ARC / athlete protection platform / injury risk intelligence

Protect athletes before small signals become major injuries.

From signal to decision.

One preventable injury can change a season. ARC helps coaches, athletes, and sports medicine staff see warning signs earlier by turning Catapult, WHOOP, CSV uploads, wellness surveys, body-map pain reporting, and recovery context into explainable decisions. It is not a dashboard to inspect after the fact. It is a decision-support system built to produce something useful from session one, even when the data is incomplete.

Request Early Access 01 View the system 02
Catapult, WHOOP, Oura-compatible inputs, uploaded CSVs, wellness surveys, and body-map pain reporting aligned in one operational layer.
Role-based outputs for coaches, athletes, and sports medicine staff with short, actionable language before training begins.
Graceful degradation and cold-start confidence keep ARC useful without pretending every team has perfect data.
01 / Problem

Teams are already collecting data. The gap is action.

Most teams already have some combination of wearables, spreadsheets, surveys, and staff notes. The hard part is not collection. It is turning fragmented signal into action before training begins. Many injuries emerge under coach-controlled load, many programs lack clean labeled injury data, and many existing systems are too expensive or too heavy to operationalize. Warning signs usually build through smaller shifts in soreness, sleep, exposure, pain location, and recovery quality long before anyone calls it a problem.

By the time an athlete is pulled, the pattern has usually been visible for days.

Operational risk
Missed morning check-ins, localized soreness drift, reduced sleep recovery, and exposure spikes often sit in different systems or different conversations. The result is delayed translation. Coaches need the short version. Sports medicine staff need the mechanism and context. Athletes need a reporting loop that does not feel punitive or useless.
D-4
Pain note added
D-2
Sleep recovery down
D-1
Load spike vs baseline

Collection without context creates false confidence.

Data reality
A readiness score without pain location, prior injury overlap, medication context, or session history is not enough to direct a day of training.
Wearables alone do not explain why the signal changed or what to do next.
Many collegiate and academy teams need useful output without a fully instrumented environment.
Staff need research-grounded narratives behind a recommendation, not just a flag.

Small ignored signals become larger roster problems.

Performance cost
One missed signal can become reduced availability, unstable return-to-play progression, or a preventable roster problem that started as a small shift.
02 / Built for everyone on the sideline

Role-based logic, not one generic dashboard.

Coaches, athletes, and sports medicine or performance staff do not need the same screen, the same level of detail, or the same decision language. ARC presents the right context to the right person while keeping the underlying reasoning aligned across the whole workflow.

For coaches Roster view
Readiness at a glance
See who is stable, who is drifting, and who needs a different session plan before the team steps onto the field.
Daily team risk overview with player-level mechanism summaries and readiness context.
Session adjustment suggestions tied to load, fatigue, and recent symptom trend.
Roster invites, workflow setup, and short decision support before training begins.
For athletes Daily check-in
Fast reporting, low friction
Athletes can report fatigue, body-map pain, readiness, nutrition, sleep, and recovery in a format that is quick to complete and clear in purpose.
Quick daily check-ins with body-map pain reporting and readiness status.
Nutrition and recovery logging with follow-up after recommendations change.
Privacy-aware reporting that supports honesty and a useful feedback loop.
For sports medicine and performance staff Clinical context
Useful when the decision gets harder
Staff need signal progression, assessment outcomes, intervention history, and clinically useful context that supports load management and return-to-play choices.
Assessment outcomes, injury flags, and recovery notes that stay attached to the record.
Pre-season baseline annotation, prior injury overlap, and return-to-play context.
Clinically useful summaries rather than generic wellness snapshots.
03 / How the system works

Signal to strain to risk to decision.

ARC moves the staff from raw data to an operational recommendation. It works across richer environments and leaner ones alike, producing useful output even when not every data source is available. That graceful degradation matters in real collegiate and academy settings.

Signal

Collect what the athlete and system are already saying.

GPS wearables, WHOOP or Oura inputs, CSV uploads, daily wellness surveys, pain body maps, profile data, and staff notes enter a common layer.
Strain

Watch how load and fatigue accumulate over time.

Acute:chronic workload ratio, output drop, recovery deficit, mechanical stress, soreness progression, and pain trajectory are read as a pattern instead of disconnected values.
Risk

ARC detects instability before the problem is obvious.

ARC's six-signal engine builds a mechanism-aware risk pattern using simulation percentile, prior overlap, and explainable drivers while preserving honest confidence.
Decision

Present a recommendation people can actually use.

Coaches get reduce-load or modify-session guidance. Athletes get a clear loop. Sports medicine staff get monitor, assess, or return-to-play context. One signal. Different views. Same logic.
04 / Explainability

Not a black-box dashboard.

ARC is useful because the model can be inspected at the point of action. Staff can see why the score changed, what it means, and what to do next in under 30 seconds. That is what makes the output trustworthy enough to use.

Sample reasoning: hamstring strain risk elevated

Explained output
Sprint load rose 35% above the athlete's baseline window. Hamstring soreness increased over three straight mornings. Sleep trend fell after the exposure spike. Prior injury overlap and reduced readiness confidence pushed the pattern higher.
0.71
This is not a diagnosis. It is an explainable probability signal with visible drivers and honest confidence. ARC starts with priors and rule-based logic, then improves as more sessions and feedback accumulate.

Why the risk changed

Model drivers
Driver 01 / load spike this week vs baseline exposure window
Driver 02 / hamstring soreness increasing over consecutive days
Driver 03 / sleep trend falling after heavy session demand
Driver 04 / prior injury overlap and reduced readiness confidence

Recommendation

Decision support
Reduce sprint density for the session, maintain technical work, prompt post-warmup feedback, and refer for staff assessment before the next high-speed block.
05 / Feedback loop

The system improves through response, not just monitoring.

A recommendation only matters if the next signal captures what happened after it. ARC keeps the loop short. The system recalibrates as coaches rate alert quality, athletes report recovery, and sports medicine staff log assessment outcomes, intervention effect, and whether the athlete improved naturally or only looked better under medication.

06 / FAQ

Questions teams ask before the pilot starts.

ARC is meant to be understood quickly. The workflow should feel operational in under a minute, not like a platform that needs a long explanation before anyone trusts it.

ARC collects the signal a team already has, reads how strain is accumulating, maps mechanism-aware risk, and then presents a role-based recommendation for coaches, athletes, and sports medicine staff.
No. Wearables improve signal quality, but ARC is designed for graceful degradation. Teams can start with CSV input, wellness surveys, body-map pain reporting, and staff context, then expand from there.
Daily reporting can include body-map pain location, soreness, fatigue, sleep, readiness status, nutrition or recovery notes, and follow-up after a recommendation changes.
Coaches get short, actionable outputs: team risk overview, player-level mechanism summaries, session adjustment suggestions, and decision support before training begins.
Yes. Prior injury overlap, baseline annotation, recovery notes, assessment outcomes, and return-to-play context can all shape the risk narrative and the confidence behind the recommendation.
ARC is designed for that role. Sports medicine staff can review injury flags, assessment outcomes, recovery notes, and intervention follow-up in a workflow that stays connected to coach and athlete views.
No. ARC is an athlete protection platform and injury risk intelligence system. It provides explainable decision support, not a diagnosis and not a medical device.
ARC starts useful from session one with priors and rule-based logic. Confidence improves as temporal trends, feedback, outcome quality, and intervention history accumulate across the workflow.
07 / Pilot

Pilot ARC with your team.

Early pilots are best suited to collegiate programs that want a tighter readiness and care workflow across coaching, performance, and sports medicine. Strong early use cases include soccer, baseball, and water polo, with web-first deployment fully acceptable in early rollout.

Request access 60-day pilot

Pilot ARC with your team

Start with one roster, one workflow, and one shared decision loop. The objective is simple: make athlete signal operational before the next training day begins, with honest cold-start confidence that improves as sessions accumulate.
Reviewed program by program / web-first pilots supported
Request early access / college teams / coach + staff workflow
Early use cases Sports fit

Where the workflow is already clear

Soccer for high-speed exposure and soft tissue risk. Baseball for throw load, travel fatigue, and readiness drift. Water polo for shoulder demand, fatigue monitoring, and return-to-play context.
Soccer / baseball / water polo
What ARC needs Operational fit

A shared process beats more data.

The strongest pilots have consistent check-ins, wearable or CSV input, and a staff group willing to review why a recommendation changed instead of only whether it changed. ARC works best where trust and scrutiny coexist.
Explainable / low-friction / staff-aligned