Lookfinder lets users search fashion by matching styles, instead of browsing catalogues.
Lookfinder started as an idea to bring the online shopping experience into the modern times. Together with a backend-developer and data scientist we developed a working prototype.
I was responsible for the UX Design and development of the fronted using React.
Let me explain
1
You cannot filter based
on how clothes look
2
You need to check
a lot of websites
3
You may not even know
what you are looking for
What we have right now
Categories
You can narrow things down — but still get thousands of items. And if you're looking for a style, not a jacket or jeans, this doesn't help much.
Speed
Success
Control
The Search Bar
Search functions can be unpredictable. Do they only look at product titles? Do they consider descriptions? Can they recognize details in images? Most of the time, it’s unclear.
Speed
Success
Control
Praying for Ads
Social media ads often suggest clothing that matches personal taste and surface hard-to-find pieces. But the selection is unpredictable, and there’s no control over what appears.
Speed
Success
Control
Scroll endlessly
This method ensures nothing gets overlooked, but at the cost of efficiency. Browsing through endless pages of products takes time and effort.
Speed
Success
Control
Site AI bots
AI bots can suggest clothes based on descriptions, but they depend on precise input. If you’re unsure how to describe your style, refining the results can quickly become frustrating.
Speed
Success
Control
Similar Clothes
Most stores suggest clothes similar to what you’ve clicked on. The issue? You first have to find something good. And after a few clicks, you might end up trapped in a stylistic dead end, where everything looks the same.
Speed
Success
Control
69% of online shoppers go straight to the search bar when visiting ecommerce sites, but 80% leave due to a poor experience.
Shoppers browsing fashion visuals online often experience choice overload, making it harder to commit to a purchase.
You show your friend a few outfits you like.
They recommend you clothes of similar style.
The user matches
outfits they like
We create a
taste profile
Turns out newer Visual Language AIs are amazing at categorizing outfits by detailed style.
The user sees
matching pieces
single option
focus on the
details
two options
focus on the
comparison
four options
focus on the
general impression
5+ options
focus on the
variety
4 – todays magic number
Just enough to get a clear sense of the style, without getting lost in the details. This layout helps people build a quick impression of a look, rather than focusing on specific pieces. It also reduces the expectation that they’ll get exactly what’s shown in the images.
User Journey
The outfit-matching step is central to the user journey. Since it often takes several rounds, users should be able to return to it easily—also from the product recommendations.
Main Userflow
The wireframes reflect the key moments in the user journey: A landing page to directly start the process, followed by the matching page where users explore and refine outfit preferences, and finally the results page showing the product recommendations.
Landing
Matching
Results
Explorations & Variants
Reactions
Every step of the way, we showed screens and working prototypes to potential users—always keeping their tech background and understanding in mind. From the beginning, the feedback was great—people really responded to both the idea and the way it was built.
”It feels like Tinder”
“I want to match, its really fun”
“Me and my girls will use
the hell out of this”
But not everything was
perfect from the start.
“How long do I need to match?”
A small hint
During testing, we noticed that some users didn’t realize they could view matching products right after making a selection. To help with this, we added a small hint to the bottom bar for new users. After that change, the issue didn’t come up again in later tests.
"Much better" :)
