Four-Layer Agent Containment Stack
The full containment stack in one diagram: sandbox, permission gate, HITL approval and SIEM audit applied in sequence around a single dangerous tool call.
Independent Action Verification Workflow
Rule 3 in practice: the agent that acts emits the action trace, a separate verification lane confirms the effect, and only a human closes the case.
Full FlowZap Code
Copy and paste the following FlowZap code into a project in your FlowZap account to see this template diagram.
execution { # Execution
n1: circle label:"Start"
n2: rectangle label:"Isolate the endpoint"
n3: rectangle label:"Emit the action trace"
n1.handle(right) -> n2.handle(left)
n2.handle(right) -> n3.handle(left)
n3.handle(bottom) -> verification.n4.handle(top) [label="Trace and post-action state"]
}
verification { # Verification
n4: rectangle label:"Read independent telemetry"
n5: diamond label:"Effect confirmed"
n6: rectangle label:"Close the case"
n7: circle label:"End"
n4.handle(right) -> n5.handle(left)
n5.handle(right) -> n6.handle(left) [label="yes"]
n6.handle(right) -> n7.handle(left)
n5.handle(bottom) -> human.n8.handle(top) [label="no"]
}
human { # Human
n8: rectangle label:"Re-authorise a second attempt"
n8.handle(bottom) -> execution.n2.handle(bottom) [label="Retry by another agent"]
}
Install the MCP packagenpm install -g flowzap-mcpMCP documentation
Related templates
HITL Approval Containment Workflow
Layer 3 of the agent containment stack: dangerous tool calls are suspended and sent to a human reviewer, who approves or aborts the operation before anything executes.
Audit Logging & SIEM Containment Workflow
Layer 4 of the agent containment stack: arguments are sanitized, secrets stripped and the action trace written to the SIEM before execution continues.
Patch Closure Proof Workflow
Closing-proof workflow across detection, remediation and assurance: measure the fix rather than the reaction, rate the outage risk and refuse closure without evidence.
Agent Mandate Scope Enforcement Workflow
Consent is not a mandate: a third-party agent's requested scope is compared to the customer mandate before read-only access is granted, and every access event is audited.
Agent Sandbox Containment Workflow
Layer 1 of the agent containment stack: every tool call executes in an ephemeral container, and any path outside the workspace is denied and logged as a security event.