By playing, you agree to uListen's Terms and Privacy Policy and YouTube's Terms of Service.
How I AIHow I built an Apple Watch workout app using Cursor and Xcode (with zero mobile-app experience)
Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.
At a glance
WHAT IT’S REALLY ABOUT
Building Apple Watch workout app via Cursor, Xcode, and structured AI workflow
- Terry Lin built “Cooper’s Corner,” an Apple Watch + iPhone workout tracker that lets users speak exercises, weight, and reps, then converts the transcript into structured workout logs with history and analytics.
- He started with an ultra-simple MVP: recording Voice Memos on Apple Watch, transcribing with GPT, and dumping results into a spreadsheet—then upgraded to a database-backed system and native apps.
- Because iOS development requires Xcode for building/debugging, he “dual-wields” Cursor for coding and Xcode for compilation, simulator/device testing, and watch builds.
- He developed a repeatable Cursor process—PRD creation, PRD review (rated for executability), PRD execution, plus refactoring and “rubber duck” learning rules—while managing token/context limits with smaller files and frequent Git commits.
IDEAS WORTH REMEMBERING
5 ideasStart with a “low-effort” MVP before building the full app.
Terry validated the core behavior by narrating workouts into Apple Watch Voice Memos, then using GPT to transcribe/tag and output to a spreadsheet—proving the value before investing in native apps and backend structure.
Voice-to-structured-data is the real product unlock, not just transcription.
The app doesn’t merely convert speech to text; it extracts exercise, weight, reps, timestamp, and other tags into consistent records that power analytics like top exercises and progression charts.
Mobile AI coding still needs platform-native tooling for build/debug.
Cursor can generate and edit Swift/iOS code, but Xcode remains essential for compilation errors, simulator/device behavior, and Watch-specific builds—so he keeps both tools pointed at the same project folder.
Treat the model like a cross-functional team with a real dev process.
His workflow mirrors org structure: write a PRD, have another “role” review it, iterate until it’s executable, then run a phased checklist with pauses—reducing hallucinations and rework.
Use “PRD review scoring” to predict whether execution will succeed.
By asking a model to rate the PRD (0–10) assuming zero context, he finds missing edge cases, unclear file targets, or inconsistent APIs—then iterates until it’s ~9/10 to enable near one-shot implementation.
WORDS WORTH SAVING
5 quotesTwo months later, I now have an Apple Watch and an iPhone app.
— Terry Lin
They could either work with you or work for you.
— Terry Lin
I realized I was just running into a lot of context windows with these same rules.
— Terry Lin
I call it vibe refactoring.
— Terry Lin
Anything that lets me know what's going on in the mobile.
— Terry Lin
High quality AI-generated summary created from speaker-labeled transcript.
