-
-
search results
-
recommendation for users based on preferences!
-
similiar plot books
-
description page
Inspiration
We often struggle to find stories that truly resonate with us. Generic recommendation engines fall short because they don't understand our cultural context or taste. We wanted to build something smarter — something that goes beyond ratings and genres to understand why you like what you like.
What it does
LitFlix uses Qloo’s cultural AI to recommend movies and books based on your past preferences. Whether you loved Fight Club or Little Women, it finds similar titles through deep cultural signals rather than surface-level tags.
How we built it
We used React for the frontend and FastAPI for the backend. We integrated the Qloo endpoints to retrieve entity IDs and generate taste-based recommendations. We added a smooth carousel-based UI to show curated picks based on books, movies, or locations you've selected.
Challenges we ran into
Understanding how the Qloo Insights API worked in practice was a learning curve. Mapping real-world inputs like “Paris” or “The Great Gatsby” to usable entity IDs required iteration. We also had to rethink what “good recommendations” mean in a real-world product.
Accomplishments that we're proud of
We built a live, working taste-driven recommendation engine in just a few days. It’s visually intuitive, culturally aware, and delivers recommendations that actually surprise users in a good way.
What we learned
Taste is complex, and building truly personalized experiences requires more than simple filters or genres. Qloo's graph and APIs made us think in terms of cultural relationships, not just content attributes.
What's next for LitFlix
We want to expand recommendations to include music and fashion, allow saving & rating, and improve onboarding to better understand each user's vibe from the start. We’re also exploring monetization as a taste-curated discovery engine for streaming platforms and bookstores.
Log in or sign up for Devpost to join the conversation.