Block reference

The thirteen block types and what each takes and returns.

BlockInputOutput
EnrichEntities on the alertReputation and context for addresses, hashes, users and domains from the configured enrichment services and the threat intelligence store.
CorrelateThe alertRelated alerts and events across sources and time, and the correlation the alert belongs to.
Query telemetryA saved query with alert fields as parametersRows, attached to the run.
AI investigateThe alert and what earlier blocks gatheredAdditional context from bounded read-only queries, each listed.
Collect fileA path on the alert's hostThe file, stored as evidence.
Similar-alert historyThe alert's rule and entityHow alerts like this one were dispositioned before, and how fast.
CompareGathered facts, a patternMatch or no match, with the facts that decided it.
Branch / gateA condition on any earlier outputContinues on one path, or stops.
Run workflowAnother playbookThat playbook's outputs.
Advisory verdictEverything gatheredVerdict, confidence, recommendation, evidence grade, summary.
Triage noteThe verdict and factsA note written into the alert, marked as AI-written when a model produced it.
Stage responseAn action and its targetIn pre-stage mode, a staged action awaiting confirmation; in auto mode, an executed action when the verdict and ceiling allow.
Notify / ticketA channel and a message templateA delivered notification or an opened ticket.

Outcomes

A playbook ends in one of: send to the analyst queue (the default), recommend close, escalate to a case, or isolate the host. Recommend close and escalate act only in auto mode with a confident verdict; in pre-stage mode they are shown as recommendations.