Inspiration
Growing up, we all loved playing trivia games, but as we got older, the games available to us seemed to fall behind the expectations. We wanted to bring a competitive spirit to trivia in a fun, but measurable way.
What it does
We built a trivia app that harnesses the power of AI to generate questions and uses an ELO system, similar to one utilized for chess, to assess user strength. As you play more matches, your rating will become more accurate, and with a queue system prioritizing similarity in ranking, you'll be matched with members with similar skills. Including features like AI-powered feedback on questions you get wrong, we emphasize learning, while also keeping a competitive spirit to the app.
How we built it
We built it using Next.js for the front-end, Fast-API for the backend, and Supabase for the database. We wrote logic to process large chunks of data to generate trivia-like questions and also created a queue process where users are matched up according to skill.
Challenges we ran into
Creating the matchmaking queue system was a unique technical challenge, as well as making the generated questions have the "right feel".
Accomplishments that we're proud of
Getting the matchmaking queue to function while also making the app visually appealing were accomplishments we were proud of.
What we learned
We learned about managing asynchronous tasks and workers, precise prompt engineering, servers and networking, and keeping code simple and clean.
What's next for Triviate
We'd love to expand more and create more features such as:
- More variety and larger pool of questions
- Availability for users to generate their own questions based on prompts
- Users keeping track of accuracy with each specific subject
- New and more exciting game modes
- Many other ideas
Built With
- fastapi
- nextjs
- python
- supabase
- typescript

Log in or sign up for Devpost to join the conversation.