Inspiration
I built ELI-You because traditional studying doesn't always work for everyone. Sometimes a student understands a concept perfectly when it's explained in a familiar context, but struggles when it's presented in a textbook or classroom. I wanted to create a tool that makes difficult concepts feel more understandable by connecting them to things students already know and enjoy.
What it does
ELI-You is an AI-powered study tool that takes a concept a student is struggling with and explains it using a topic they're interested in. Instead of giving everyone the same generic explanation, ELI-You makes learning more personal, relatable, and engaging. It can also generate quizzes to help students test whether they actually understand the concept.
How we built it
I built ELI-You as a web application with a Flask backend and an interactive frontend. The backend connects to Google's Gemini API to generate personalized explanations and quizzes. We focused on structured AI responses so that the generated content could be reliably displayed and used by the website. We also designed the system to keep the AI-generated explanations flexible rather than relying on hard-coded content.
Challenges we ran into
One of my biggest challenges was getting AI-generated responses to consistently follow the structure my application expected. Gemini could sometimes return valid information in an unexpected format, which caused my quiz generation and parsing to fail. I also had to work through backend deployment, CORS, networking, API configuration, and Git issues while making sure the application could work for users beyond our own computer.
Accomplishments that we're proud of
I am proud that I turned a simple idea into a working AI-powered learning platform. I successfully connected a real AI model to a functional web application and created a system that can transform difficult concepts into explanations tailored to a student's interests. I am especially proud of the idea behind ELI-You because it focuses on making education feel personal rather than treating every student the same.
What we learned
I learned that building an AI application involves much more than simply connecting an API. Reliable structured outputs, error handling, backend architecture, deployment, networking, and user experience all matter. I also learned how important it is to design around the unpredictability of AI-generated content and build systems that can gracefully handle unexpected responses.
What's next for ELI-You
Next, I want to make ELI-You more personalized and useful as a long-term study companion. I plan to improve the quality and consistency of AI-generated content, expand the quiz and learning features, add progress tracking, and make personalization more powerful. My goal is to turn ELI-You from a tool that explains concepts into a complete learning experience that adapts to each student's needs.
Log in or sign up for Devpost to join the conversation.