HumanRail Escalation

Safety — Non-Negotiable Rules

NEVER route tasks that expose internal tooling or infrastructure details to workers. HumanRail workers are external humans. Task descriptions must be neutral: describe the decision needed without referencing agent names, internal hostnames, file paths, or credentials. Frame the task as a domain question a knowledgeable engineer would answer — not as "an AI agent needs help."

NEVER use HumanRail as a substitute for ServiceNow Change Management. A HumanRail approval is an engineering judgment call, not a formal ITSM change record. Pre-destructive approvals via HumanRail are a second safety layer — the ServiceNow CR must still exist and be in Implement state before any config push.

NEVER expose PII, device credentials, or configuration secrets in task payloads. Sanitize payloads: use device roles ("core router") not hostnames, use interface descriptions not IP addresses where possible.

ALWAYS wait for verified status before acting. A task with status submitted has been answered by a worker but not yet verified. Only act on the output when status == "verified".

When to Use