StudyBuddy AI

Your AI-powered study companion — organize, prioritize, and conquer your workload effortlessly.

Comment

Project Story — StudyBuddy AI

Inspiration

During my university years, I struggled with managing multiple assignments, exams, and deadlines. I noticed that most students relied on basic to-do lists or calendars, which were static and didn’t adapt to priorities or workload. I wanted to create a tool that not only tracked tasks but also smartly suggested study plans and priorities using AI, helping students maximize productivity without burnout.

What it does

StudyBuddy AI is a full-stack AI-powered study scheduler that helps students:

  • Organize tasks, assignments, and reminders in one place.
  • Auto-prioritize tasks based on deadlines, subjects, and workload.
  • Generate personalized study plans using Google Gemini AI.
  • Track progress with completion stats, streaks, and hours studied.
  • Receive daily/weekly reminders and auto-overdue task alerts.

It’s essentially a personal AI study assistant available on desktop and mobile.

How we built it

The project is built using a modern web stack:

  • Backend: Node.js + Express + MongoDB, with JWT authentication for secure user sessions.
  • Frontend: HTML/CSS/JS served statically, fully responsive and mobile-friendly.
  • AI Integration: Google Gemini API (1.5 Flash) to suggest personalized study schedules and task prioritization.
  • Automation: Cron jobs to mark overdue tasks and repeat reminders.
  • Database: Mongoose schemas for User, Task, and Reminder with validation, virtuals, and helper methods.

The workflow:

  1. Users register/login → JWT session issued.
  2. Users add tasks & reminders → tasks auto-checked for overdue status.
  3. Users request AI suggestions → system calls Gemini API → personalized plan returned.
  4. Users track progress → stats updated in real-time.

Example: Task Prioritization Formula

We calculate a priority score $P$ for each task:

$$P = \frac{W}{T} \times U$$

where:

  • $W$ = workload (estimated hours)
  • $T$ = time until deadline (in hours)
  • $U$ = user-defined urgency factor

This ensures tasks with less time and higher workload appear first.

Challenges we ran into

  • AI Provider Migration: Transitioning from traditional LLM structures to Google Gemini’s content-based API architecture.
  • Task Scheduling Logic: Ensuring recurring reminders, overdue updates, and progress tracking worked seamlessly together.
  • Authentication: Securing JWTs and password hashing while keeping the user experience smooth.
  • Frontend Rendering: Making a responsive calendar view and real-time task updates without heavy frameworks.

Accomplishments that we're proud of

  • Successfully integrated Google Gemini 1.5 API for high-speed, personalized study planning.
  • Implemented full CRUD + toggle + bulk delete + progress tracking for tasks.
  • Achieved real-time reminders and overdue automation via cron jobs.
  • Created a light/dark mode feature saved in localStorage.
  • Made the app fully responsive for both desktop and mobile.

What we learned

  • Full-stack architecture from database to frontend integration.
  • Interacting with Google Generative AI services for practical automation.
  • Advanced MongoDB/Mongoose techniques: virtuals, population, auto-updates.
  • Task scheduling logic, prioritization, and UX for productivity apps.
  • Real-world challenges of authentication, error handling, and cron automation.

What's next for StudyBuddy AI

  • Mobile app version with offline support.
  • Improved AI capabilities: auto-summarize notes, detect procrastination patterns.
  • Calendar integrations with Google Calendar / Outlook.
  • Gamification features to encourage streaks and achievements.
  • Collaborative features: group study plans and shared task boards.
Share this project:

Updates