I built LayerCall after getting tired of the same pattern: blocking disposable email addresses stops almost nothing. The signups that matter use real mailboxes, often on domains registered days earlier, from addresses that look completely ordinary. What gives them away is the combination — the domain's age against the IP's provider against whether the phone is a VoIP line. Getting that meant three vendors, three response shapes, three bills, and writing the correlation by hand anyway. So LayerCall is that correlation as a product. One call returns IP, email, phone, domain and device together, with a 0-100 score, an allow/review/block verdict, and the individual signals behind it so you can explain a decision rather than just make one. The part I find most interesting is the newer half: verifying AI agents. An agent arrives with a real browser, a real fingerprint and a real mailbox, so nothing in a classical fraud stack has an opinion about it. What you actually need to know is which agent it is and whether it can prove it — a signature problem, not a fraud-signal problem. There's a live demo that runs the real engine with no signup, and a free tier that needs no card. Happy to answer anything.

LayerCall

Score a whole signup for fraud in one API call

Score a whole signup for fraud in one API call