AI Shopping Assistant
A conversational grocery price-comparison assistant for the UAE. Shoppers describe what they need in plain language, and the assistant searches major retailers in parallel to return a price-ranked best-value basket on iOS, Android, and WhatsApp.
Project Overview
A conversational grocery price-comparison assistant for the UAE. Shoppers describe what they need in plain language, and the assistant searches major retailers in parallel to return a price-ranked best-value basket on iOS, Android, and WhatsApp.
The Problem
UAE shoppers compare grocery prices by hand across separate retailer apps, which is slow and tedious. They needed one natural-language query that returns the best-value basket with live prices and availability.
The Solution
A FastAPI backend runs a multi-step LangGraph agent that classifies the request, crawls retailers in parallel, filters unavailable or off-topic items, then ranks the best match per item. Results stream to an Expo app, with WhatsApp on the same backend.
Use Cases
Natural-language search
Ask in plain language with no keyword syntax to learn.
Parallel retailer crawl
Searches major UAE retailers at the same time for live prices.
LLM-driven ranking
An LLM ranks and selects the best matching product per item.
Safety filters
Unavailable and off-topic products are removed before ranking.
Live progress
Each step streams to the app so the experience feels responsive.
Omnichannel
The same backend powers mobile apps and WhatsApp.
Project Screenshots
What I Delivered
- LangGraph agent over FastAPI with live streaming
- Parallel crawler service for major UAE grocery retailers
- LLM-driven ranking with availability and relevance filters
- Expo React Native app with multi-provider OAuth
- Twilio WhatsApp channel on the shared backend
Ready to build something useful?
Whether you need a freelance build, a full-time hire, or a short intro call, pick the path that fits and I will respond within 24 hours.