a lane is a rules.json or .head pack — write your own (RULEPACK.md)

Scam & fraud phrasing detection

free · certified

scam_detect@0.1.0 · 3 routes

Classifies messages as 'clean', 'suspicious' or 'scam' over classic fraud shapes: lottery/prize, crypto-doubling, gift-card demands, IRS/impersonation, advance-fee openers. 'suspicious' is the honest middle tier — soft signals like urgency language escalate rather than convict.

Try it live — pinned to expert:"scam_detect"

Free demo endpoint, no signup. Same call your agent would make.

Taxonomy (3 routes)

clean, suspicious, scam

Honest limits

Pattern detection, not semantic fraud analysis — formulaic scams catch at 0.9+, novel phrasing can miss (that's what 'suspicious' + the abstention path are for). Complements, doesn't replace, real anti-fraud tooling.

Install

python3 tools/lane_install.py scam_detect@0.1.0 --apply --appliance .
python3 tools/lane_repro.py scam_detect-0.1.0.lanepack.tar.gz --url http://localhost:8402   # re-run the published eval yourself

sha256: b8cf0aa43d5a3d04e849fe7e… · Apache-2.0 · download lanepack

NEED YOUR OWN ROUTES?

A private lane on your taxonomy — trained, calibrated, exclusive. €149 / domain, 3 business days.

Get a lane like this pricing →

generated by tools/render_lanes.py · source: index.json