Search+
Play some "on theme" music while you scroll :)
0:00/1:34
ESTIMATED READING TIME
5 mins
Team
Shaina Desroches
Colin Mendoza
Ankita Narayan
Yuwei Huang
Adela Milkes
ROLE
UX Designer
UX Researcher
SKILLS
User Research
Artificial Intelligence
Visual design
TIMELINE
4 weeks
Project Overview
The 'Message' That Got Away (cue Katy Perry)
“I swear I texted you that”, has become my go-to excuse when I can’t find something in iMessage.
The Challenge
We Remember Context, but Our Phones Only Hear Keywords.
Looking for an old message in iMessage often feels like digging through a messy attic. You know it’s in there somewhere, but finding it requires endless scrolling, half-remembered keywords, and mounting frustration. The iOS Messages search depends on exact keywords, which doesn’t reflect how people naturally recall conversations.
Fun example that popped up on my TikTok feed! :)
Problem Statement
User Research
User Insights
We surveyed 20 iPhone users between the ages of 18–50 to understand how they search for old messages and manage information within Apple’s native Messages app.
People who have given up trying to find a message after multiple failed search attempts
0%
0%
People who screenshot or pin texts as a backup system
0%
0%
Users remember context, not keywords
Most participants said they rarely recall the exact words they used in a conversation. Instead, they remember the topic, person, or timing of the exchange.
“the restaurant my friend sent last month”
Users want AI to understand real-world language
Many said they would want the AI to recognize slang, shorthand, and cultural references, not just formal English.
“If I type something like ‘SoFlo,’ it should know I mean South Florida.”
Privacy matters (wait is Apple reading my messages?)
Several participants said they were excited about smarter search but immediately asked how private it would be.
“If it’s using the same intelligence as Siri or Photos Memories, then yeah, I'd actually use it.”
User Personas
The Over-Organizer:
Olivia (37, Marketing Manager)
Core needs
Wants AI to group messages by topics (e.g. “wedding planning,” “travel ideas”).
Needs quick access to photos, receipts, and links shared months ago.
Values smart filters that surface relevant details automatically.
Frustrations
Wastes time scrolling through mixed media and unrelated results.
Finds Apple’s current search too rigid for her multitasking workflow.
The Meme Archivist:
Omari (22, International Student)
Core needs
Search that handles code-switching, slang, and mixed language phrases.
Visual search results: quick previews of memes, photos, GIFs.
Wants a clean, fast experience, less typing, more results.
Frustrations
Endless scrolling breaks up conversation flow.
Has to screenshot messages so they don't get lost
Key Features
@prianca
@nandi
feedback loop
guided prompt
Native design builds trust
=
Use Apple Intelligence branding and components from their design system to make the experience native to their new AI features.
Feedback transparency
=
The design must include a clear visual feedback loop showing the user how the AI interpreted their query (e.g., "Searching for: [Keywords: Pizza, Link, Last Friday]").
Context not keywords
=
The feature uses semantic search, translating the user's natural language (including slang and abbreviations) into concepts to index conversations.
Ideation and Solution
Integrating Natural Language Processing (NLP)
Natural Language Processing (NLP) is a branch of artificial intelligence that enables computers to understand and interpret human language. In my case study, I applied NLP to explore how Apple could make message search more conversational and intuitive.
Instead of relying on exact keywords, NLP allows the system to recognize intent and context, so a user could type “the photo my friend sent at the beach” and still find it. By designing with NLP in mind, I aimed to make Apple’s message search feel more human, helping users find memories the same way they naturally think and speak.
A Quick Journey Map
Hi-fi Prototype
Emma can’t remember which Mexican restaurant she went to with friends last week, but she knows the name’s buried in their messages from Friday, so she uses Search+ to find it.
Access the prototype here!
Guided Prompts:
Subtle placeholder text like “Describe your conversation…” encourages discovery
Seamless Integration
Natural-language input built into the existing iOS Search Bar for a familiar feel.
Smart Results
Displays related conversations Emma can quickly tap to find what she’s looking for.
Apple Branding
Uses Apple Intelligence logo and gradient colors for a cohesive, native experience.
Transparent Feedback:
Shows how the AI interprets user queries for clarity and trust.
Reflections
Metrics of Success
Evaluating Apple Intelligence through user impact
We identified metrics that could measure the impact of the contextual search, including query success rate, time to find messages, and feature adoption. Tracking these would help us understand how well the AI interprets natural language, how efficiently users can locate messages, and how readily the new feature is embraced. These metrics guide design decisions by highlighting areas for improvement and ensuring the search experience remains intuitive and valuable for users.
Query Success Rate
Percentage of natural language queries that result in a user clicking on a suggested conversation.
Time to Find
Average time taken to find a specific message using the new feature vs. the old keyword-only search.
Feature Adoption
Percentage of users who use the new contextual search field over the standard search
What I Learned
Working within the iOS design system, combining AI, and piecing everything together during late nights at the library (fueled by a very large pizza) taught me a lot about designing tech that actually makes life easier. I learned that the real magic of AI isn’t about showing off intelligence,
it’s about simplifying everyday tasks, giving users clear feedback so they always know what’s happening, and creating moments that just work without them even thinking about it.
GatorRyde
A simple way for students to connect and plan long-distance trips together
ESTIMATED READING TIME
5 mins
ROLE
UX Designer
UX Resaercher
SKILLS
User Research
Artificial Intelligence
Visual design
TIMELINE
4 Weeks
TEAM
Shaina Desroches
Colin Mendoza
Ankita Narayan
Yuwei Huang
Adela Milkes
Project Overview
The 'Message' That Got Away (cue Katy Perry)
“I swear I texted you that” has become my go-to excuse when I can’t find something in iMessage.
The Challenge
We Remember Context, but Our Phones Only Hear Keywords.
Looking for an old message in iMessage often feels like digging through a messy attic, you know it’s in there somewhere, but finding it means endless scrolling, half-remembered keywords, and mounting frustration. The iOS Messages search relies on exact keywords, which doesn’t reflect how people naturally remember conversations.
Fun example that popped up on my TikTok feed! :)
Problem Statement
USER RESEARCH
User Insights
We surveyed 20 iPhone users between the ages of 18–50 to understand how they search for old messages and manage information within Apple’s native Messages app.
67%
said they’ve given up trying to find a message after multiple failed search attempts.
58%
admitted they screenshot or pin texts as a backup system
Users remember context not keywords
Most participants said they rarely recall the exact words they used in a conversation. Instead, they remember the topic, person, or timing of the exchange.
“the restaurant my friend sent last month”
Users want AI to understand real-world language
Many said they would want the AI to recognize slang, shorthand, and cultural references, not just formal English.
“If I type something like ‘SoFlo,’ it should know I mean South Florida.”
Privacy matters (wait is Apple reading my messages?)
Several participants said they were excited about smarter search but immediately asked how private it would be.
“If it’s using the same intelligence as Siri or Photos Memories, then yeah, I'd actually use it.”
The Over-Organizer:
Olivia (37, Marketing Manager)
Core needs
Wants AI to group messages by topics (e.g. “wedding planning,” “travel ideas”).
Needs quick access to photos, receipts, and links shared months ago.
Values smart filters that surface relevant details automatically.
Frustrations
Wastes time scrolling through mixed media and unrelated results.
Finds Apple’s current search too rigid for her multitasking workflow.
The Meme Archivist:
Omari (22, International Student)
Core needs
Search that handles code-switching, slang, and mixed language phrases.
Visual search results: quick previews of memes, photos, GIFs.
Wants a clean, fast experience, less typing, more results.
Frustrations
Endless scrolling breaks up conversation flow.
Has to screenshot messages so they don't get lost
The Over-Organizer:
Olivia (37, Marketing Manager)
Core needs
Wants AI to group messages by topics (e.g. “wedding planning,” “travel ideas”).
Needs quick access to photos, receipts, and links shared months ago.
Values smart filters that surface relevant details automatically.
Frustrations
Wastes time scrolling through mixed media and unrelated results.
Finds Apple’s current search too rigid for her multitasking workflow.
The Meme Archivist:
Omari (22, International Student)
Core needs
Search that handles code-switching, slang, and mixed language phrases.
Visual search results: quick previews of memes, photos, GIFs.
Wants a clean, fast experience, less typing, more results.
Frustrations
Endless scrolling breaks up conversation flow.
Has to screenshot messages so they don't get lost
The Over-Organizer:
Olivia (37, Marketing Manager)
Core needs
Wants AI to group messages by topics (e.g. “wedding planning,” “travel ideas”).
Needs quick access to photos, receipts, and links shared months ago.
Values smart filters that surface relevant details automatically.
Frustrations
Wastes time scrolling through mixed media and unrelated results.
Finds Apple’s current search too rigid for her multitasking workflow.
The Meme Archivist:
Omari (22, International Student)
Core needs
Search that handles code-switching, slang, and mixed language phrases.
Visual search results: quick previews of memes, photos, GIFs.
Wants a clean, fast experience, less typing, more results.
Frustrations
Endless scrolling breaks up conversation flow.
Has to screenshot messages so they don't get lost
The Over-Organizer:
Olivia (37, Marketing Manager)
Core needs
Wants AI to group messages by topics (e.g. “wedding planning,” “travel ideas”).
Needs quick access to photos, receipts, and links shared months ago.
Values smart filters that surface relevant details automatically.
Frustrations
Wastes time scrolling through mixed media and unrelated results.
Finds Apple’s current search too rigid for her multitasking workflow.
The Meme Archivist:
Omari (22, International Student)
Core needs
Search that handles code-switching, slang, and mixed language phrases.
Visual search results: quick previews of memes, photos, GIFs.
Wants a clean, fast experience, less typing, more results.
Frustrations
Endless scrolling breaks up conversation flow.
Has to screenshot messages so they don't get lost
Key Features
Native deisgn builds trust
=
Use Apple Intelligence branding and components from their design system to make the experience native to their new AI features.
Feedback transparency
=
The design must include a clear visual feedback loop showing the user how the AI interpreted their query (e.g., "Searching for: [Keywords: Pizza, Link, Last Friday]").
Context not keywords
=
The feature uses semantic search, translating the user's natural language (including slang and abbreviations) into concepts to index conversations.
Hi-fi Prototype
Emma can’t remember which Mexican restaurant she went to with friends last week, but she knows the name’s buried in their messages from Friday, so she uses Search+ to find it.
Access the prototype here!
Reflections
Metrics of Success
To measure the success of the feature, we would track:
Query Success Rate
Percentage of natural language queries that result in a user clicking on a suggested conversation.
Time to Find
Average time taken to find a specific message using the new feature vs. the old keyword-only search.
Feature Adoption
Percentage of users who use the new contextual search field over the standard search
What I Learned
Working within the iOS design system, combining AI, and piecing everything together during late nights at the library (fueled by a very large pizza) taught me a lot about designing tech that actually makes life easier. I learned that the real magic of AI isn’t about showing off intelligence,
it’s about simplifying everyday tasks, giving users clear feedback so they always know what’s happening, and creating moments that just work without them even thinking about it.