CONSCIOUS
01.
Simplicity is persuasive. Creative solutions can still be possible with simple, scalable designs.
02.
Conversational UX matters. The AI's tone directly shapes user trust and satisfaction.
03.
Designing for sustainability is designing for emotion. People keep what they feel connected to.
Round 1
Average Score
0
1
2
3
4
5
6
3.62
3.95
4.48
Round 2
Round 3
Context
I was a UX researcher,
and working under a post doc at UCSB's Research Mentorship program.
As an avid fashion lover, I wanted to explore how UX design solutions could shift fashion from an industry of overconsumption back to a way of self-expression.
Problem
Fashion has been reduced to hauls…
The experience of sustainable shopping is rewarding, but it’s hard to know what’s worth keeping, what fits your style, or how to even start building a wardrobe that lasts.
Research & Process
The Ideation Process!
Using the painpoints gathered, I sketched early flows focused on reconnection — how users could rediscover what they already owned.
Solution
Users can upload images of their garments, automatically categorized and sorted by Gemini's computer vision.
01.
I conducted usability testing with 12 participants and surveyed 70+ people.
Through three rounds of testing with the 12 participants, I measured task success, error rate, and perceived helpfulness.
Takeaways
Average Usability Score
User Insights
My big picture question was:
How might we help users develop a personal, lasting relationship with their clothes—using AI and UX to make sustainability intuitive?
Timeline
Role
Skills
Sketched low-fidelity wireframes to explore flows for digital wardrobe upload, AI outfit recommendations, and style onboarding.
Prompt-engineered interactions around a LLM chat-based stylist, emphasizing quick, conversational feedback loops
Designing AI-driven wardrobe assistant & feedback loops that turns fast fashion habits into sustainable style routines
Current platforms make discovering your
style difficult…
Cognitive overload:
Managing your wardrobe, finding outfits, and tracking purchases all live in separate, disjointed tools.
Lack of personalization: Existing systems often miss personal context like users’ motivations for shopping.
Trend-driven systems:
Most apps push new products instead of encouraging users to rewear what they own.
I built StyleMate’s high-fidelity prototype in Figma, later connected to Gemini’s multimodal API.
Users preferred when the AI asked clarifying questions before suggesting outfits.
A “Favorites” section increased attachment to clothing items.
Participants who self-identified as “not fashion-savvy” rated the app most helpful — average usability score of 4.48 / 5 after revisions.
June 2024 -August 2024
UX Researcher & Sole Prototyper
Flutter
Python
Figma
UX Research
Users can chat with a personal stylist who
focuses on REUSING and building attachments to
existing garments based on closet uploaded by user + revisit past conversations
02.
After making an account, homepage is adjusted to
your shopping preferences, adapting to your
overconsumption tendencies with reminders and
positive reinforcement.
03.
StyleMate
Connection > Consumption
The Ideation Process!
Solution
03.
02.
01.
Users can upload images of their garments, automatically categorized and sorted by Gemini's computer vision.
01.
Usability Testing
Takeaways
Average Usability Score
How might we help users develop a personal, lasting relationship with their clothes—using AI and UX to make sustainability intuitive?
Timeline
Role
Skills
Designing AI-driven wardrobe assistant & feedback loops that turns fast fashion habits into sustainable style routines
Trend-driven systems: Most apps push new products instead of encouraging users to rewear what they own.
The experience of sustainable shopping is rewarding, but it’s hard to know what’s worth keeping, what fits your style, or how to even start building a wardrobe that lasts. I wanted to design something that made that process feel good, not guilt-driven.
My big picture question was:
Cognitive overload: Managing your wardrobe, finding outfits, and tracking purchases all live in separate, disjointed tools.
I built StyleMate’s high-fidelity prototype in Figma, later connected to Gemini’s multimodal API.
June 2024 -August 2024
UX Researcher & Sole Prototyper
Flutter
Gemini API
Python
Figma
UX Research
The rise of fast fashion has turned self-expression into overconsumption. People are buying 60% more clothing than they did two decades ago, only to keep them for half as long.
I joined UCSB’s Research Mentorship Program wanting to explore where AI and UX could shift that behavior and reimagine how design could orient behavior towards wanting less to consume less.
Background & Context
Users can chat with a personal stylist who
focuses on REUSING and building attachments to
existing garments based on closet uploaded by user + revisit past conversations
02.
PAIN POINTS:
03.
03.
Using the painpoints gathered, I sketched early flows focused on reconnection — how users could rediscover what they already owned.
Sketched low-fidelity wireframes to explore flows for digital wardrobe upload, AI outfit recommendations, and style onboarding.
After making an account, homepage is adjusted to
your shopping preferences, adapting to your
overconsumption tendencies with reminders and
positive reinforcement.
Users preferred when the AI asked clarifying questions before suggesting outfits
A “Favorites” section increased attachment to clothing items.
Participants who self-identified as “not fashion-savvy” rated the app most helpful; average usability score of 4.48 / 5 after revisions
Simplicity is persuasive. Creative solutions can still be possible with simple, scalable designs.
Conversational UX matters. The AI's tone directly shapes user trust and satisfaction.
Designing for sustainability is designing for emotion. People keep what they feel connected to.
Prompt-engineered interactions around a chat-based stylist, emphasizing quick, conversational feedback loops
I conducted three rounds of usability testing with 12 participants to refine both flow and tone. Metrics measured: task success, error rate, and perceived helpfulness.
Lack of personalization: Existing systems often miss personal context like users’ motivations for shopping.
StyleMate ui/ux research
Designing AI-driven wardrobe assistant & feedback loops that turns fast fashion habits into sustainable style routines
Timeline
Role
Skills
June 2024 -August 2024
UX Researcher & Sole Prototyper
Flutter
Gemini API
Python
Figma
UX Research
The rise of fast fashion has turned self-expression into overconsumption. People are buying 60% more clothing than they did two decades ago, only to keep them for half as long.
I joined UCSB’s Research Mentorship Program wanting to explore where AI and UX could shift that behavior and reimagine how design could orient behavior towards wanting less to consume less.
Background & Context
Connection > Consumption
The experience of sustainable shopping is rewarding, but it’s hard to know what’s worth keeping, what fits your style, or how to even start building a wardrobe that lasts. I wanted to design something that made that process feel good, not guilt-driven.
Cognitive overload: Managing your wardrobe, finding outfits, and tracking purchases all live in separate, disjointed tools.
Lack of personalization: Existing recommendation systems often miss personal context — users’ values, cultural preferences, or motivations for shopping.
PAIN POINTS:
How might we help users develop a personal, lasting relationship with their clothes—using AI and UX to make sustainability intuitive?
My big picture question was:
The Ideation Process!
Using the painpoints gathered, I sketched early flows focused on reconnection — how users could rediscover what they already owned.
Sketched low-fidelity wireframes to explore flows for digital wardrobe upload, AI outfit recommendations, and style onboarding.
Prompt-engineered interactions around a chat-based stylist, emphasizing quick, conversational feedback loops
Solution
01.
After making an account, homepage is adjusted to
your shopping preferences, adapting to your
overconsumption tendencies with reminders and
positive reinforcement.
02.
Users can chat with a personal stylist who
focuses on REUSING and building attachments to existing garments based on closet uploaded by user + revisit past conversations
Users can upload images of their garments, automatically categorized and sorted by Gemini's computer vision.
03.
Average Usability Score
I conducted three rounds of usability testing with 12 participants to refine both flow and tone. Metrics measured: task success, error rate, and perceived helpfulness.
Users preferred when the AI asked clarifying questions before suggesting outfits
A “Favorites” section increased attachment to clothing items.
Participants who self-identified as “not fashion-savvy” rated the app most helpful; average usability score of 4.48 / 5 after revisions
User Insights
03.
02.
01.
Takeaways
Simplicity is persuasive. Creative solutions can still be possible with simple, scalable designs.
Conversational UX matters. The AI's tone directly shapes user trust and satisfaction.
Designing for sustainability is designing for emotion. People keep what they feel connected to.
I built StyleMate’s high-fidelity prototype in Figma, later connected to Gemini’s multimodal API.
Thanks for scrolling all the way!