Inspiration In India, more than 10 million people lose their money or confidential information due to digital scams and it keeps increasing with the digital payment ecosystem.
What it does Paste any suspicious message and get an instant AI verdict, SCAM, SUSPICIOUS, or SAFE, with a confidence score, red flags explained in plain English, and clear advice on what to do next.
How we built it React + Vite frontend, Tailwind CSS for UI, Google Gemini 2.5 Flash for AI analysis via REST API, deployed on Vercel. Total cost: $0.
Challenges we ran into Gemini API compatibility across model versions, accidentally committing our API key to a public repo (Google auto-revoked it), and Tailwind v4's breaking PostCSS changes, all hit us hard but we pushed through.
Accomplishments that we're proud of Built, debugged, and deployed a fully working AI product in a single session. The AI doesn't just flag scams, it explains exactly why in language anyone can understand.
What we learned The hardest part of building an AI product isn't the AI, it's the integration. API security, rate limits, and parsing inconsistent responses taught us more than any tutorial.
What's next for ScamShield Browser extension, WhatsApp bot, regional language support (Hindi, Tamil, Bengali), real-time URL scanner, and an API for banks and NGOs to embed ScamShield directly into their platforms.
Log in or sign up for Devpost to join the conversation.