CLAIM-2026-07-27-02
Article 6 defines three tiers of agent decision authority: human-only for irreversible acts; agent-proposes-user-approves; and autonomous execution within an explicitly delegated scope, with the boundary documented before deployment.
Why it matters
The tiering is the reusable engineering frame — it maps one-to-one onto Approval Gate and Delegated Scope.
Sources
- SRC - Pebblous - China AI agent decision tiers