soup-team-crew_Meal Master

Inspiration

As university students, we constantly see our peers struggling to stretch their grocery budgets, only to let food spoil because they lack the time or inspiration to cook. Staring into a dorm fridge full of mismatched ingredients is a daily reality that drives massive food waste on campus, which inspired us to build a practical solution that benefits both hungry students and the environment.

What it does

Meal Master instantly turns a quick picture of your raw, leftover ingredients into a structured, actionable recipe using AI. Additionally, it features a "Neighborhood Pantry," a real-time local network that allows students to post and claim unused ingredients from their peers before they spoil.

How we built it

We designed the mobile frontend using React Native for a seamless experience on both iOS and Android. The core logic is powered by a FastAPI Python backend that we containerized with Docker and deployed to Google Cloud Run. We utilized the OpenAI Vision API to analyze the fridge images and Supabase to securely manage user authentication and the real-time pantry database.

Challenges we ran into

Getting the AI to consistently return parseable data was a massive hurdle; vision models often default to conversational apologies when uncertain, which completely broke the app's rendering. We heavily refined our prompt engineering to force strict JSON arrays.

Accomplishments that we're proud of

We are incredibly proud of successfully deploying a fully containerized, serverless backend that communicates seamlessly with a native mobile application. Building a functional peer-to-peer food sharing network on top of a complex AI vision integration all within the tight time constraints of a hackathon was a huge win for our team.

What we learned

Beyond mastering Docker and Google Cloud Run deployments, we learned how to effectively handle asynchronous state management in React Native. Balancing the mobile frontend user experience with backend API constraints taught us how to bridge raw AI capabilities with a resilient, user-friendly product.

What's next for soup-team-crew_Meal Master

We plan to expand the Neighborhood Pantry feature to include campus-wide dorm filtering and add gamification badges for students who share the most food. Ultimately, we want to refine the UI, tighten up the database security rules, and officially launch the app to our student body to make a real, measurable dent in campus food waste!