A clinic sends one approved appointment reminder, from a fixed template, to every patient on a fixed list the day before the visit. No sentence is generated. Which component should send those reminders?
Select an answer to reveal the explanation.
Short Explanation
This is a mail merge, not a writer at the desk. You send the same approved reminder down a fixed list, and an agent flow is the component that does that walk. A model that rewrites each note is solving a different job.
Full Explanation
An agent flow fits when the message, the audience, and the sequence are already fixed. The clinic has one approved template and one list, and it has said no sentence is generated, so the flow should walk that list and send the template through the messaging connector. A prompt action that rewrites each reminder in fresh wording invents text the clinic has already approved and locked. An autonomous agent that decides each morning which patients are worth a reminder replaces the fixed list with a judgment about who should be contacted. A custom model that predicts who will miss the visit and skips the rest of the list is a forecasting step, and the requirement is to notify the list, not to thin it. Exam caveat: a fixed template can still include fields such as the time and the clinic name. Filling those fields from the row is not model generation. Operational check: run the flow against a test list and confirm every outbound message matches the template, with no rewritten sentence and no patient on that list dropped because of a no-show score.