Scamlens
Team Thanakorn Morasilp
The big news
Everyday people get expert-level scam detection in a single upload. ScamLens checks screenshots or pasted text from SMS phishing, fake courier fees, government impersonation and predatory loans. A fast, lightweight machine-learning model classifies content in under a millisecond, while any bank accounts or PromptPay IDs are cross-checked against official blacklists. A second AI tier handles uncertain cases with grounded verification, avoiding the hallucinations of chatbot-only checks. Fast, cheap and grounded, it helps stop scams before money moves.
Watch the demo
What it does
A two-tier scam detection prototype combining a TF-IDF and Naive Bayes classifier with blacklist lookups and LLM-based grounded verification for uncertain cases. Built with Next.js, TypeScript, Node.js and Python.
Try it yourself
U-tags
Tap a tag to find similar projects
Meet the team
This is an independent hackathon project. Some features may be prototypes. Please do your own research before relying on it.