Coin Toss
An AI -powered travel planner for the confused traveller
Overview
Travel planning often becomes overwhelming due to information overload, safety concerns, and unfamiliarity with social and cultural norms. This can turn an exciting experience into a stressful task.
Goal
Simplify travel planning, reduce decision fatigue, and provide a safe, culturally informed travel experience through an innovative app that leverages Generative AI to create personalized itineraries and incorporates a playful "coin toss" feature for effortless decision-making.
Role
Lead UX Designer
Tools
Figma, Miro, Python, Google Gemini
Team
3 UX Designers, 2 UX Researchers, 2 Developers
Timeline
April - May 2024 (4 weeks)
BACKSTORY
One Group, Six Opinions…Zero Itineraries?
Our diverse team of six, with varying preferences for adventure, relaxation, and culture, often struggled to agree on trip itineraries. Planning visits to each other’s countries felt overwhelming and led to indecision.
Team Kick-Off Meeting
PROBLEM
Planning trips is difficult
Between balancing everyone’s preferences and switching between multiple apps for flights, stays, food, and things to do — group travel planning quickly turns into a chaotic, overwhelming experience. What starts as excitement often spirals into indecision, app fatigue, and confusion.
CURRENT USER JOURNEY:
Current User Journey
How might we make group travel planning more fun and frictionless by using AI to settle indecisions and spark spontaneous adventures?
SOLUTION
One app. Two itineraries. Zero stress.
Coin Toss uses AI to generate two personalized itineraries based on everyone’s preferences. Whether the group is indecisive or already has a destination in mind, users can let the AI decide or enter their choice. The app then curates experiences—places to visit, eat, and explore—making it easy to compare, choose, and skip the app-juggling hassle.
PROPOSED USER JOURNEY:
Proposed User Journey
USER INTERVIEWS
80% of users felt overwhelmed planning trips
Before diving into design, we wanted to ensure this was a real, shared pain point. So, we conducted in-depth interviews with 9 individuals—from solo travelers to group trip planners. I explored their travel habits, frustrations, and aspirations.
User Interviews
"We spent more time deciding where to go than actually booking anything.” — Interviewee, 7
KEY INSIGHTS
Decision Making Challenges
Users expressed difficulties in making travel decisions and a desire for an initial structure to guide their travel planning process.
Fragmented Planning Process
7 out of 9 interviewees mentioned using multiple apps and resources while planning and traveling. This fragmented approach led to inefficiencies and frustrations.
Safety and Cultural Awareness Concerns
A major concern raised by participants was around safety and lack of knowledge about social and cultural norms in unfamiliar destinations.
USER FLOW
Flexible discovery, clear choices, and seamless iteration
This flow highlights key decision points, such as choosing a destination or generating one spontaneously, and showcases how preferences and input shape personalized results. Optional loops, like regenerating itineraries, were kept visible to support exploration without overwhelming the user.
User Flow
IDEATING SOLUTIONS 1.1
Less confusion, faster decisions and seamless interaction
Rapid sketching allowed us to explore different layouts, interactions, and visual patterns, helping us identify the most intuitive designs that minimized friction and empowered user choice. We then refined and combined the strongest elements into a cohesive concept for wireframing.
The early sketches of Coin Toss
IDEATING SOLUTIONS 1.2
We translated our sketches into mid-fidelity wireframes, with each team member exploring different parts of the flow. Despite time constraints, we created multiple versions, quickly tested them, and collaboratively refined the strongest ideas into a cohesive solution.
The early iterations of Coin Toss
IDEATING SOLUTIONS 1.3
Each round simplified decisions, reduced clutter and streamlined choices
We created three iterations of the core user flow in low-fidelity wireframes, each aiming to reduce complexity and enhance clarity. By testing these versions with users, we identified friction points and patterns that supported intuitive navigation. Feedback from these quick tests helped us refine interactions and streamline the journey.
Variations of Itinerary Generation
HIGH FIDELITY PROTOTYPE
Letting Go of the Decision Fatigue
Some users didn’t want to plan at all—they just wanted to go. For them, we designed a one-tap ‘Coin Toss’ flow where the AI instantly picks a destination and builds an itinerary. This low-effort path reduces cognitive load and brings spontaneity back to travel.
HIGH FIDELITY PROTOTYPE
Tailored Travel Experience
Generic travel suggestions left users feeling frustrated and indecisive. To solve this, we introduced a preference input flow that captures each user’s travel style so the AI can generate tailored itineraries, cutting down irrelevant options and making decisions easier.
HIGH FIDELITY PROTOTYPE
Balancing Choice and Convenience
This dual-option approach empowers decision-making. If they’re still unsure, a quick coin toss helps them choose between the two—keeping the process light, flexible, and user-driven.
HIGH FIDELITY PROTOTYPE
Informed on-the-go decisions
During user testing, we discovered that travelers felt overwhelmed when seeking local information, such as prices, cuisine options, and cultural norms.
To address this issue, we integrated Gemini AI into our app, providing users with immediate, context-aware answers to their travel-related questions. This integration negates the need to navigate away from the platform.
AI INTEGRATION
So how does the AI work?
When a user inputs their preferences, the app sends structured prompts to Gemini via API calls, generating two tailored itineraries. If undecided, the AI assists by selecting one based on weighted preferences. For local recommendations — like prices, food, or cultural tips — live API calls fetch up-to-date information, ensuring the experience stays relevant and personalized.
Gemini AI Integration
60% "Tossed the Coin" and 72% users felt culturally informed and safer in plans
Learnings
This project taught me how to move fast without losing focus on the user.
I deepened my understanding of integrating GenAI into products — from designing smart prompt structures to making API interactions feel seamless.
Working in a hackathon setting sharpened my ability to collaborate under pressure, adapt quickly, and make clear design decisions even with tight time constraints.
Next Steps
With more time, I would focus on real-world user testing to validate the AI’s effectiveness and uncover edge cases.
Future improvements would center around making itineraries even smarter — adapting dynamically based on user feedback — and strengthening the AI’s local recommendations for greater trust and cultural sensitivity.
Read more of my case studies
