Inspiration
As Berkeley students, we noticed a recurring struggle — finding the perfect study spot.
Whether it was Haas being full, Moffitt too loud, or cafés lacking outlets, the process of locating a good place to study often felt like a daily quest.
We realized that despite Berkeley’s countless study spots, most students rotate between the same few. The idea for JustDoeIt came from a simple question:
“What if your study habits could recommend your next favorite spot?”
By combining data, community insights, and AI, we wanted to make studying feel easier, smarter, and more personalized — helping students save time and thrive academically.
What it does
JustDoeIt is your personal study companion — an intelligent platform that connects UC Berkeley students to their best study environments.
It helps you:
- Discover study spaces based on AI-powered recommendations
- Track your study sessions, streaks, and productivity
- Visualize real-time busyness and space availability
- Explore an interactive campus map of Berkeley’s top spots
- Learn from community ratings and tips shared by peers
In short, JustDoeIt helps students study more effectively — and enjoy the process along the way.
How we built it
We built JustDoeIt using a modern full-stack architecture:
🧠 Backend
- FastAPI (Python) for a lightweight, high-performance REST API
- Supabase (PostgreSQL) for authentication and real-time database sync
- Python 3.9+ for data processing and analytics logic
- AI recommendation engine leveraging user behavior data
💻 Frontend
- React 18 + TypeScript for a fast, responsive UI
- Vite for rapid builds and local development
- TailwindCSS + Radix UI for elegant, consistent design
- Interactive Map Layer using Mapbox (experimental)
🧩 Architecture
Frontend and backend communicate via secure REST endpoints.
Session data and productivity metrics are stored in Supabase, then analyzed for real-time insights and personalized study recommendations.
Challenges we ran into
Building JustDoeIt was an exciting but challenging journey.
Some of the key hurdles we faced included:
- 🔌 Data Integration:
Combining user session data with Supabase analytics in real-time without performance lag. - 📊 Recommendation Algorithm:
Designing an AI model using Claude API that adapts to user preferences dynamically rather than relying on static rules. - 🧭 Map Interaction:
Rendering an interactive map that balances usability with information density (outlets, WiFi, crowd level, etc.). - 🧱 Frontend Scalability:
Maintaining a fast and fluid UI as we integrated multiple complex components (charts, maps, analytics).
Accomplishments that we're proud of
- 🎓 Built a working AI study-space recommender from scratch
- 🗺️ Designed an interactive Berkeley study map with real-time data
- 📈 Created a personal study analytics dashboard to visualize habits and productivity
- ⚡ Developed a full-stack system that runs efficiently on local and cloud setups
- ❤️ Received great feedback from Berkeley peers who tested the prototype
What we learned
Building JustDoeIt taught us invaluable lessons in both technical and user-centered design:
- How to balance data engineering with UX simplicity
- The importance of real-time synchronization for meaningful analytics
- How small details — like outlet availability or noise level — drastically influence user satisfaction
- How to design for scalability early on, preparing for Bay Area-wide expansion
We also deepened our understanding of FastAPI, Supabase, and frontend performance optimization using Vite and TailwindCSS.
What's next for JustDoeIt
We’re just getting started.
🚀 Upcoming Goals
- 📱 Launch mobile apps (iOS + Android) for on-the-go recommendations
- 🌉 Expand to Stanford, UCSF, and other Bay Area campuses
- 🤝 Introduce study group and social matching features
- 🌙 Add offline mode and smarter habit-tracking AI
Ultimately, our vision is to create a global platform that helps students anywhere find their best study environments — powered by data, driven by community, and guided by design.
Study smarter. Explore more. JustDoeIt.



Log in or sign up for Devpost to join the conversation.