Work

About

Resume

Playground

Contact

Mobility Ambassador

Launch Project by King County Metro

AI | Conversational Design | Full-stack To C Project
An AI-powered transit assistant designed to provide accessible, real-time, and personalized support.

Timeline

2024.10-2025.3

Role

Product Designer

User Researcher
Visual Designer

Contribution

-UIUX design, Graphic design, Branding Design, Motion Design

-Prototyping iteration & validation through usability test & stakeholder communication

-Prompt Design

-AI Use Case Definition

-User Research

Tools

Figma

Adobe Effect
Slack

Methods

-AI Integration & Usability: Designed AI interactions and prompts by defining use cases, applying cognitive research and ethical principles, and iterating based on testing and technical constraints

-Design & Collaboration: Created prototypes, visuals, and interaction flows while aligning with the team on a cohesive design system. Worked closely with sponsors to balance stakeholder goals and technical constraints.

Understand Stakeholder

King County Metro aims to promote its official app, reduce customer service overload, and better support underserved groups like seniors, people with disabilities, and non-native speakers.

-Commuters and first-time visitors have different needs depending on trip purpose and familiarity.

-During transfers, riders face app overload and must quickly decide between various tools and transportation options.

Design Considerations

Lead User Research

Brainstorming

Help team understand user

How might we design a user-friendly Al concierge that enables smooth cross-transit system experiences for different users and under different scenario?

Design question iterated for four times based on sponsor’s feedback and research.

Pain Points

Lack Awareness of Existing Tools
(Visitors)

Over 20 local transit tools offer real-time alerts and accessibility info, yet 87% of first-time visitors don’t know they exist.

Dynamic Needs
(Local's Familiarity and Trip Type)

Users’ priorities change based on trip type and system familiarity—visitors need app guidance, while commuters want real-time updates.

High Support Demand

(Vulnerable Groups)

67% of inquiries come from riders with disabilities, seniors, or non-native speakers—highlighting the need for inclusive design.

Design Solution

Personalization

Customized Based on User Profile

Trip Specified Recommendation

Real time AI suggestions catering to different trip type

Accessible & Multilingual Design

Added voice and language options to support a wider range of users.

Progressive Profiling

How should I design data collection to reduce drop-off and build user trust?

Design Consideration:
By splitting data collection into two stages, I minimized cognitive load upfront while building enough context for smarter support later. This approach respects user trust, avoids overwhelming first-time users, and allows more relevant, timely interactions as needs evolve.

User Journey Stages

How should I design for long-term engagement?

Contextual Trip Prompts

What should be questioned to understand user’s current scenario?

I designed trip-based prompt suggestions tailored to each user scenario, helping the AI better understand the trip context and generate relevant, visualized responses.

“Here are local apps!”

You Prioritize time!!!
So I list out time, cost and walking distance for you!

Are you going to your office by bus as usual?
Hold On! A bus stop will change along your route!

VUI

Prompt Structure Design

Technical MVP Development

Design consideration:
Instead of relying solely on a full conversational chatbot, I used progressive input and scenario-based prompt suggestions to guide users at the right time. This helped reduce friction, improve task flow, and enabled the AI to better understand trip context for generating relevant, visualized responses.

Iteration based on usability testing

The design went through five iterations, guided by MVP check-ins with the sponsor, usability testing with 8 users, technical feasibility reviews, and feedback from domain experts.

Reflection:

This process taught me the importance of balancing user needs, technical constraints, and stakeholder goals. Iterating with real feedback helped me think critically, prioritize effectively, and stay adaptable in a fast-changing context.

Work under limited resource

With one engineer, I built a lightweight design system and clear docs to speed up handoff and development.

Reflection:

This experience taught me to think critically about scalability and communication—design isn’t just about visuals, but about enabling smooth collaboration under constraints.