AI assistant for product design
Project Overview
Kami is your AI co-pilot for product design, guiding you from research to design without tool overload, messy data, or creative burnout.
Project Type
Class Project (HCI for Interaction Design)
Timeline
Jan 2025 - Apr 2025
Role
Lead Product Designer, User Researcher, and Prototyper
Team
Clayton Lin, George Kim, Gabriena Feng
Problem
Product designers switch between too many tools and spend too much time on manual tasks
Goal
Enable designers to work in one platform and use AI to improve workflow efficiency.
Key Features
Here are our final solutions for each core flow. They solve key pain points in product design and create a smooth, end-to-end workflow.
1
Research with Kami
Researches your topic and turns the findings into clear, well-designed summaries.
2
Brainstorm with Kami
Generates diverse idea directions based on your research data.
3
Design with Kami
Generates the full set of screen designs for an idea.
Turn wireframes into polished hi-fi mockups with clarity and consistency.
Adapts UI styles based on your preferences while preserving the core experience.
4
Prototype with Kami
Turn your design into a working app
4
Test with Kami
Tests multiple design versions and tells you which one works better for your users.
Secondary Research
We started with market research, we focused on two main categories: UI/UX design tools and AI-powered design tools. Both markets are experiencing rapid growth in the coming years.
At the same time, more product designers are turning to AI tools to streamline their workflow, moving beyond traditional software like Figma and Sketch.
Competitor Analysis
To identify gaps in the current landscape, we tested 10 leading AI tools across two domains: research and UI design.
Competitor's Weaknesses
No tools support both research and design
AI designs lack user and research data support
AI design tools generate one single design at a time
Kami's Opportunities
All-in-one workflow, connecting research, design, prototyping, and testing.
Designs based on research, leading to more informed and relevant results.
Explore multiple options before choosing one, supporting creativity.
Primary Research
To better understand designers’ current workflows, challenges, and attitudes toward AI tools, we conducted 10 in-depth interviews and collected 55 questionnaire responses.
Participants included designers from big tech companies, startups, and universities. .
70%
find it time-consuming to synthesize large amounts of data
88%
think AI designs lack variety and creativity
68%
editing AI designs takes a long time
84%
think AI output quality is unreliable for design.
Design Goal
Based on the insights we gathered from designers, we identified clear needs across research, ideation, design, prototyping, and testing. Our goal was to streamline this entire workflow, making it faster, easier.
Gather and synthesize user insights
Generate multiple ideas backed by real user needs
Help designers create creative ideas quickly
Build prototypes with minimal effort
Iterate quickly with AI-powered feedback
Low-Fidelity Wireframes
The first version is divided into three sections: a layer panel on the left, the main design canvas in the center, and an AI panel on the right. In this version, we included only the essential features to ensure the interface is clean and easy to navigate.
Wireframe of the Design Canvas Page
Based on this design canvas page design, we built three user flows into a clickable wireframe prototype: initiating AI interaction, using AI for research, and generating designs with AI.
Usibility Test
We tested the three flows with over 30 designers from diverse backgrounds, gathered their feedback, and iterated on the design. This testing process went through more than three rounds.
Page for New Project
This is the screen shown after the user creates a new file. In the first version, the AI panel was on the right. Designers were confused and didn’t know what to do.
We changed it to a single input field in the center, making the prompt clear and reducing confusion.
Before
After
Workspace Page
At first, we wanted designers to change everything by talking to the AI with natural-language prompts. But during testing, we saw that this was not very clear. The AI sometimes could not understand what designers really wanted.
To fix this, we added the manual Properties Panel back on the right and moved the AI panel to the left. This made it easier for designers to edit design.
Before
After
Final Design
After multiple rounds of testing and iteration, we arrived at a streamlined layout that supports fast, flexible, and focused design work.
Assets & AI Panel
A transparent, chat-based AI partner that shows every step and supports fast, flexible iteration.
Clicking a tag takes the user to its corresponding design.
Properties Panel
All AI outputs remain fully customizable, giving designers complete control to tweak and perfect layouts effortlessly.
Prompt Bar
A simple entry point where designers can ask Kami to generate, upload, or style anything. Quick-start suggestions below help users begin right away and show what they can do on the platform.
