Skip to content

Rules of Engagement

Rules of Engagement (RoE) are the contract the Autonomous Security Agent must obey. Before the agent acts, you define what it may target, what it must never do, and what it’s trying to achieve. RoE plus runtime guardrails are what make autonomy safe.

BenefitCapabilityBusiness value
Bounded autonomyExplicit scope and constraintsThe agent can’t stray outside what you authorized
Clear intentDefined objectivesThe agent works toward your goal, not a generic one
AccountabilityRoE recorded and auditedDefensible record of what was permitted

The Rules of Engagement panel (under Autopilot) lets you set the engagement’s scope (allowed targets), constraints (forbidden actions, limits), and objectives. At runtime, a guardrails layer detects sensitive contexts — for example production or critical scope — and enforces the RoE on every step, alongside the per-phase Tool Matrix. The agent never grants itself elevated platform privileges, and tenant isolation always holds.

  1. Open Autopilot → Rules of Engagement.
  2. Define the scope, constraints, and objectives for the engagement.
  3. Start an agent session — it operates only within the RoE.
  4. Review the audit trail afterward to confirm compliance.
  • Keep scope as narrow as the objective allows.
  • Treat RoE as mandatory, not optional — never run an unbounded session.
  • Review the audit trail after every session.