Hanzo
OpenapiRisk

Search exhaustively for the model shape that fits your own history

Search runs an exhaustive search for the model shape that best fits the caller organisation's own history, and answers 202 with the run to read back.

POST /v1/risk/search

Addresshttps://api.hanzo.ai/v1/risk/search
MethodPOST
OperationriskSearch
AuthAuthorization: Bearer $HANZO_API_KEY

Search runs an exhaustive search for the model shape that best fits the caller organisation's own history, and answers 202 with the run to read back.

Every candidate is replayed over that organisation's OWN feature surface in its own sandbox — its own aggregates, its own model, neither of them the live one — so a run cannot move a live threshold and cannot see another organisation's data. The result is the learning curve for each shape and the one that fit best, ranked on how closely it honoured the stated appetite, whether it warmed at all, whether it saturated, and how much of the coordinate space it left blind.

An empty history is REFUSED rather than reported as zero alerts, because "no alerts" is exactly what a quiet model looks like.

Request

1 field, body application/json (required).

FieldInTypeRequiredDescription
daysbodyintegerDays is how much of the organisation's own history to replay, 1 to 400.

Response

StatusBodyMeaning
202riskSearchRunaccepted

202 body — 3 fields.

FieldInTypeAlwaysDescription
candidatesbodyintegerCandidates is how many model shapes will be tried.
eventsbodyintegerEvents is how much of the organisation's own history the run will replay.
idbodystringID addresses the run.

Failure carries the platform error shape — see Errors.

Examples

hanzo risk search create

Risk API · All Hanzo APIs · Interactive reference

How is this guide?

On this page