Nexora

Upload notes and instantly transform static content into adaptive AI-driven assessments.
Context-aware AI generates quizzes and answers user questions in real time.
Performance analytics identify weak concepts and enable targeted practice.

Inspiration

As students, we often spend hours studying large volumes of material without knowing which topics we actually struggle with. Existing learning platforms and AI tutors usually answer questions but fail to adapt based on a student’s mistakes. This lack of personalized feedback inspired us to build Nexora.

What it does

Nexora is an AI-powered adaptive learning tutor. Students can upload their study material, ask questions, and take AI-generated quizzes. The system analyzes incorrect answers and confusion patterns to identify weak topics, then dynamically prioritizes those topics in future explanations and quizzes.

How we built it

The project is built as a web-based application. The frontend provides interfaces for uploading notes, interacting with the AI tutor, and attempting quizzes. The backend processes study material, communicates with a Large Language Model (LLM) for answering questions and generating quizzes, and tracks topic-level performance using lightweight data storage. A rule-based adaptation layer ensures learning is focused on identified weak areas.

Challenges we ran into

One of the main challenges was designing an effective way to identify learning weaknesses without training a custom machine learning model. We solved this by structuring quiz feedback and mapping incorrect responses to topics. Ensuring that AI responses stayed aligned with the uploaded study material was another challenge, which we addressed through careful prompt design and context control.

What we learned

Through this project, we learned how to design adaptive AI systems, structure effective prompts for large language models, and build end-to-end applications under time constraints. We also gained experience collaborating as a team and balancing feature ambition with realistic execution.

Future Scope

Future improvements include detailed progress analytics, exam-date–based study plans, mobile support, and integration with institutional learning management systems.

Team Contributions

Mohamed Shahid: Frontend development and UI design
Monish: Backend development and API integration
Pritham: AI logic, prompt engineering, and quiz generation