “bad decision” keeps happening because the team shape leaves the athlete with two bad options and no good one.

Data doesn’t automatically solve it. But it can stop the room from lying about it.

Workload Data Changed the Conversation

Every coach says they care about player health. Data shows whether the system actually supports it.

This is why workload, fatigue, and recovery data have become central. Coaches are not just asking who can play. They’re asking who can play well, who can train, who needs reduced load, who is drifting into risk, and who is giving signs the body is compensating.

This doesn’t mean data predicts everything. It doesn’t. Bodies are complicated. Contact is chaotic. Injuries happen even when everyone does the right thing.

But workload data makes the conversation earlier and sharper.

The useful question is not “Is this player tough enough?”

The useful question is – what is the athlete’s body telling us before the body starts yelling?

That’s a very different way to manage performance.

And honestly, it’s more respectful to the athlete.

Because without data, coaches can confuse pain tolerance with readiness. They can confuse a player’s willingness to push with actual capacity. They can ask for more because the player says they’re fine, even when the pattern says they’re not.

Data gives the staff a better map. Not a perfect map. Better. And in elite sport, better matters.

Video Plus Tracking Data Is the Real Shift

Video alone is powerful. Tracking data alone is useful.

Together, they’re a different thing.

This is why the best coaches care right now. They don’t just want to know a player ran a certain distance or hit a certain speed. They want to know what was happening in the game when the output happened.

Was the sprint useful?
Was the run reactive or proactive?
Was the player covering for someone else?
Was the high workload created by tactical chaos?
Was the slow recovery angle physical fatigue or bad positioning?

This is where video plus data matters.

A number without film can mislead you. Film without data can leave too much to memory. Together, they give the coach a better chance of understanding the actual rep.

The NBA and AWS are doing this in a very public way. AWS says the NBA’s first AI-powered advanced stats include Defensive Box Score, Shot Difficulty, and Gravity. Defensive Box Score is built to quantify defensive contributions traditional stats miss, Shot Difficulty evaluates each shot through factors like shooter positioning and defensive pressure, and Gravity measures the attention certain players draw and the advantages they create for teammates.

Gravity is the one getting me.

Because coaches have known forever that some players bend the court without touching the ball. They pull defenders. They create space. They change decisions. They make the game easier for everyone else.

That value used to be hard to defend internally. Now the tech is trying to measure it. Not perfectly. I don’t trust anything claiming perfection. But enough to make invisible value less invisible.

That’s why coaches are obsessed. Data can finally start showing the things good coaches always felt but couldn’t always prove.

The Box Score Misses Too Much

The box score is not useless.

It’s just small.

It catches the ending of the play, not always the reason the play worked. It catches the goal, the assist, the rebound, the tackle, the completion, the miss. But it misses the rotation, the pressure, the spacing, the decoy run, the recovery, the screen, the leverage, the player who made the correct decision two passes before the stat happened.

This is why modern coaches are moving beyond traditional numbers.

A player can score less and still bend the game. A defender can produce value without steals or blocks. A lineup can work because of space, timing, and pressure – not because the simple stat line screams at you.

Same thing in football. Same thing in cycling. Same thing in basketball. Same thing across sport.

The best coaches already knew the box score was incomplete. Now they have more ways to prove what it missed.

And once you can prove it, you can coach it.

That’s the part that matters. Because vague praise doesn’t develop players. Vague criticism doesn’t either. Evidence does.

This Is Everywhere Now

One mistake people make is treating sports analytics like it belongs to one sport or one league.

It doesn’t.

Cycling teams are using AI platforms to unify race, rider, and performance data. Football teams are working from player-tracking data on every play. Basketball is measuring defensive pressure, shot difficulty, and off-ball gravity. Performance staffs are connecting athlete workload with video. Coaches are trying to see the whole picture faster, because the game is not waiting around for them.

This is not a fad.

It’s becoming the operating layer of modern coaching.

The best coaches are not fighting it. They’re shaping it. They’re asking better questions of the data. They’re learning what to ignore, which is just as important as learning what to trust.

Because more data is not automatically better. Better questions are better. Cleaner decisions are better. Faster alignment is better.

That’s the obsession. Not the data itself. The clarity.

The Danger Is Worshipping the Dashboard

Here’s where I get cranky.

A dashboard can make people stupid if they treat it like a boss.

A clean chart feels official. A metric with two decimal points feels important. A model output can sound smarter than a coach saying, “I don’t buy it.”

But sometimes the coach is right.

Sometimes the data is missing context. Sometimes the input is messy. Sometimes the model is measuring the wrong thing. Sometimes the number looks bad because the player is doing a job that protects the team but hurts the metric.

This is why the best coaches don’t worship data.

They interrogate it.

They ask where it came from. What it misses. What it assumes. Whether it matches film. Whether it matches what the athlete feels. Whether it helps the next decision or just makes everyone feel clever.

The worst version of data in coaching is when people hide behind it.

“The model said.”

Ok. Why?

Show me the clip. Show me the pattern. Show me the confidence. Show me what changed. Show me what we’re going to do with it.

If nobody can answer it, the dashboard is decoration.

And sports already has enough decoration.

The Data Doesn’t Coach the Player

Data can identify the pattern.

It cannot sit across from the athlete and deliver the message the right way.

That still belongs to the coach.

A dashboard can say a player is late rotating. It can’t know whether the player needs a hard correction, a quiet conversation, a role adjustment, more confidence, less information, or a completely different teaching cue.

A model can show workload risk. It can’t always know whether the player is scared to admit soreness because they’re fighting for minutes.

A tracking system can show speed drop-off. It can’t know the full emotional load of a season.

This is why the human part still matters so much.

Actually, it matters more.

Because the better the information gets, the more important communication becomes. If the coach can’t turn evidence into trust, the athlete won’t absorb it. If the staff can’t translate data into action, the team won’t change. If the room can’t handle disagreement between the coach’s eye and the model, everyone just retreats into their favorite opinion.

That’s not progress.

It’s noise with charts.

The Best Coaches Ask Better Questions

This is the real edge.

Not answers. Questions.

Why does this player fade after a certain load?
Why does this lineup defend better even though it scores less?
Why does our structure break after substitutions?
Why does this athlete perform better in one role than another?
Why are we calling the same pattern in the same situation?
Why does this player’s value show up in film but not in the box score?
Why do we keep blaming effort when spacing is the real problem?

Good data makes lazy explanations harder. That’s why some people resist it. It threatens the comfortable story. And every team has comfortable stories. “That player is inconsistent.” “We’re a tough team.” “We just need more energy.” “He doesn’t fit.” “She’s not ready.” “We got unlucky.”

Maybe.

Or maybe the evidence says something else.

The best coaches are obsessed with data because they want to know which story is real.

Why Do Coaches Use Data in Sports?

• Coaches use data to track workload, fatigue, movement, tactical patterns, and player development.
• It doesn’t replace instinct – it gives coaches better evidence before making decisions.

The Future of Coaching Is Not Less Human

When people come across sports technology, this is what I want them to understand as Cassandra Toroian: the best technology in sports does not make the game less human.

It makes the human decisions more accountable.

That’s different.

The lazy fear is that data turns athletes into numbers and coaches into button-pushers. And yes, bad organizations can absolutely do that. A bad process with better tech is still a bad process. Sometimes it’s worse because now it’s confident.

But the good version is powerful.

The good version helps a coach see the player more clearly. It helps an athlete understand exactly what needs to change. It helps performance staff protect bodies with better evidence. It helps teams stop confusing memory with truth.

The future of coaching is not a coach replaced by AI.

It’s a coach who has to be sharper because AI is in the room.

The room has more evidence now. More film. More tracking. More workload data. More tactical analysis. More proof of what actually happened. This means the best coaches can’t just rely on presence, reputation, or gut.

They still need instinct. They just need instinct with discipline.

That’s why the best coaches in the world are obsessed with data right now. Not because they want sports to become cold. Because they know the game is already producing the evidence.

And once the evidence is sitting right there, the real question is pretty simple… Are you brave enough to look at it?

References

Reuters – New AI Partnership to Propel INEOS Grenadiers Back to Top, Team Hopes: https://www.reuters.com/sports/new-ai-partnership-propel-ineos-grenadiers-back-top-team-hopes-2026-04-28/

INEOS Grenadiers – INEOS Grenadiers and Netcompany Announce Landmark AI Partnership: https://www.ineosgrenadiers.com/news/ineos-grenadiers-and-netcompany-announce-landmark-ai-partnership-to-power-the-future-of-performance/

NFL Football Operations – NFL Next Gen Stats: https://operations.nfl.com/gameday/technology/nfl-next-gen-stats/

AWS – The Data Behind the Win: How Catapult and AWS IoT Are Transforming Pro Sports: https://aws.amazon.com/blogs/iot/the-data-behind-the-win-how-catapult-and-aws-iot-are-transforming-pro-sports/

AWS – NBA Powered by AWS: https://aws.amazon.com/sports/nba/

NBA – Inside the Game: https://www.nba.com/inside-the-game

Amazon – NBA and AWS Team Up to Bring AI-Powered Stats to Basketball Fans: https://www.aboutamazon.com/news/aws/nba-aws-cloud-ai-partnership-basketball-innovation

Barça Innovation Hub – AI & Computer Vision in Football Analytics: https://barcainnovationhub.fcbarcelona.com/blog/ai-computer-vision-football-analytics/

Catapult – Fundamentals: Player Load and Athlete Work: https://www.catapult.com/blog/fundamentals-playerload-athlete-work