How does the platform capture human-in-the-loop interventions for regulated workflows that require manual approval?

Human-in-the-loop checkpoints are managed by pausing durable execution at designated steps, awaiting human input while preserving full state. Once the reviewer responds, the platform records their identity, decision, and timestamp as a signed step within the verifiable execution record. This produces an immutable audit trail for auditors, proving human consultation at the required point. It does not validate the quality or business appropriateness of the human choice.