Inspiration
We wanted to build something that makes meeting new people feel natural—not forced. Music and movies say more about us than generic bios ever do, so we created a way to match people through the media that truly reflects who they are.
What it does
MediaMates connects to your Spotify and Letterboxd accounts, analyzes your music and film tastes, generates compatibility scores using AI, and shows you friends who share your vibe. It also provides fun, AI-generated explanations for why you match.
How we built it
We built a responsive web app with custom HTML/CSS UI screens, integrated the Spotify and Letterboxd APIs for user data, and used Gemini/OpenAI to analyze tastes and generate compatibility insights. Flask handled routing, API calls, and result processing.
Challenges we ran into
We struggled with aligning dynamic UI hitboxes across different screen sizes, managing OAuth/API permissions, and parsing inconsistent media data. Tuning the AI prompts for meaningful compatibility scoring also took iteration.
Accomplishments that we're proud of
We designed a cohesive retro aesthetic, created a fully interactive matching experience, successfully integrated two major media platforms, and built a working AI-powered compatibility system—all within hackathon time.
What we learned
We learned how to work with multiple APIs at once, how to structure async data flows, how to build responsive design from scratch, and how to refine AI prompts to produce accurate, personalized insights.
What's next for MediaMates
We want to add real user profiles, friend requests, deeper AI personality summaries, group matching, and support for more platforms like Goodreads or Last.fm. We also plan to deploy the app and open it for real users.
Log in or sign up for Devpost to join the conversation.