All projects
Case study · 2024 — Present
Ohga — AI Wellness Companion
Independent consumer product — adaptive, privacy-first wellness
Independent builder · Independent
Personal product
FlutterDartRiverpodDriftFirebase
The problem
The problem
Wellness apps drown users in generic advice and dashboards. People need one clear action that adapts as their biology changes — without shipping health data to a black box by default.
Outcomes
- Consumer agent product designed for adaptive insights and local-first privacy posture
- Personal model that improves from user responses over time
Product
Ohga tracks patterns and surfaces actionable recommendations (sleep, move, eat, rest) rather than walls of charts.
Privacy-by-design: process on-device where possible; avoid “health data as training corpus” defaults.
Key tradeoffs
Data residency
Chose: Local-first processing bias
Rejected: Cloud-only personalization
Trust is the product in wellness; leakage kills the brand.
What was hard
- Personalization without invasive telemetry
What I would change
- Public metrics once beta cohort is large enough
Artifacts
