Review public-comment moderation flags
Reviews & approvals · Example outcome
The handoff
A private potentially harmful or abusive public comments flagged for moderator review review draft with source checks, uncertainty notes, and human approval status.
Keep in mind
Language classifiers can misread dialect, quotation, humor, or reclaimed terms. Use clear community rules, limit retention of commenter data, preserve the original context, provide an appeal path, escalate credible threats safely, and require a human moderator to approve every removal, restriction, or account action.
