⏸️ Should This Be Automated?

Before an agent sends, rejects, suspends, accuses, publishes, or escalates, check whether a machine should be doing it at all. Should This Be Automated? gives agent developers, operations teams, support leaders, and policy owners before a people-facing action is automated. a bounded, structured review built around observable evidence, calibrated inference, alternative explanations, missing context, and stable verdicts. Its specific rubric covers irreversibility, vulnerability, power imbalance, appealability, factual dispute, recipient preference, public exposure. It refuses emotional-leverage optimization, diagnosis, protected-trait inference, retaliation, and non-consensual disclosure. High-stakes or irreversible cases receive an explicit human-review recommendation. The package performs no network request, publication, message delivery, purchase, account change, or claim to know another person's inner state.