StudyBuddy

Select Buddy
Chat Interface
Flashcards
Pins
Quiz
Quiz Evaluations

Inspiration

We were inspired by the idea of making learning more personalized and engaging. Everyone learns differently like some prefer detailed explanations, while others want quick summaries/flashcards or interactive tests. We thought, "What if we could build an AI-powered study buddy that adapts to individual learning styles?" That’s how Study Buddy came to life.

What it does

Study Buddy is an AI-driven platform that helps students learn by offering highly customized content based on their preferences. Users can interact with AI-powered buddy professors in different domains, such as cybersecurity, finance, or AI. The platform lets users adjust tone, comprehension level, and content length to get exactly the kind of explanation they want.
Additionally, it offers a Pins Board for saving important responses and a Desk Declutter feature using Coco SSD, which analyzes the user’s desk and suggests ways to organize it for a better study environment.

How we built it

We used Next.js for the frontend and styled the interface using Material UI to ensure a clean, modern design. The backend was built with Node.js, while Firebase was used as the database to store user data and pinned responses. For secure authentication, we integrated Clerk.
To power the content generation, we used the Gemini Flash AI model via API. The Desk Declutter feature was implemented using Coco SSD from TensorFlow, allowing object detection and generating personalized decluttering suggestions.

Challenges we ran into

One of the biggest challenges was crafting effective prompts for generating customized responses. We had to balance multiple factors like tone, and content length to provide meaningful answers.
Another challenge was integrating Coco SSD smoothly into the application and ensuring real-time object detection worked well. Managing data storage for pinned content and maintaining a responsive UI were also areas where we faced some hurdles.

Accomplishments that we're proud of

We’re proud of building a platform that offers personalized learning experiences. Successfully integrating multiple technologies like AI, object detection, and real-time customization was a major accomplishment. We’re also proud of designing a user-friendly interface that enhances the overall learning experience.

What we learned

We learned a lot about working with AI models, designing prompt strategies for better responses, and integrating machine learning models into real-world applications. We also gained experience in creating interactive UIs, managing backend services, and ensuring seamless authentication.

What's next for Study Buddy

We plan to add more features, such as gamification & progress tracking, to help users evaluate their learning. We also want to enhance the professor personas by adding more domains and deeper expertise. Another goal is to improve the Desk Declutter feature by adding more advanced suggestions and potentially integrating smart reminders.