Time
2023.10 - 2024.06
My Role
Lead Product Designer
UX Researcher
Team
CEO, PM/ PO,
4 x Designers
3 x Dev Team
Problem we want to solve
Always find yourself jumping between different apps to find saved articles, images, PDFs, notes? It's frustrating and time-consuming.
Our solution
A platform where you can save all your digital content in one place. It understand your content, organize files automatically, and retrieve what you need at no time.
Target Users
People who rely heavily on digital content, from researchers and creators to business professionals and students.
Chanllenge 1:
Core Functions, from Research to Prototyping
What are the key user behaviors and pains during file management? And what are the tactics?
We conducted stakeholder interviews to indentify them.
User Behavior
User Painpoints
Product Tactic
📂Collect
"Great info, but where to save it?"
Drag and drop to save on AutoMind
🗃️Organize
"Oh I just named 10 folders!!"
Smart tags for each document
🧠 Digest
"Too lengthy I can't read!"
Chatbot that use GPT-4 API
🧐 Retrieve
"Oops, where can I find that thingy?"
Relate search use smart tags
We quickly drafted some wireframes of the 4 key scenarios
📂Collect:
Drag and drop to save on AutoMind
🗃️Organize:
Smart tags for each document
🧠 Digest:
Chatbot that use GPT-4 API
🧐 Retrieve: Relate search use smart tags
🤯Market Reality: Competitors Already Doing Well in the Essential Functions!
Direct
Trickle AI
MyMind
Cubox
Indirect
ChatGPT
Perplexity
Monica
What Makes Our Product Stand Out?
I brought this question to Product Manager, and he revealed that in our product vision, there is an unimplemented "Copilot" concept, designed to provide users with inspirational ideas.
📂Collect
🗃️Organize
🧠 Digest
🧐 Retrieve
+
👩🏻✈️✈️
Copilot AI feature?
I realized the significant business opportunity here:
The Copilot AI feature can be our unique value proposition in the market!
Challenge 2:
Unlock the Potential of Copilot AI feature
HMW Design and incorporate the Copilot AI feature, to transform AutoMind into an inspirational platform outstands the market?
I firstly draw a diagram to mapping out the strategies and tactics of Copilot AI:
I conducted design team meeting to explore AI-generated content concepts:
Concept 1:
MindMap generator
AI can automatically detect documents that has similar topics, and generate mindmap for better digestion
Concept 2:
Weekly email of inspiration report
Users receive a compilation of inspirational content based on user activity and set preferences at daily or weekly.
However, I got the push back from PM:
“No, these are NOT what we looking for”
We identified the previous solutions were too passive,
failing to actively engage users in their current tasks.
I conducted a design workshop to realign Copilot AI principles:
Real-time inspiration
Interactive with users
Simple and Intuitive
Applying these principles, I worked with a designer to brainstorm scenarios, where the Copilot AI create cards based on users contents and needs.
📚 Scenario 1
AI created study plan for users who want to be Data Scientists
💚 Scenario 2
AI made an aesthetic collage for users' home decor ideas
📋 Scenario 3
AI made an automatic to-do list based on user's content
🧘🏻♀️ Scenario 4
AI created a meditation music list for user to relax
The team agreed that these inspirational cards captured the Copilot AI principles!
To communicate with the engineering teams, I designed the AI logic system, translated the conceptual scenarios into a concrete framework
Here's a User Case Example:
Input User Files:
Audio recordings of classroom lectures & discussions
Copilot AI Topic Define:
Knowledge & Efficiency
AI Role:
Learning Assistant & Efficiency Accelerator
AI Actions:
Generate flashcards;
Create detailed study schedules
Output Inspirational Cards:
PDF flashcard set
List of study materials
👍 I presented my solutions to the team, and everyone was absolutely thrilled!
🚀This feature drove a huge
36% boost📈 in subscription intention from our user survey!
💰And brought us $1.8 Million in VC funding!
✨Copilot AI Panel Design
AI-generated cards loaded √
AI-generated cards Loading…
Intro Banner for first-time users
Inspiration card detail page
Challenge 3:
Optimizing Card-Based Interface
We designed high-fidelity card types and found that, inevitably, the cards can't be within the same height.
Image
Audio
Website
Video
Text
To-do
And Varying-height might bring challenges in scanning and locating documents.
Fixed-height
Varying-height
Fixed-height or varying-height, which is better?
I conducted desk research on card-based design:
We also made a usability test with 7 participants, designed qualitative and quantitative questions and tests, comparing these two layout options.
And here's the feedbacks:
5 out of 7 users identify content types 34% quicker in the varying-height layout.
3 out of 7 Users mentioned feeling slightly overwhelmed by the non-uniform layout initially.
6 out of 7 users preferred the varying-height layout after becoming familiar with it.
Based on research finding, we opted for a
Varying-height design to balance content flexibility with visual appeal.
To reduce users initial overwhelm, we made a few actions to refined card layouts.
Developed coherent padding and layout patterns
Established height rules for similar content types
✨Final Interface Design Balancing Creativity and Efficiency
Card cascading
Detailed card pages displaying more information
Design Handoff & Reflection
Home page + Inspiration Handoff (Dark mode)
Home page + Inspiration Handoff (Light mode)
Design System (Partial)
Integrated the feedback , I collaborated with a designer to implemented responsive design, and got the 👍👍👍 from PM and the develop team!
I led the Design Inspection Process
Create and manage inspection documentation, maintain the implementation status of design elements.
Hold weekly meetings to discuss implementation challenges, provide clarifications and additional details.
Conduct design reviews, and iterate on designs based on technical constraints.
Reflections: Navigating a Rapid Tech Landscape
🌟 Innovation is challenging but rewarding
I led the creation of an "inspiration panel" when ideas were scarce. Despite the difficulty of thinking expansively, this innovative approach led to breakthrough concepts.
🤼🏽♀️ Monitor competitors closely
I continuously tracked competitors, analyzing their new features, and relevance to our model. This vigilance kept us ahead in the market.
⚡ Prioritize ruthlessly in startups
In the fast-paced startup world, time management is crucial. Deciding on MVP features versus future developments required strategic planning and resource discussions.