Inspiration
As students, managing multiple subjects, assignments, deadlines, and different difficulty levels can become overwhelming. We wanted to build something that does more than simply store a to-do list — something that helps students decide what to study first and understand their academic workload.
This idea led to CampusAssist AI, a student-focused academic productivity assistant.
What it does
CampusAssist AI helps students organize and prioritize their academic tasks.
Students can:
- Add subjects and topics
- Set difficulty and importance
- Enter days remaining and estimated study time
- Get a calculated priority score
- Track completed and pending tasks
- Analyze their academic workload
- Identify deadline risks
- Create study plans
- Access AI-based academic assistance and quick revision features
How we built it
CampusAssist AI was built using Python and Streamlit.
We used:
- Python for the application logic
- Streamlit for the interactive web interface
- SQLite for storing tasks and completion status
- A custom priority engine to calculate task priority
- AI integration structure for explanations, recommendations, study planning, and revision
- Git and GitHub for version control and project management
The priority engine combines difficulty, importance, and urgency to generate a practical priority score for each task.
Challenges we ran into
One of our biggest challenges was making the application reliable when deployed without requiring every user to configure an external AI API.
We also had to debug deployment issues, connect the application with GitHub, manage local data storage, and make sure the core application continued working even when an AI service was unavailable.
These challenges helped us focus on building a resilient application where the core academic management features remain usable independently.
Accomplishments that we're proud of
We are proud to have built a functional academic assistant from the ground up.
Our key accomplishments include:
- Building a working Streamlit application
- Creating a custom academic priority algorithm
- Adding workload and progress analytics
- Implementing SQLite-based task management
- Creating multiple academic assistance modules
- Successfully connecting the project to GitHub
- Successfully deploying the application through Streamlit Cloud
Most importantly, we created a solution around a real student problem rather than building technology without a practical purpose.
What we learned
Through this project, we learned how to turn an idea into a working application and how different components work together.
We gained practical experience with:
- Python application development
- Streamlit
- SQLite databases
- Git and GitHub
- Cloud deployment
- Debugging deployment errors
- Designing features around user needs
- Structuring an AI-enabled application
We also learned that building a project is an iterative process: testing, debugging, improving, and simplifying are just as important as writing the initial code.
What's next for CampusAssist AI
We plan to expand CampusAssist AI with:
- Personalized AI study recommendations
- Calendar and timetable integration
- Assignment and exam reminders
- Performance prediction
- Personalized learning paths
- Improved AI-powered study planning
- More detailed student performance analytics
- Mobile-friendly improvements
Our long-term goal is to evolve CampusAssist AI from an academic task manager into a personalized learning companion for students.
Log in or sign up for Devpost to join the conversation.