Start here
The free tool below runs entirely in this browser — no account, nothing stored or transmitted. Redact anything you would not want kept before you type it.
Open the companion tool →Why the check reads structure, not people
Romance scams are devastating precisely because the feelings involved are real to the person having them. A check that says "you should have known" fails the reader; a check that names the sequence of moves — affection, then isolation, then an emergency only money can solve — does not.
The pattern is stable across languages and platforms: rapid intensity, an excuse why in-person meeting keeps failing, and escalating financial emergencies. Those moves can be seen without judging the reader's feelings at all.
The protocol
- Paste redacted excerpts — remove names, addresses, and account details first.
- Read the move-by-move basis. A single move is not proof; a recurring shape is a reason to slow down.
- Before sending money, try the one move that breaks the pattern: propose a verified in-person or video meeting with no money involved.
- If you already sent money, contact your payment service, then report at ReportFraud.ftc.gov and ic3.gov.
What the tool does
Paste redacted chat excerpts and get a reading of the conversation's moves — intimacy, isolation, emergency, payment — with the basis shown. It runs in this browser; nothing is sent or stored.
Limit first: This is a pattern aid, not a fraud investigation service and not a judgment on anyone's relationship. It can miss a pattern and it can flag an ordinary conversation.
Open the companion tool →One human next step
Talk to one trusted person who is not part of the relationship about what you found, and report through the FTC's romance-scam guidance at ReportFraud.ftc.gov.
Research log and safety checks
AI-assist path: not used for a verdict. This artifact is an inspectable sequence-of-moves reading; a remote model would add an opaque judgment where the reader needs to see which move is the concern. §6.10: not a frontier-pace topic.
§0.5 protection result: category is scam-fraud-defense; crisis-adjacent: no; fear/urgency/scarcity toolkit used: no. The protective function is free and the paid feature is convenience only.