VeriTrust AI

Landing Page
Login/Signup Page
Dashboard
Verification Result
Trust Analysis / Charts

Inspiration

Millions of people donate online every year, but verifying whether an NGO or fundraising campaign is genuine remains difficult. Fraudulent donation websites and misleading campaigns reduce trust and discourage people from contributing. VeriTrust AI was created to help donors make safer and more informed decisions through AI-assisted credibility analysis.

What it does

VeriTrust AI analyzes publicly available website information to evaluate the credibility of NGOs and donation campaigns. It validates URLs, examines trust indicators such as HTTPS security, website metadata, contact information, and organizational details, then generates an explainable trust score along with confidence levels and verification insights.

How we built it

The frontend was built using React, Vite, and Tailwind CSS, while the backend was developed with FastAPI and Python. OpenAI Codex was used extensively during development for frontend implementation, backend development, debugging, API integration, and rapid feature iteration throughout the hackathon.

Challenges we ran into

One of our biggest challenges was ensuring reliable website verification. We faced backend integration issues, API communication problems, and website metadata extraction challenges. We also refined the trust scoring logic to provide meaningful and explainable verification results.

Accomplishments that we're proud of

Built a complete AI-powered verification platform.
Developed an explainable trust scoring system.
Created a modern and user-friendly interface.
Successfully integrated frontend and backend components.
Delivered a working prototype within the hackathon timeframe.

What we learned

This project strengthened our understanding of full-stack AI application development, API integration, metadata analysis, debugging complex backend workflows, and using OpenAI Codex effectively for rapid software development.