I analyzed 227M Medicaid billing records to flag potential fraud
Public fraud detection across 227M Medicaid claims—1,860 flagged providers, zero false positives yet.

This turns HHS's huge Medicaid dump into a near-instant lookup: search 7.1K procedures (HCPCS/CPT), compare state-by-state averages, and browse by service categories or territories. The interface surfaces useful aggregates (avg payment, total claims, totals paid) and a map for quick comparisons — very handy for reporters and policy folks. I’d like clearer methodology notes and an obvious CSV/API download, but as a public-facing explorer it makes otherwise opaque data immediately usable.
Journalists, healthcare researchers, policy analysts, patient advocates, clinicians interested in reimbursement data
Public fraud detection across 227M Medicaid claims—1,860 flagged providers, zero false positives yet.
Constant-rate broadcast eliminates Tor's guard/exit node vulnerability entirely.
Targets fuse data and behavior into ordered, self-contained blocks so your code reads like a sequence (width animates, then color, then fetch) instead of juggling promises and external animation libs. The built-in Web Animations usage and the $$ wait-syntax are neat, opinionated moves — but it's still a bold, niche bet against mature motion ecosystems and will need strong integration stories to win broad adoption.
YouTube sponsorship tracker when Social Blade and HypeAuditor already map creator deals.
Web-based VoIP with AI agent support competing against Skype and Twilio.
SEO metrics on directory links save research time, but free blog lists already exist.