Inspiration
We wanted to create a simple yet practical project to get more hands-on experience with full-stack web development. Our goal was to practice building, connecting, and deploying the pieces of a modern web app, while also experimenting with generative AI integrations.
What it does
VarietyShoppingHour is a web app where users can enter shopping items with details like name, price, image, and description. The app uses the Gemini API to validate and filter items, ensuring they match the entered criteria before saving and displaying them.
How we built it
VarietyShoppingHour is a web app where users can enter shopping items with details like name, price, image, and description. The app uses the Gemini API to validate and filter items, ensuring they match the entered criteria before saving and displaying them.
- Frontend: React for the user interface
- Backend: Express/Node.js to handle API routes and item validation
- Database: MongoDB to store user-submitted items
- AI: Gemini API for content checking against item fields
Challenges we ran into
- Setting up authentication and handling user sessions
- Debugging unexpected behavior when integrating the Gemini API
- Resolving merge conflicts and syncing our work across team members
Accomplishments that we're proud of
- Successfully connecting all components (React, Node, MongoDB, Gemini) into one working app
- Collaborating effectively to merge code and bring our different parts together
What we learned
- Hands-on experience with the MERN stack
- How to integrate generative AI APIs into a web workflow
- The importance of teamwork, communication, and version control in development
What's next for VarietyShoppingHour
- Smarter GenAI support: recognizing saved items and providing intelligent recommendations
- More robust authentication and personalization features
- A cleaner, more polished UI/UX for item browsing

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