Prefer Solo

Inspiration

We believe travel should be as personal and dynamic as the people experiencing it. Inspired by everyday moments of curation—like how Barilla matches playlists to pasta cooking times—we set out to create an app that crafts journeys perfectly aligned with your unique tastes and schedule.

What it does

Prefer builds custom travel itineraries by combining your pre-set profile (preferences in food, activities, music, and more) with real-time inputs like travel duration and chosen localities. The app uses an advanced LLM to generate multiple travel plans, integrates Spotify for mood-based soundtracks that match your journey, and taps into crowdsourced data to highlight the best local spots.

How we built it

Layered Architecture: A clear separation of frontend (React + Tailwind), backend (Node.js), and a Smart Services layer for API integrations and AI-driven recommendations Advanced Integrations: Leveraged Firebase for authentication, Firestore for storage, and APIs like Google Maps, Spotify, and OpenAI LLM services to provide real-time, personalized insights.

Challenges we ran into

Integrating Multiple APIs: Coordinating real-time data from various sources (Spotify, Google Maps, etc.) while maintaining performance. User-Centric Design: Crafting an intuitive interface that balances rich functionality with ease of use. LLM Optimization: Ensuring the AI consistently produces relevant and exciting travel plans that cater to diverse preferences. Data Consistency: Keeping user profiles and dynamic inputs synchronized for accurate recommendations.

Accomplishments that we're proud of

Robust Personalization: Successfully built a recommendation engine that tailors experiences to individual users. Seamless Integrations: Achieved smooth integration of third-party services Responsive Design: Developed a user interface that is both visually appealing and highly functional

What we learned

Data-Driven Design: Leveraging real-time data can dramatically elevate personalization and user satisfaction. User-Driven Innovation: The importance of listening to user feedback and iterating quickly to meet real needs Recommendation Systems for Various Use Cases