BlindSpot

What it does

BlindSpot is an AI-powered personalised learning platform designed to help students understand their mistakes and improve their weaker subjects. Students answer questions, receive feedback to help them understand their errors, and track their progress. The goal is to help students identify their blind spots and learn more effectively.

Uses

BlindSpot helps students practise topics, identify areas where they struggle, and receive personalised AI-generated feedback when they answer questions incorrectly. It aims to make studying more interactive and help students focus on the areas where they need the most improvement.

How we built it

We built BlindSpot using React and Vite for the frontend, Python and FastAPI for the backend, and SQLite to store student attempts. We integrated Google’s Gemini AI to generate personalised feedback that explains mistakes and provides helpful hints. The platform also includes a dashboard and study sessions to make learning more organised.

Challenges we ran into

One of our biggest challenges was integrating the frontend, backend, database, and AI model into one working application. We also encountered issues with API communication, CORS configuration, and getting AI-generated feedback to display reliably. These challenges taught us the importance of testing each component and ensuring that different technologies work together correctly.

Accomplishments that we’re proud of

We’re proud of building a working learning platform that brings together an interactive interface, a backend API, database storage, and AI integration. We turned our idea into a functional prototype and established the foundation for personalised learning that focuses on understanding mistakes rather than simply marking answers right or wrong.

What we learned

We learned how to connect a React frontend to a Python backend, build API endpoints with FastAPI, store data using SQLite, and integrate Google’s Gemini AI. We also gained experience debugging technical issues, managing API credentials, and working through the challenges of building a full-stack application under time pressure.

What’s next for BlindSpot

Next, we want to make AI feedback more reliable, improve progress tracking using students’ actual performance data, and make study sessions adapt more effectively to individual weaknesses. We also hope to expand the question bank, support more subjects, and develop a more comprehensive personalised learning experience.

Built With

• database
• python