Scope and Models
What the framework covers, the vocabulary it runs on, the threats it is built against, and the two instruments everything after it is scored on: the autonomy tiers and the maturity model.
Purpose and Scope
What the framework is for, the six design principles it rests on, who owns which part of it, and what it deliberately leaves out.
Definitions and Boundaries
Precise definitions for agent, tool, action boundary and blast radius — and the scoping trap that makes most agent inventories partial.
The Threat Model
Six structural properties that make agentic risk different from application risk, mapped to the OWASP Agentic Top 10 and six attack paths.
Autonomy Tiering: Deciding How Much Agency to Grant
Five tiers from advisory to privileged autonomous, with the approval authority and control set each one requires.
The Maturity Model
Five levels across ten domains, scored as the minimum rather than the average, with Level 2 as the minimum defensible bar.