Four operational probes a Moral Alignment Audit runs on a deployed system — normative coherence, scope drift, justification collapse, harm asymmetry — and how scoring maps to severity tiers.

A safety-first framing of AI alignment gives auditors a checklist and deployers a feeling. It is not a foundation. To build autonomous systems whose judgments survive contact with real people, we have to ground them in normative ethics — explicitly, defensibly, and operationally.