
Timeline
September 2025 - April 2026
Role
UX Research Lead
UX Designer
Collaboration
1 Product Manager
3 Designers
3 Developers
4 Research Stakeholders
Nav
Problem
Most people with epilepsy track their seizures and medications using multiple tools, causing confusion and trouble in analyzing symptoms due to the disorganization and users' memory issues.
Solution
We built a centralized platform to record everything epilepsy-related, which is designed for this audience's unique pain points. Users can understand their conditions better through AI-powered insights and patterns.
Impact
93%
user satisfaction rate on the final prototype
74%
potential conversion rate
(tester to future user)
How might we create a centralized hub catered for people with epilepsy and their specific needs, which enables them to track their symptoms and understand their conditions better?
IDEATION
Accessibility when designing for a vulnerable population
This is my first time designing for a target audience with specific health concerns, so I conducted a desirability study and a co-design session to learn how visuals and interfaces can impact people with epilepsy.
Avoid bright colors and motion
Flashing light and animation can potentially trigger seizures. We prioritized designing the dark mode version of the app while still ensuring color contrast and bring calm, relaxed feelings to users.

Personalize experiences
Epilepsy is extremely complicated and varied — each person can experience it very differently.
We customized the app experience based on individual users' unique triggers and seizure types.
Create a positive perception of epilepsy
People often associate epilepsy with the image of a lightning bolt striking through a brain, which evokes negative connotations and emotions.
We created Finn — a mascot that acts as a gentle and supportive companion for people with epilepsy, helping them feel better about their conditions.

CHALLENGE
Manage stakeholder expectations and set product prioritization
Expectations 🌟
Stakeholders wanted to have a fully functional app with 5-6 main features that is ready to launch at the end of the 6-month project.

Constraints ⚠️
Building from scratch with no funding
Working 5-10 hours/week
Recruiting user testing participants take time
Considering stakeholder and user needs, as well as the team's bandwidth, I analyzed all the features on an Impact-Effort matrix and proposed the list of prioritization to the rest of the team.
Throughout the project, we were constantly discussing to make sure everyone on the same page with where the project goes.
Must have
Nice to have
Skip for now

DESIGN DECISION #1
All-in-one Epilepsy diary: Seizures, Medications, and Daily check-ins
Users either don't use any platform to record their symptoms, or use too many platforms all at once: calendars, Notes app, journal, etc. These tools are not designed for people with epilepsy specifically and require a lot of manual work.
I designed a specialized feature for each type of conditions users often need to log, providing templates and auto-populated fields to save time and effort.

DESIGN DECISION #2
AI-powered Insights and Trends
Logging medication and seizures wouldn't mean anything if users couldn't identify patterns and trends of their conditions, especially when epilepsy is unpredictable and complicated.
I designed an AI agent that could autonomously analyze users' data and reveal hidden insights into each person's unique experience with epilepsy — what they don't see on the surface.
Previous Iteration
Previous Iteration
❌ Surface-level insights
❌ No trends/ patterns over the time
❌ Text > Statistics & data

Final Iteration
Previous Iteration

✅ Highlight key data points + stats
✅ Show changes in user's conditions over the time
✅ Reveal hidden causes of seizures
Previous Iteration
Previous Iteration
❌ Using text to describe info is confusing
❌ Limited space to display multiple info types

Final Iteration
Previous Iteration

✅ Using both icons & colors for accessibility
✅ Show multiple info all at once for easier comparison
BEYOND THE PHONE SCREEN
Experimenting with AR glasses & smartwatches
IMPACT & USER FEEDBACK
Users make better decisions and get the tasks done more quickly
I tested the prototype with 8 users from diverse backgrounds—including students and tech professionals—with varying levels of cloud experience (beginner to intermediate) and from different regions across America, Europe, and Asia. The outcome was promising.
87%
Participants said the user flow was easy to comprehend, and the visual design and content were intuitive
70-75%
of the user process was automated by Copilot Agent, which gave users ease of mind
REFLECTION
What I learned as a Designer
Responsible AI
Being assigned to work on an AI-first project, I always reminded myself the most important goal was to remain user-centric and make sure my AI-powered design could solve user problems.


Think outside the box
As a designer, I’m often encouraged to follow the design systems, but in this project, I was given the creative freedom to explore new design elements. This experience taught me to take bold steps beyond the patterns I had limited myself to, create something new, and demonstrate its usability to the team.
Two-way collaboration
As a young designer, I’ve always seen collaboration as a way to learn from others and get feedback on my work. But this project showed me that my ideas could also contribute to others’ projects and inspire them. My design turned out to be more influential than I expected!

Big thanks to my teammates for building this app with me!



