Case study · 2026 · AI · Web · Mobile
Your smartwatch sees patterns in your sleep, heart rate and activity that nobody else notices.Built an AI app that reads your watch data. It actually tells you when something's off, in plain everyday words.
AIHealthIQ ingests heart-rate, sleep, steps, and oxygen data from smart watches and fitness bands, correlates trends with an LLM, and pushes treatment, medication, and lifestyle suggestions to a web + mobile UI. The studio shipped data ingestion, the correlation pipeline, the recommender, and the dashboards.
- Express
- React-Redux
- SQLite
- OpenRouter
Inside the build
Overview
- 4
- Wearable signals
- 3
- Surfaces shipped
- 1
- Correlation pipeline
- API
- First-class API
Pulls data from smart watches, fitness bands, and other sources (heart rate, sleep, steps, oxygen), correlates with AI, and recommends treatment, medication, or lifestyle changes. Web and mobile UI, with an API.
What shipped
What it does
- Wearable data ingestion
- AI analysis and trend watching
- Treatment and lifestyle suggestions
- Web and mobile UI, plus API
The problem
- Smart watches collect data nobody interprets
- Everyday data rarely reaches a doctor
- You don't know when to actually book a visit
Why it matters
- Someone always watching your data
- AI flags real changes, not noise
- Concrete lifestyle tips, not generalities
How it shipped
- 01 · BRIEF
Map the wearable signals worth pulling.
Workshop with the founders to pin down which four signals (HR, sleep, steps, SpO2) actually drive the recommendations · everything else dropped from v1 scope.
- 02 · BUILD
Express ingest + LLM correlation + Redux UI.
Express backend handles per-vendor wearable feeds, normalises, persists in SQLite, then OpenRouter routes to the model best-suited per signal type. Redux drives the React + mobile UIs off the same store shape.
- 03 · SHIP
Web, iOS, Android, plus the public API.
Three end-user surfaces shipped on the same correlation engine, plus a HealthApplication-typed JSON-LD'd API for clinic integrations.
Stack
Ingest
Per-vendor wearable feeds, normalised
Apple Health, Garmin, Fitbit, Oura · normalised to a single internal schema before correlation.
AI
OpenRouter-routed correlation engine
Different signals route to the model that handles them best · cost-aware fallback per request.
UI
Web + iOS + Android off one store
Redux store shape shared across React web and React-native mobile · one source of truth for trend cards.
API
Clinic-grade JSON API
HealthApplication-typed schema · clinics can pull patient summaries on demand.
Case study
“Our smartwatches were collecting data nobody actually read. The studio built a system that connects the dots, sleep + heart rate + activity together, and tells you in plain words what changed and why it matters. The week we started using it, it caught a pattern I'd missed for years. The team also handed back a manual so we can keep adding new sources without rebuilding everything.”
More work
Next project
AutoImport