This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend
What I Built
I built PrepMate AI for my friend. We regularly meal prep our weekly lunches, and our fridge is almost always stocked with the exact same high-protein staples: chicken breast, eggs, tempeh, lettuce, corn, and tomatoes.
While healthy, eating the same variations of salads and grilled chicken every day leads to massive decision fatigue and flavor boredom. I built this lightweight web app to solve that. She simply checks off the ingredients we currently have left in the fridge, and the AI instantly acts as a creative chef, generating a unique recipe, a new flavor twist, or a fresh dressing idea using only what we have on hand.
Demo
Code
How I Built It
The project is built as a highly responsive Single Page Application using:
- Frontend: Next.js (App Router) and Tailwind CSS for a clean, mobile-first UI.
- AI Core (Open-Source): I utilized Gemini open-weight model. To keep the app lightning-fast for a quick weekend build, I routed the inference through the Gemini API.
- Integration: A Next.js API route securely handles the prompt construction. The system prompt forces Gemini to respect the selected ingredients and format its output into a beautifully structured Markdown recipe (Catchy Name, Why It Works, and Step-by-Step Instructions).
Top comments (0)