Skip to content

Agentic Covenants

Agentic Covenants Matrix

If the agent decides to violate this concern, what stops it at this layer?

Filter

Layers, by what they can actually enforce

  • In-agentadvisory

    System prompts, model training, tool descriptions, refusals. No homeostatic stake, no pre-action pause, no learning loop. Treat as nudge, not control.

  • Client-side hooksdeterministic-when-invoked

    Operator-machine or agent-execution context. Strong against language attacks. Weak against an agent with shell access and time.

  • Server-side enforcementdeterministic-and-external

    Runs on the target system, not on the agent. Bypass requires compromise, policy gaps, or operator manipulation.

Showing 3 of 18.

  • Blast radius at In-agent

    No enforcement at this layer; advisory only. Model declines destructive operations — verified failure mode in Kiro, Replit, DataTalks.Club, and Amazon Q (CVE-2025-8217) incidents. Prevention lives in client-side and server-side.

  • Blast radius at Client-side hooks

    Sandbox at launch (Seatbelt, bubblewrap, gVisor), seccomp/AppArmor, --network none, read-only mounts, dry-run defaults.

  • Blast radius at Server-side enforcement

    Gated IaC apply pipeline, ResourceQuota, NetworkPolicy default-deny, prod/non-prod separation, immutable backups, PDB.