March - May 2026

Color.

Swipe to build your blend profile

Food Blend

Context

Beli is an app that allows users to share food recommendations with friends, personalizing the food experience and building a community among foodies. As someone who loves venturing new foods, I wanted to reduce decision fatigue when deciding a place to eat. This idea was a part of an independent case study in my Digital Product Design class at Cornell.

Role

Product Designer

Timeline

Feb - May 2026 (4 months)

Skills

UX Research, Prototyping, Figma

Team

Just myself :]

PROBLEM + RESEARCH

How does Beli help people decide a place to eat?

After interviewing four individuals, I was able to get a better idea as to how Beli is used and how food discovery currently looks like.

"After receiving a notification from my friend, I opened the app to browse and rank the restaurant we went to together."
"When I want to eat with my friends, I use beli and surf the app through the feed to look for recommendations."
"Beli encourages me to try new places to eat through the school leaderboard and ranking system."

Insights from the interview:

Friend's activity boosts others' engagement.

Promotes food exploration in metropolitan areas through competition

Trusted reviews help decide where to eat

Revisiting the People Problem

When I am deciding on a place to eat, I want to choose a restaurant based on personalized recommendations, so I can confidently choose a place that I will enjoy. But this is hard because:

  1. 1It is hard to connect personalized recommendation system with friend's activity to make a decision
  2. 2Existing solutions has a place for multiple user input without a specific direction in where to take them

Market Research

How do existing products provide recommendations?

Yelp provides anonymous reviews with details for ratings and specific notes from random users. Google Maps provides recommendations mostly from where the user is located and they’d have to search it up. Both of these experiences are isolated, focusing on getting reviews or navigating to the place.

Spotify blend provide recommendations through themed-playlists or shared playlists with friends. Many of the recommended songs are based on the user’s current listening experience. Friends’ activity is also used to build the shared playlists.

Brainstorming

How do we maintain and prioritize trust while streamlining the process of transforming personalized recommendation to meaningful decisions?

From the research, I centered my solutions around answering this question. I identified three opportunity areas to brainstorm more specific solutions, coming up with two specific solutions in each of the spaces — six solutions total.

1

Friend's Data

  • Remix of friends and users' activity user to create a list of recommendations
  • Food Blend similar to Spotify Blend
2

Decision Making

  • Q&A to break down the decision-making process
  • User Tags to categorize user's eating activity to choose similar places
3

Feed Navigation and Recommendations

  • Messaging System for receiving recommendations
  • Additional Filters to current recommendation system

After completed SWOT and feasibility& impact analysis of each solution, I decided to focus on the Food Blend and Plate Off feature where users can compare recommendations that are compatible to come to a decision. Through Food Blend, the user invites their friends to generate a list. Plate Off allows users to compare each of the restaurants by swiping left or right to generate a ranked list.

Visualizing the solution...

Low fidelity wireframe sketches of the Food Blend flow
Low fidelity sketches
Information architecture diagram
Information architecture
Medium fidelity screen iterations
Medium fidelity iterations

Iterating

Exploration and design decisions

Design iteration comparisons for entry point, card swiping, and friend selection. Final Flow label appears at the bottom of this section per Figma.

User Testing

Testing our solution.

After user feedback, I revisited and made changes to my designs.

Swipe profile and restaurant detail screens from user testing
Friend profile and guides screens showing blend access points
Blend results list with ranked restaurants and preference tags

The Final Product

In the Future

If I had more time...

Group Setting

Expanding this feature to help make decisions for parties larger than 2

Messaging

A message system would reduce the friction in creating blends without leaving the app

Gamifying

Adding themes to blends or categorizes to further encourage food exploration

Reflection

What I learned.

  1. 1

    Continue iterating! There were moments where I was stuck when designing, but creating more iterations led to new directions of the project.

  2. 2

    Adapt to changes — When iterating and designing my solution, Beli had developed new features that addressed parts of my problem space. I had to make revisions to ensure that my solution did not create any redundant features. Although the design process can sometimes be unpredictable, it has pushed me to be more creative.

  3. 3

    User empathy — It was important for me to recognize that the problem I identified early on did not encompass the full user experience. By revisiting my people problem, I create specific solutions centered around the user to design product with intention.