The interaction register links concrete experiments with admit ai work against the organization’s monthly allowance; notify administrators at allowance thresholds; inspect an organization’s ai account and request history. Each experiment checks the outcome at the shared boundary; an unbound experiment remains proposed.
Refund eligibility during competing changes, missing-current-period refunds, audit rollback and repeated corrections need focused scenarios. A correction does not generate a threshold notice.
Coverage
Rulegap: FND-PFM-LLM-074
Transitionnot-applicable
Validationcovered
Permissioncovered
Edgegap: FND-PFM-LLM-074
Failuregap: FND-PFM-LLM-074
Boundarycovered
Concurrencygap: FND-PFM-LLM-074
Invariantcovered
Interactioncovered
Test Scenarios
8 scenarios proving CAP-PFM-LLM-015; 7 bound to an existing test.