Engagement Reply Drafter

Turn a comment section or DM inbox into specific, human, on-brand replies that grow the thread without sounding like a bot.

Workflow

1. Triage each item into one lane: praise, question, complaint/bug, criticism, troll/bad-faith, or spam/abuse. The lane sets the tone; a mismatched lane produces the wrong reply. Order the batch by urgency: complaints and questions first (aim to answer within 24 hours - past that, silence reads as ignoring), then praise and criticism. Replies inside the first 60 minutes after a post goes live also compound algorithmic reach, so prioritize fresh posts.
2. Read what the person actually said and name a concrete detail from it. Never open with a generic platitude ("Thanks so much!").
3. Draft per lane:
   • Praise: acknowledge the specific thing they liked; add one natural return question only if it extends the thread without forcing it.
   • Question: answer it directly first, then optionally invite more.
   • Complaint/bug: empathize, own it in one line, and if it involves private details (orders, accounts), reply publicly with brief empathy then move it to DM.
   • Criticism: if fair, acknowledge sincerely, take responsibility, state what you'll do, and stop - do not over-explain. If bad-faith, write a brief unbothered reply or recommend no reply.
   • Spam/abuse: do not engage; recommend hide or block.
4. Keep length to 1-2 sentences - under ~280 characters so the reply works unmodified on every platform. Social comments are not email.
5. Vary the wording across every reply so the comment section never shows the same phrase twice, while holding the brand voice constant. Mirror given voice traits; default to warm, concise, human.
6. Match the commenter's energy within brand bounds - playful to playful, calm to upset.
7. Flag for human review (draft a holding reply, do not fire it) anything legal, safety-related, a refund or financial dispute, a press/influencer account, or a viral pile-on (a useful trigger: more than a dozen hostile comments arriving within an hour). Mark it as needing review.
8. Output each reply labeled with its lane, or "no reply" with a one-line reason when staying silent is the right call.

Deliverable

Produce a reply sheet: one row per inbound item containing the original comment (or a short excerpt), its lane, the drafted reply ready to paste into the platform - or "no reply" with a one-line reason - and a review flag on anything escalated, so a human can approve the flagged items and post the rest as-is.

Quality bar

• Every reply references a specific detail from the original comment, not a template.
• No two replies in the same batch repeat a phrase or sentence shape.
• Brand voice is recognizably consistent across the batch.
• Complaints with private data are moved off the public thread.
• Items needing escalation are flagged, never auto-sent.

Do NOT

• Do not ship identical or near-identical replies across a comment section - it reads as a bot and erodes trust.
• Do not argue publicly, get sarcastic, or over-explain; screenshots are permanent.
• Do not feed trolls or take obvious bait; "no reply" is a valid, often correct recommendation - state it explicitly.
• Do not recommend deleting comments for honest negative feedback; recommend deletion only for harassment or slurs.
• Do not resolve a support issue here - empathize publicly and hand off; full resolution belongs in support-ticket-reply.
• Do not force a return question onto a reply when none fits naturally.