Study-Pilot

Track-AI4Good

Inspiration

Students often rely on scattered learning materials and generic AI chatbots that answer questions but do not actively manage the learning process. I built StudyPilot to turn studying into a personalized, goal-driven workflow.

What it does

StudyPilot converts PDFs, PowerPoint slides, notes, audio, and video into a personalized learning experience. It provides source-linked explanations, adaptive quizzes, study notes, flashcards, spaced repetition, mock exams, and progress tracking.

How we built it

I built StudyPilot using Python, FastAPI, JavaScript, and an AI API through OpenRouter. Its workflow combines document processing, information retrieval, learner modelling, assessment, and revision planning. It tracks mistakes and topic mastery to prioritize weaker concepts and recommend the next study activity.

Challenges we ran into

One key challenge was keeping AI-generated answers grounded in uploaded materials. I addressed this using source retrieval, citations, answer verification, and fallback practice questions when AI generation is unavailable. I also designed the study workflow to remain useful when external AI services fail.

Accomplishments that we're proud of

I integrated multimodal material ingestion, a structured course knowledge base, source-grounded tutoring, adaptive assessments, per-topic mastery tracking, a study dashboard, and personalized revision into one application.

I also implemented question and knowledge-base audits, answer-quality evaluation, and simulated-student experiments. These allow me to examine not just whether features work, but also where retrieval accuracy, grounding, and personalization need improvement.

What we learned

I learned to combine language models with retrieval, document processing, source metadata, assessment verification, and learner-state tracking. I also learned that a useful educational AI system needs more than convincing answers: it needs traceable evidence, reliable question generation, meaningful personalization, and transparent evaluation.

What's next for Study-Pilot

My priorities are to improve exact citation accuracy and unsupported-query detection, refine the adaptive policy so that lower repetition also produces stronger mastery gains, run independent framework-based evaluations, and validate the system with real learners. I also aim to improve multimodal figure understanding and make personalized recommendations more reliable across longer study sessions.

Built With

• agentic-ai
• bayesian
• css
• deepeval
• html
• information-retrieval
• javascript
• numpy
• ocr
• openrouter
• pillow
• pymupdf
• python
• scikit-learn
• spaced-repetition
• sqlite
• tf-idf
• whispr