Perplexity is an emerging AI-powered search engine with 15M+ users, designed to deliver detailed, reliable answers. However, while it's actively growing, a lot of students still don't really know what it is.
I worked with Perplexity to reimagine how Perplexity could better serve academic needs and improve student engagement.
MY ROLE
Designing a Highlight-and-Save Feature for Seamless Workflows
FEATURE RECOMMENDATION
Helping Students Research and Write Essays More Efficiently
I designed a highlight-and-save feature that lets users capture text directly from outside sources and store it in their personal library (Spaces).
✏ᝰ Students can highlight key pieces of texts, save them in Spaces, and generate essays with embedded quotes.
THE RESULT
Starting From Scratch: How did I narrow down the problem space?
USER RESEARCH
Students + AI Tools: Diverse Uses, Different Goals
In order to gain product feedback on Perplexity and other competitors, we surveyed students at UCLA across 4 user types. With 135+ survey respondents and 30+ interviews across 35+ STEM & Humanities majors, we discovered that:
TEAM BRAINSTORM & IDEATION
Based on data, we identified themes and brainstormed a range of features, bringing them to discover which resonated most.
FEATURE OWNERSHIP
I took ownership over tackling the problem of students wasting time jumping between AI tools and academic workflows.
After researching and talking to students, they mentioned that they liked the annotating feature and would find a context saving feature helpful. I realized Spaces in Perplexity are underutilized (based on data, only 4% of students have tried the feature), but they allow users to create and categorize their personal folders.
What is Spaces?
Spaces - A personal library with collaborative folders where users can save and organize articles and texts for easier access and ongoing research.
SHARPENING FOCUS ON A CORE GOAL
USER STORIES
Discovering User's Frustrations with Tab Switching
With this goal in mind, I interviewed more students to learn about their views on context switching. 90% of students spend 1-7 hours weekly on research, but constantly have to switch contexts between research, citation tools, and LMS submission.
COMPETITIVE ANALYSIS
Uncovering the Gap in Direct Insight Capture
To validate the pain points users are facing, I analyzed AI tools to understand how they capture content and organize workflows. While tools offer AI generation capabilities, there is currently no way to save insights directly without switching between tabs.
This absence signaled an opportunity: by solving what others haven’t, this new feature could differentiate the product and deliver immediate value to higher education.
Limitations of Other AI Tools
• No in-context saving: Most tools don’t allow users to highlight and save text directly
• Lack of organization: There’s no built-in way to group or revisit saved insights
• Heavy reliance on copy-paste: Users have to switch to external tools to organize their findings
• Not designed for research workflows: Not many tools are tailored for knowledge building
Ideation, Design, Iterate, Test, and Repeat
IDEATION
Initial Feature Exploration
Given the constraint of time, I sketched out many low-fidelity concepts to visualize how to integrate the feature into Perplexity.
USABILITY TESTING
Discovering New Perspectives and Iterating
Through 5 rounds of designing and iterating, I interviewed a diverse group of users - including those who had never used Perplexity and experienced Perplexity users - to ensure the design is intuitive for both new and returning users.
Key Change #1
90% of users preferred the inline dropdown over a popup for its speed. It lets them highlight, save, and keep reading without interruption, while also adding to a new Space without leaving the page.
Key Change #2
I explored different visual styles for how saved quotes would appear. Through user testing, I found that users preferred a cleaner look.
Key Change #3
Some users mentioned they would like to see a confirmation after adding text to a Space. To address this, I introduced a new pop-up and tested different placements. I ultimately positioned it here, as it felt most intuitive during later rounds of user testing.
FINAL PROTOTYPE
Snippet: Seamlessly save your key insights from articles into Spaces
Add Article Quotes to New Folders in Spaces
Select an article and highlight important texts and create a new Spaces folder and store the texts.
Write Essays with Saved Quotes
Type into an essay topic and generate essays with quotes embedded directly in your Spaces folder.
Final Testing Metrics
NEXT STEPS
If I had more time…
I would:
• Refine interactions: Explore additional ways to streamline steps and design micro-interactions that make the feature feel faster
• Expand highlighting: Continue developing the highlighting tool into an annotation system, enabling students to add notes and connections while reading
• Prototype other concepts: Build functional prototypes of features we brainstormed and validate them through usability testing
TAKEAWAYS
Good design reduces cognitive load.
Users are often juggling multiple tools and tasks at the same time — my job as a designer is to make the next action intuitive and frictionless. When flow is uninterrupted, engagement follows naturally.
Cross-functional teamwork and collaboration drive product clarity.
Working closely with PMs and PMMs helped align design decisions with product goals, ensuring the every feature we created wasn’t just functional — but also launched with the right purpose.
Test. Learn. Iterate. Repeat.
Through rounds of usability testing and talking to users, I saw firsthand how tiny interaction tweaks — like confirmation states or button placement — made the difference between hesitation and intuitive use.