Inspiration

Recently one of my family member got scammed due to fake e-commerce website and fake reviews

What it does

VERIBUY is an AI-powered e-commerce intelligence platform that helps users make safer purchasing decisions. It analyzes products, sellers, prices, and customer reviews using Google Gemini to detect fake products, assess seller trust, summarize reviews, and suggest better-value alternatives across platforms

How we built it

We built VERIBUY using Google AI Studio and Gemini models as the core intelligence layer. The frontend is developed with React, TypeScript, and Vite, featuring a modern dark UI inspired by Web3 platforms. Gemini handles product analysis, review summarization, authenticity scoring, and conversational assistance. The app is deployed as a web application using environment-based configuration.

Challenges we ran into

Ensuring secure AI key management in a client-based environment was a major challenge. We also had to design reliable AI prompts to analyze authenticity and reviews without access to proprietary marketplace APIs. Balancing realism, performance, and hackathon time constraints required careful architectural decisions.

Accomplishments that we're proud of

We successfully integrated Gemini for multiple real-world e-commerce use cases, including fake detection and review intelligence. Building a clean, premium UI and deploying a fully functional AI-powered web app within a limited timeframe was a major achievement.

What we learned

We learned how to design AI-first applications, write effective structured prompts, and deploy modern web apps securely. We also gained valuable experience in explaining AI limitations transparently while still delivering strong user value.

What's next for VERIBUY

Next, we plan to move AI processing to serverless backends, integrate real marketplace APIs for live price comparison, add barcode and image-based scanning, and expand VERIBUY into a browser extension and mobile app.

Built With

Share this project:

Updates