Inspiration## Inspiration
Students often study from large PDFs and notes but struggle to identify important concepts, clarify doubts, and practice effectively. We wanted to build a personalized learning assistant that helps students learn directly from their own study materials.
What it does
Adaptive AI Tutor is a personalized learning platform that brings study materials, AI-powered assistance, practice quizzes, and learning progress together in one place.
- Study materials: Upload PDF notes for text extraction and processing.
- AI tutor: Ask questions about learning concepts and study materials.
- Practice quizzes: Generate questions to test understanding.
- Learning progress: Track quiz performance and topic mastery.
- Personalized practice: Use learning progress to identify topics that need more attention.
How we built it
We built a full-stack application with a Next.js frontend and a Python FastAPI backend. The backend provides API endpoints for document processing, question answering, quiz workflows, and learning progress. PDF processing uses text extraction and OCR, while the learning workflow organizes material into chunks for retrieval and topic-based practice.
Challenges we faced
One of our main challenges was deploying PDF OCR reliably in a cloud environment. We also worked on connecting the frontend to the backend API and organizing the quiz and learning-progress workflows.
What we learned
We gained experience building and deploying a full-stack AI learning application, connecting frontend and backend services, processing study documents, and designing personalized learning workflows.
What's next
We plan to improve cloud-based OCR reliability, strengthen answers grounded in uploaded materials, and further personalize quizzes using student performance.
What it does
How we built it
Challenges we ran into
Accomplishments that we're proud of
What we learned
What's next for Adaptive AI Tutor
Built With
- ai
- fastapi
- machine-learning
- natural-language-processing
- next.js
- python
- react
- restapi
Log in or sign up for Devpost to join the conversation.