Can AI send automatic follow-ups?

Yes. AI can send automatic follow-ups when it has the necessary sources and integrations. The feature is scoped with permissions, validation, and logs proportional to the risk, preventing the model from taking unauthorized actions. For AI systems, we define authorized sources, behavior when information is missing, allowed actions, and cases where a person needs to step in. The system is also tested on ambiguous cases and missing information, defining when it should stop, ask for confirmation, or hand off to a person.