Skip to main content

​
Core Concepts

​
The Governance Loop

ABS operates on a continuous loop of Monitor, Evaluate, and Act.
  1. Monitor: Capture events from agents (Prompts, Tool Calls, API Requests).
  2. Evaluate: Run events through the Policy Engine and Trust Layer.
  3. Act: Enforce the decision (Allow, Block, Redact, Escalate).

​
Trust Hierarchy

Policies are applied in layers:
  1. Kernel Layer (Highest): Immutable invariants (e.g., “Never expose private keys”).
  2. Profile Layer: Domain-specific rules (e.g., “Financial”, “Healthcare”).
  3. Workspace Layer: Team specific rules (e.g., “Dev Environment allow-list”).

​
The Envelope Protocol

All decisions are wrapped in a Decision Envelope (ADR-008). This ensures that every Allow/Block decision is:
  • Cryptographically Signed: Cannot be forged.
  • Traceable: Linked to a specific Event ID and Trace ID.
  • Auditable: Stored in the immutable Write-Ahead Log.