RecipeFit

Introduction

Between tight schedules, ingredient shortages, allergies, and fitness goals, cooking a healthy, satisfying meal can feel like solving a puzzle. For students and health-conscious individuals alike, this often means bouncing between five apps just to make dinner.

RecipeFit was created to eliminate that burden. Our goal was simple: make it as easy as possible to find a recipe that works for you, with what you have. Built by a team of five using MERN + Flask, I served as the product manager and contributed to early feature scoping, user validation, and AI integration strategy.

Target Users

• College students, young professionals, or anyone who:
• Wants to eat healthy
• Has dietary restrictions (e.g. allergies, macro goals)
• Doesn’t have time to scroll through a dozen recipe blogs
• Often cooks with limited ingredients on hand

Our Goal

To design and build a recipe app that filters by available ingredients, dietary restrictions, and nutrition targets, offering smart substitutions and curated results—all in one place.

User Discovery: “I Have Food, But No Idea What to Cook”

To understand the friction behind everyday meal planning, we interviewed 16 students and early-career professionals who cook at least 2x a week. We asked about their current cooking process and biggest frustrations.

Common Pain Points:

• Ingredient mismatch: “I don’t have cumin or coconut milk, so I just give up.”
• Allergy anxiety: “Even if a recipe says ‘peanut-free,’ I still triple-check.”
• Macro confusion: “I want something high-protein, but I’m not about to calculate grams manually.”
• Recipe fatigue: “I scroll for 10 minutes before realizing I don’t want any of it.”

We also sent out a broader survey (n = 45) and found:

• 68% want to track some form of nutrition
• 82% search for recipes based on what’s in their fridge
• 60% have tried and abandoned a recipe app

Insights that Shaped Our Product

Competitive Analysis: Too Much or Too Little

Gap: None of these tools helped users say: "Here’s what I have, here’s how I eat—what can I make?"

Product Features

• Smart Recipe Finder: Users enter ingredients, allergies, macros, and preferences (e.g. “high protein” or “quick meals”) to get curated recipe suggestions.
• Substitution Intelligence: If a user is missing a key ingredient, we use Gemini to suggest substitutions that maintain nutrition and flavor balance.
• Personalized Nutrition Cards: Each recipe comes with a visual nutrition breakdown (protein/fat/carbs) and a quick flag if it matches user-defined macro goals.
• Saved Recipes + Profiles: Users can favorite recipes, set macro/allergy filters once, and see history of what they’ve made before.

How We Built It

• Frontend: React + Tailwind CSS
• Backend: Node.js + Express + MongoDB (for user and recipe data)
• Supplemental Flask API: Handles Gemini prompt generation and calls
• External APIs: Edamam for nutrition + allergy tagging, Gemini for substitution logic
• Auth: JWT-based session handling
• Testing: Selenium for user flow validation

Technical & PM Challenges

Balancing Specificity and Flexibility

Too many filters = no results. Too few = irrelevant ones. We iterated on the filter logic to let users prioritize (“must-have” vs “nice-to-have”).

Prompt Engineering for Gemini

Early prompts gave wild substitutions (e.g., “replace chicken with applesauce”). We restructured prompts to include recipe context, diet labels, and formatting rules.

Allergy Trust

We had to sanitize and validate Edamam’s responses. If a recipe contained “may contain peanuts,” we excluded it entirely from peanut-free results.

Outcomes & Wins

• Delivered a fully functional full-stack MVP in 5 days
• Achieved successful end-to-end substitution flow using Gemini
• Built and styled modular components (search, filter, nutrition cards) from scratch
• Tested with 10 users post-launch — 80% said they'd use it over Google searching

What We’d Improve

• Fuzzy Ingredient Matching: A fridge may have “tomato sauce” but the recipe says “crushed tomatoes.” We want to improve semantic matching.
• Community Curation: Add ability to mark recipes “dorm-friendly,” “microwave-only,” etc.
• Meal Planning Mode: Let users plan a week of meals based on macros and re-use ingredients.

RecipeFit: Eat smart. Cook easy.