🌿 Aloe AI – Smarter Choices for Healthier Lives
🧠 Problem
Most people struggle to interpret nutrition labels or spot hidden ingredients that can worsen their health. This becomes especially dangerous for individuals with medical conditions like hypertension, diabetes, or allergies. Despite detailed packaging, most consumers can't translate that data into actionable decisions.
People don't need just facts—they need clear, personalized insight: “Is this safe for me to eat?” That’s what Aloe AI delivers.
💡 What It Does
Aloe AI is a health-aware barcode scanner that empowers users to make smarter grocery decisions based on their medical history and health goals.
Here’s how it works:
- Users sign up and fill in their medical profile (e.g. hypertension, gluten sensitivity).
- They scan any product’s barcode using their phone.
- Aloe AI fetches ingredient and nutrition data, and uses along with the user’s profile with Perplexity’s Sonar API.
- The Sonar API returns a clear, natural-language evaluation of whether the product is a good match for the user’s health.
- Aloe AI displays that feedback in plain English, helping the user immediately decide if the item is a “Yes,” “Maybe,” or “No.”
This process takes seconds—and can prevent years of health consequences.
🤖 How Aloe AI Uses Perplexity
Perplexity’s Sonar API powers Aloe AI’s intelligence. It's what makes Aloe more than a barcode scanner.
- We dynamically generate context-rich prompts that combine product info with the user’s health conditions.
- Sonar responds with personalized, explainable text: not just “good” or “bad,” but why a product is or isn't a good fit.
- It handles nuanced health questions, like: > “Is this safe for someone with high blood pressure and celiac disease?”
- Unlike traditional LLMs, Sonar can return up-to-date, factual responses—including information about product recalls, corporate history, or recent health concerns.
Without Sonar, Aloe AI wouldn't be possible.
🔮 What’s Next
- Alternative recommendations if the scanned product is not the best fit for the user.
- Wider food product support through multiple databases
- Calories tracking for even more personalized responses. (if the user has consumed enough sugar for the day, the scan grade or a suger-y product will be worse)
- Add health goal tracking and dietary trend analysis
⚙️ Tech Stack
- Frontend: Next.js (React) with mobile-friendly barcode scanning
- Backend: FastAPI (Python)
- Auth & DB: Supabase
Built With
- fastapi
- nextjs
- sonar
Log in or sign up for Devpost to join the conversation.