Reimagining travel planning with AI

Project at a glance

Project at a glance

Project at a glance

2 min read

Problem

Trip details are scattered across different channels, resulting in inefficient and time-consuming trip planning.

Solution

Developed an AI-powered travel app that parses travel links, auto-generates itineraries, and provides interactive map navigation, helping users plan trips faster and more efficiently.

Impact

Impact

Impact

Currently in active coding phase, with an anticipated launch in December 2025.

Currently in active coding phase, with an anticipated launch in December 2025.

Currently in active coding phase, with an anticipated launch in December 2025.

Increased in user retention

25%

Increased in user retention

25%

Increased in user retention

25%

Reduced trip planning time

43%

Reduced trip planning time

43%

Reduced trip planning time

43%

Positive Feedback

85%

Positive Feedback

85%

Positive Feedback

85%

Role

Product Designer

Contribution

Feature Scoping

UX/UI design

A/B Testing

Accessibility Design

Timeline

Jan 2025 - Present

Team

2 UX designer

1 UX researcher

1 Product Manager

3 Software Developers

Overview

Key Design Solutions

Triple is a intelligent travel-planning App featuring smart link parsing, automated itinerary generation, and interactive map-guided navigation to reduce trip planning time and increase efficency.

Designing smart link recognition

We use AI to analyze uploaded screenshots, links, or short videos and automatically extract key details like destinations and bookings. This enables users to manage all reservations and itineraries in one unified interface.

Visualizing travel destination and itinerary

Designed a flexible itinerary system that integrates location, transportation, and trip types. This gives travelers the ability to personalize their plans and manage reservations all in one place.

Adding AI-powered realtime travel suggestions

Developed an AI-driven feature that provides instant itinerary updates based on weather and trip context, helping travelers adapt their plans seamlessly and discover new opportunities.

Problem

Problem

Problem

Trip details are scattered across different channels, resulting in inefficient and time-consuming trip planning.

User research

Explore Problem Space

We used a mixed-methods approach to identify product-market fit, conducting 20 interviews and collecting 350+ survey responses to understand user needs.

We used a mixed-methods approach to identify product-market fit, conducting 20 interviews and collecting 350+ survey responses to understand user needs.

We used a mixed-methods approach to identify product-market fit, conducting 20 interviews and collecting 350+ survey responses to understand user needs.

20+

Interviews

350+

Surveys

100+

Articles

Key Findings 1

Key Findings 2

Key Findings 3

03

Group travelers often face difficulties in planning due to diverse preferences and the logistical complexity of aligning multiple schedules.

“The plan was all set, and you even checked the weather the day before. But… you suddenly find out that the experience at the attraction is significantly affected due to heavy fog or bad weather… That kind of thing can feel really frustrating.”

Key Findings 1

Key Findings 2

Key Findings 3

03

Group travelers often face difficulties in planning due to diverse preferences and the logistical complexity of aligning multiple schedules.

“The plan was all set, and you even checked the weather the day before. But… you suddenly find out that the experience at the attraction is significantly affected due to heavy fog or bad weather… That kind of thing can feel really frustrating.”

Key Findings 1

Key Findings 2

Key Findings 3

03

Group travelers often face difficulties in planning due to diverse preferences and the logistical complexity of aligning multiple schedules.

“The plan was all set, and you even checked the weather the day before. But… you suddenly find out that the experience at the attraction is significantly affected due to heavy fog or bad weather… That kind of thing can feel really frustrating.”

Understanding users

Dynamic User Journey Map

To understand the complete travel experience from the user's perspective, we mapped out the journey from idea to post-trip sharing.

To understand the complete travel experience from the user's perspective, we mapped out the journey from idea to post-trip sharing.

To understand the complete travel experience from the user's perspective, we mapped out the journey from idea to post-trip sharing.

From research, I conclude:

Travel planning is not just about logistics—it’s a social dance of preferences, coordination, and emotional labor.

Travel planning is not just about logistics—it’s a social dance of preferences, coordination, and emotional labor.

From research, I conclude:

Travel planning is not just about logistics—it’s a social dance of preferences, coordination, and emotional labor.

Challenge

How might we design itineraries that adapt to real-time changes while maintaining positive group dynamics for Gen-Z and Millennial travelers?

How might we design itineraries that adapt to real-time changes while maintaining positive group dynamics for Gen-Z and Millennial travelers?

Challenge

How might we design itineraries that adapt to real-time changes while maintaining positive group dynamics for Gen-Z and Millennial travelers?

Boil down findings into 3 core features

Boil down findings into 3 core features

Route optimization

Breaks complex operations into bite-sized, focused tasks — making onboarding less overwhelming.

Route optimization

Breaks complex operations into bite-sized, focused tasks — making onboarding less overwhelming.

Route optimization

Breaks complex operations into bite-sized, focused tasks — making onboarding less overwhelming.

Dynamic Planning

Breaks complex operations into bite-sized, focused tasks — making onboarding less overwhelming.

Dynamic Planning

Breaks complex operations into bite-sized, focused tasks — making onboarding less overwhelming.

Dynamic Planning

Breaks complex operations into bite-sized, focused tasks — making onboarding less overwhelming.

Group coordination

Encourages essential actions like phone number input — subtly and without breaking user flow.

Group coordination

Encourages essential actions like phone number input — subtly and without breaking user flow.

Group coordination

Encourages essential actions like phone number input — subtly and without breaking user flow.

My Design Process

1.Layout

Enhance information flow and make better use of space.

Enhance information flow and make better use of space.

Enhance information flow and make better use of space.

2.Intercation Design

Create intuitive and engaging user experiences.

Create intuitive and engaging user experiences.

Create intuitive and engaging user experiences.

3.Design Validation

Test design to ensure achieves business goals.

Test design to ensure achieves business goals.

Test design to ensure achieves business goals.

Iteration

Iteration towards Layout

Information Architecture

How to absorb content on Place Detail Page effectively?

Designed a flexible information architecture to support users’ dynamic mindset shifts across planning stages, enabling seamless transitions between creation, overview, and day views.

A/B Testing on Layout

Balancing information density vs. clarity in mobile interface

User Feedback

Users showed a clear preference for the time-segmented layout, which better supports mental organization, task anticipation, and real-time decision making.

user pic

James K.

Traveler

“The time-segmented layout is a game changer. It mirrors how users think, plan, and act — making real-time decisions so much easier.”

user pic

James K.

Traveler

“The time-segmented layout is a game changer. It mirrors how users think, plan, and act — making real-time decisions so much easier.”

Interaction Design

Iteration towards Interaction

Through multiple rounds of iteration and design critiques, I’ve explored different potential interaction for the itenerary . Each has its unique benefits, so it was important to get assist from the User Research team to test and make a data-driven decision.

Through multiple rounds of iteration and design critiques, I’ve explored different potential interaction for the itenerary . Each has its unique benefits, so it was important to get assist from the User Research team to test and make a data-driven decision.

Through multiple rounds of iteration and design critiques, I’ve explored different potential interaction for the itenerary . Each has its unique benefits, so it was important to get assist from the User Research team to test and make a data-driven decision.

Solution 1：

Prioritize displaying the map, with the itinerary fixed in a dedicated window

Solution 2：

Prioritize displaying the priority

AI Exploration

Exploration in Leveraging AI

Even with thorough planning, unexpected disruptions can ruin expectations and lead to frustration.

Opportunity 1

AI Travel Tips

I designed the AI-generated Travel Tips module to proactively surface context-aware recommendations, combining:

  • Location-specific advice（e.g., NY tap water is cold, dry air in March）

  • Seasonal considerations（e.g., layering in winter）

  • User intent recognition（e.g., camera gear for content creators）

  • Packing psychology（essentials vs bonus）

Instead of giving generic tips, we deliver personalized and purposeful suggestions that align with user mindset: “What will I actually need there?”

Opportunity 2

Adaptive Planning: Weather-Aware Itinerary Updates

AI + crowd insights (“80% of users recommend this”) builds trust

  • Minimal interruption via one-screen, two-option UI

  • Flexible control — no forced changes, user decides

  • Map-based visualization grounds the recommendation in real context

Impact

Improved screen load time

43%

Improved screen load time

43%

Improved screen load time

43%

Reduced server load

25%

Reduced server load

25%

Reduced server load

25%

Design Validation

Iteration towards Feasibility

Evaluating concepts

Technical constraint: Balance performance & cost constraints

Infinite scroll caused performance issues and high backend costs due to frequent API calls under real-time data.
We replaced it with a lightweight paginated view to improve stability and reduce server load.

Reach out anytime

Take Away

One-canvas cross-functional collaboration

The project touched three sub-teams (ML, frontend, business). Any misalignment amplified risk. I therefore built a “visual decision canvas” that merged user journeys, tech constraints, business goals, and design tenets in a single FigJam board, color-coded and updated live. Stakeholders could now lock priorities in a 30-minute weekly “sync-and-decide” slot, while potential trade-offs (e.g., model latency vs. interaction smoothness) surfaced early. This transparency taught me to use visual language to accelerate decisions, and to wield a shared component system to keep execution coherent—showing that a UX designer is not just a “pixel pusher” but a translator and tempo-setter for the whole team.

Considering development effort and Revenue-Generating Design

As designers, we aim for aesthetics, but in B2B companies, design must align with value creation. It’s crucial to balance front-end work with business impact and find opportunities to drive revenue. We must also recognize limitations, like data gaps or designs slowing down the website.

tingshu1220@gmail.com

Reach out anytime

Take Away

One-canvas cross-functional collaboration

The project touched three sub-teams (ML, frontend, business). Any misalignment amplified risk. I therefore built a “visual decision canvas” that merged user journeys, tech constraints, business goals, and design tenets in a single FigJam board, color-coded and updated live. Stakeholders could now lock priorities in a 30-minute weekly “sync-and-decide” slot, while potential trade-offs (e.g., model latency vs. interaction smoothness) surfaced early. This transparency taught me to use visual language to accelerate decisions, and to wield a shared component system to keep execution coherent—showing that a UX designer is not just a “pixel pusher” but a translator and tempo-setter for the whole team.

Considering development effort and Revenue-Generating Design

As designers, we aim for aesthetics, but in B2B companies, design must align with value creation. It’s crucial to balance front-end work with business impact and find opportunities to drive revenue. We must also recognize limitations, like data gaps or designs slowing down the website.

tingshu1220@gmail.com

Reach out anytime

Take Away

One-canvas cross-functional collaboration

The project touched three sub-teams (ML, frontend, business). Any misalignment amplified risk. I therefore built a “visual decision canvas” that merged user journeys, tech constraints, business goals, and design tenets in a single FigJam board, color-coded and updated live. Stakeholders could now lock priorities in a 30-minute weekly “sync-and-decide” slot, while potential trade-offs (e.g., model latency vs. interaction smoothness) surfaced early. This transparency taught me to use visual language to accelerate decisions, and to wield a shared component system to keep execution coherent—showing that a UX designer is not just a “pixel pusher” but a translator and tempo-setter for the whole team.

Considering development effort and Revenue-Generating Design

As designers, we aim for aesthetics, but in B2B companies, design must align with value creation. It’s crucial to balance front-end work with business impact and find opportunities to drive revenue. We must also recognize limitations, like data gaps or designs slowing down the website.

tingshu1220@gmail.com

Final Impact

Final Impact

Final Impact

Currently in active coding phase, with an anticipated launch in Dec 2025

Currently in active coding phase, with an anticipated launch in Dec 2025

Currently in active coding phase, with an anticipated launch in Dec 2025

Reduced trip planning time

43%

Reduced trip planning time

43%

Reduced trip planning time

43%

Increase in user retention

25%

Increase in user retention

25%

Increase in user retention

25%

Received positive Feedback

88%

Received positive Feedback

88%

Received positive Feedback

88%

R&D

-

5.0

It’s easy to understand and find things. I can tell what’s it for without your explaination.

R&D

-

5.0

It’s easy to understand and find things. I can tell what’s it for without your explaination.

R&D

-

5.0

It’s easy to understand and find things. I can tell what’s it for without your explaination.

Management

-

4.7

The graphs are neat and I would like to use it directly.

Management

-

4.7

The graphs are neat and I would like to use it directly.

Management

-

4.7

The graphs are neat and I would like to use it directly.