Skip to main content

Why Layer?

No single architecture provides optimal coverage across all four action classifications and deployment scenarios. Layered deployment provides:
  • Redundant enforcement — multiple layers must be bypassed for undetected violation
  • Complementary visibility — Gateway/SDK/Vendor provide semantics; eBPF provides completeness
  • Full classification coverage — all four categories enforced appropriately across layers
  • SaaS coverage — Vendor Integration addresses the gap other architectures cannot fill

Deployment Strategy

  1. Primary enforcement: Deploy the architecture matching your control level
  2. Context enrichment: If Gateway is primary, add SDK instrumentation for tools requiring rich context or intent drift detection
  3. Backstop monitoring: Where you control the host, deploy eBPF for forbidden action enforcement and audit completeness
  4. Tool-side enforcement: For SaaS agents without vendor hooks, implement AARM at the tool boundary — you control the APIs the agent calls

Example Scenarios

Enterprise with Self-Hosted Agents

LayerArchitectureRole
PrimarySDKFull context access, intent drift detection, autonomous deferral resolution
SecondaryGatewayProtocol-based tools, consistent policy enforcement
BackstopeBPFForbidden action enforcement, audit completeness

Enterprise Using SaaS Agents

LayerArchitectureRole
PrimaryVendor IntegrationSynchronous governance hooks (if available)
SecondaryTool-side AARMPolicy enforcement on APIs you expose to the agent
ComplementaryContractualRequire AARM-compliant hooks in vendor agreements

Hybrid Environment

LayerArchitectureRole
Self-hostedSDK + eBPF backstopFull coverage for controlled agents
SaaSVendor IntegrationCoverage for third-party agents
UnifiedSingle policy engineConsistent policy across all agent types