UX research & design for an AI-powered fitness app for older adults
I led the research and design of Smart Baduanjin — an AI-powered fitness app that helps older adults in Hong Kong learn and practise the traditional eight-movement Chinese Qigong exercise on mobile and tablet.
Teaching Baduanjin to elderly users with AI
Baduanjin is an eight-movement Chinese mind-body exercise — short, easy to learn, and proven to enhance physical flexibility and coordination.
With Hong Kong facing a rapidly ageing population and high smartphone usage among the elderly, the government funded OliveX to explore technologies that promote active-ageing.
1. Unfamiliar with Tech
Many older adults left the workforce before technology integration, leaving them with limited digital knowledge.
2. Lack of Confidence
Limited digital exposure leads to feelings of incompetence and hesitation with new apps.
3. Cognitive Load
Learning BDJ is challenging enough — adding AI pose detection to a mobile app amplifies complexity significantly.
Insights that guided learning flows and app design
Interviews
Interviewed BDJ practitioners and non-practitioners to probe motives, struggles, and habits. Informed journey maps and feature ideas.
Sample: "When you first started learning BDJ, what did you find challenging?"
Contextual Inquiry
Observed BDJ classes to understand how older adults learn and how instructors structure lessons — directly guiding the learning flow design.
Desk Research
Explored different schools, benefits, and the history of BDJ, plus how elderly users interact with smart devices, to shape app content and interactions.
Testing prototypes in users' homes revealed what labs never would
Phone Setup Was Unintuitive
AI practice required full-body capture, but elderly users struggled to understand the placement requirement.
Cognitive Overload
Multiple new tasks at once — camera permission, phone setup, and BDJ movements — overwhelmed users simultaneously.
No Sense of Progress
Without a coach, users couldn't tell if they were improving — creating uncertainty and reduced motivation.
Doubt Towards New Apps
Many elderly users were hesitant and often sought reassurance from others before proceeding.
Three key design responses to research findings
1. Video Tutorials + Volume Prompts + Vocal Cues
Added video tutorials, volume prompts, and clear text with vocal cues to guide users through phone setup for the body scan — a completely unfamiliar requirement.
Explored different phone/tablet placement scenarios and added tailored vocal cues for each to increase usability.
2. Chunking to Reduce Cognitive Load
Reduced cognitive load by breaking learning into smaller, sequenced steps:
- → Key Points feature to familiarise poses before practice
- → Tutorial videos with pauses and zoomed-in key poses
- → Clear vocal guidance mirroring how instructors teach in class
3. Practice Video Recording for Progress Tracking
Inspired by weightlifters who film their form, I designed a recording feature letting users compare their movements side-by-side with the in-app instructor.
"Without a coach present, I wouldn't know what I did right or wrong."
This became the feature users loved most — providing a sense of improvement and progress independent of the AI's limited feedback capability.
The Outcome
Google Play HK Best Personal Growth App of 2019. Now part of rehabilitation programmes in local hospitals.
Impact
- Award-winning product launch
- Adopted in hospital rehabilitation programmes
- Validated AI can serve older adults meaningfully
"Smart BDJ has changed the way I teach patients Baduanjin. I see countless benefits for rehabilitation."
— Edward Chan, Occupational Therapist
Learnings
- Context matters — home testing reveals real barriers
- AI can enhance or hinder — consider the audience carefully
- Would enhance: real-time AI feedback, in-app peer communities