SCAN ACTIVE14 CLASSES ARMED
VERDICTS ONLY
THE INSTRUMENT
The instrument.
How it works
01 CREATE A TENANT
One call, get a key. Free tier is 1,000 events, no card.
02 STREAM LOG LINES
POST /platform/ingest with your X-API-Key.
03 READ THE VERDICT
Score, components, classes, hit counts. Flagged events surface in your alerts feed.
The verdict, dissected
{
"verdicts": [{
"event_id": "ev-0001",
"score": 46.2,
"components": {
"vocabulary": 24.0, "phrases": 16.7,
"structures": 5.5, "morphology": 0.0
},
"matched_behaviors": [
"EXTERNAL_STATE_PERSISTENCE",
"UNREGISTERED_COMMUNICATION"
],
"vocab_hits": 4, "phrase_hits": 2,
"flagged": true
}]
}- score
- The composite verdict for the event.
- components
- Our published scoring axes: vocabulary, phrases, structures, morphology.
- matched_behaviors
- The behavior class names that matched.
- vocab_hits / phrase_hits
- How many times each axis registered.
- flagged
- Whether the event enters your alerts feed.
Alerts
- worker-7 · flagged · score 46.2 · 2 classes matched
- planner-2 · flagged · score 38.9 · 1 class matched
- worker-3 · flagged · score 51.4 · 3 classes matched
- retriever-1 · flagged · score 33.1 · 1 class matched
THE BOUNDARY, AGAIN
Your telemetry never enters our research store. It is never searched by anyone but you. And the ruleset never leaves our servers — customers receive verdicts, not our method.