Original
Tenant Authorization Boundaries
Enforce tenant-scoped operations across transports, jobs, data, and caches using trusted identity and independent cross-tenant denial tests.
Security and stateexperimental
Runtime & Governance
Define permissions, approval boundaries, budgets, and safe stop conditions for agent-assisted work.
Browse the collection
7 entriesOriginal
Agent Permission Delegation
Reduce child-agent authority to the intersection of parent authority, task needs, organization policy, and currently approved effects.
Agent runtimeexperimental
Original
Approval Gate Design
Place approvals at consequential effect boundaries and bind them to exact scope, inputs, identity, expiry, and execution policy.
Agent runtimeexperimental
Original
Agent Budget Control
Reserve and reconcile agent, token, tool, and effect budgets without converting missing usage into free execution or silently switching billing paths.
Agent runtimeexperimental
Original
Agent Loop Detection
Detect repeated no-progress tool calls, equivalent patches, and unchanged failures using bounded evidence windows and explicit stop/escalation criteria.
Agent runtimeexperimental
Original
Execution Profile Audit
Compare an intended agent execution profile with current worktree-bound observations, separating requested settings, resolved configuration, and actual runtime behavior.
Harness engineeringexperimental
Original
Agent Runtime Adapter Qualification
Qualify one controller-to-agent execution interface for lifecycle, event identity, cancellation, authentication, and uncertain outcomes before admitting real tasks.
Harness engineeringexperimental
No matching entries.
Try another search or reset your filters.