## Inspiration
Students often struggle to turn a large syllabus, limited study time, and different topic difficulties into a realistic study schedule. A fixed timetable does not adapt when a student falls behind or finishes topics early.
As a student, I wanted to create a tool that could make study planning more personalized and practical.
What We Are Building
StudyPilot is an AI-powered study planner that helps students organize their subjects, chapters, deadlines, available study time, and priorities into a personalized study plan.
The goal is to make the plan adaptive rather than static. As students complete or miss tasks, StudyPilot can adjust the remaining schedule.
How It Works
Students provide their subjects, topics, exam date, available study hours, and topic priorities. The application processes this information and generates a structured study plan.
The dashboard then helps students track completed topics and monitor their progress.
Technology
The project will use a lightweight web application architecture with a Python backend, a web-based frontend, a database for study information, and an AI API for personalized planning.
Challenges
Our main challenge will be creating useful AI-generated schedules while keeping the recommendations realistic, balanced, and understandable for students. We also want the application to remain simple enough to use without overwhelming the student with unnecessary features.
What We Hope to Learn
Through this project, we aim to learn how to combine AI with a practical software application, design a useful user experience, and turn a real student problem into a working product.Inspiration
What it does
StudyPilot creates personalized study schedules based on exam dates, available study hours, topic difficulty, and progress. It can adapt the schedule when topics are completed.
How we built it
Built with Python, Flask, SQLite, HTML/CSS/JavaScript, and Google Gemini API. We also added a reliable local planner when AI is temporarily unavailable.
Challenges we ran into
Making AI scheduling reliable, handling API availability issues, and ensuring the schedule stays realistic within the student's daily time limit.
Accomplishments that we're proud of
We built a working adaptive planner that combines AI personalization with a reliable fallback, while tracking progress and adjusting unfinished topics.
What we learned
We learned how to integrate generative AI into a real application, handle API failures, manage data with SQLite, and design a more practical user experience.
What's next for StudyPilot
We plan to add better progress analytics, smarter revision planning, reminders, and more personalized learning recommendations.
Log in or sign up for Devpost to join the conversation.