PeerPort

• 

  PeerPort

Inspiration

First-generation and transfer students struggle to navigate college life without the guidance of family members who have been through the experience. Many students struggle to find mentors who understand their specific situations, whether it's navigating financial aid, choosing courses, dealing with imposter syndrome, or balancing work and studies.

What it does

AI-Powered Matching: Uses OpenAI GPT-4o-mini to intelligently match mentors and mentees based on major, hobbies, interests, and school domain. The AI analyzes compatibility and provides detailed reasoning for each match.

How we built it

Frontend:

• React for the UI
• Tailwind CSS for styling Backend (data storage):
• Firebase Firestore for storing profiles, messages, and connection requests
• Firebase Authentication for login/signup
• Firebase Hosting for deployment AI matching
• OpenAI GPT-4o-mini API for matching
• Send mentor/mentee profiles to the API
• API returns the best match with reasoning

Challenges we ran into

Setting up Firebase Authentication and Firestore with proper security rules was challenging. We had to learn how to structure data in Firestore and implement proper security rules to protect user data. Implementing localStorage fallback while maintaining data consistency with Firebase was tricky. We had to handle cases where Firebase is unavailable and ensure data doesn't get lost.

Accomplishments that we're proud of

Built a fully functional application with authentication, database, real-time features, and AI integration in a limited time frame.

What we learned

Gained deep understanding of Firebase Authentication, Firestore. Learned how to work with OpenAI's API. Improved our understanding of React hooks, state management, and component composition patterns.

What's next for PeerPort

Video Calls Integration

Built With

• firebase
• javascript
• openai
• react
• tailwind