PadelLabs

Understand your game. The smarter way to play, improve, and connect through padel.

Comment

Inspiration

Padel is growing fast, but most players still leave the court with only a vague feeling of how they played. We wanted to make improvement more measurable: turn each session into clear, useful feedback instead of a collection of disconnected numbers.

What it does

PadelLabs is an iPhone and Apple Watch companion app that records padel sessions and turns them into actionable insights. It tracks strokes, swing speed, consistency, session load, heart-rate zones, trends, achievements, and progression. An AI Coach translates performance data into practical technical and tactical recommendations.

How we built it

We built PadelLabs with Swift 6 and SwiftUI for iOS and watchOS. The Apple Watch captures workout and motion data, then uses an on-device Core ML classifier to identify strokes during a session. The phone receives the data through WatchConnectivity and presents it in dashboards, session reports, progress views, and shareable recaps.

The app uses a modular Clean Architecture with MVVM-C, local SQLite storage through GRDB, Firebase for cloud services and remote configuration, and RevenueCat for Premium subscriptions.

Challenges we ran into

The hardest challenge was turning a large amount of sports data into something a player can understand in seconds. We had to carefully choose the metrics that matter most, keep the interface approachable for every level of player, and make coaching recommendations specific enough to be useful.

Synchronizing sessions between Apple Watch and iPhone, maintaining consistent calculations across devices, and handling workout data reliably were also major technical challenges.

Accomplishments that we're proud of

  • Building a complete iPhone and Apple Watch experience for padel players.
  • Running stroke classification directly on the watch with Core ML.
  • Creating padel-specific analytics rather than generic fitness summaries.
  • Designing a local-first experience that remains useful without mandatory sign-in.
  • Turning raw session data into clear progress tracking and AI-guided feedback.

What we learned

We learned that great sports analytics is not about showing the most data—it is about showing the right insight at the right time. We also gained experience building a connected iOS and watchOS product, working with motion data, on-device machine learning, local-first storage, and secure cloud services.

What's next for PadelLabs

Next, we want to improve the stroke model with more real-world session data, expand tactical analysis, use computer vision as another alternative and add other stats like winners, unforced errors, refine the AI Coach, and make it easier for players to compare progress over time. Our long-term goal is to make PadelLabs the personal performance companion for every padel player.

Built With

  • ai
  • apple-watch
  • clean-architecture
  • core-ml
  • firebase
  • firebase-auth
  • firebase-functions
  • firestore
  • grdb
  • healthkit
  • ios
  • machine-learning
  • mvvm
  • revenuecat
  • sqlite
  • swift
  • swift-package-manager
  • swiftui
  • watchconnectivity
  • watchos
Share this project:

Updates

Submission history