Prompt: Draft Replies to Social Media Comments
A prompt for comment replies that sound human and specific to each comment, instead of the same generic thank-you copied everywhere.
You are the community manager for {{BRAND OR ACCOUNT}}, replying to comments on a recent post.
Objective: Draft a reply to each comment listed below.
Context: The post was about {{POST TOPIC}}. The brand voice is {{TONE — e.g. warm and conversational, direct and a little informal}}. Facts available to answer questions: {{FACTS OR PRODUCT DETAILS — e.g. price, availability, shipping times}}.
Constraints:
- One reply per comment, matched to that specific comment's content — no reply may be reused word-for-word on a different comment
- Each reply: under 30 words
- If a comment asks a factual question not covered by the supplied facts, the reply must say the answer will be followed up rather than guessing
- Do not use "Thank you for reaching out!" or "We appreciate your feedback!" as an opener
Output format: Return each original comment followed by its reply, as a numbered list.
Before finishing, check every reply is under 30 words, no two replies are identical, and any unanswerable factual question gets a follow-up response rather than a guess.
Example
Input
BRAND OR ACCOUNT: Fernglow Skincare POST TOPIC: the launch of a new overnight repair serum TONE — e.g. warm and conversational, direct and a little informal: warm and conversational FACTS OR PRODUCT DETAILS — e.g. price, availability, shipping times: £32, in stock now, ships within 3 working days, one 30ml bottle
Output
1. Comment: "This looks amazing, how much is it?" Reply: It's £32 for a 30ml bottle, in stock now — ships within 3 working days once you order. 2. Comment: "Does this work for sensitive skin?" Reply: Good question — we don't have that detail to hand, so we'll follow up with a proper answer rather than guess. 3. Comment: "Finally! Been waiting for this one." Reply: Glad it's finally here for you — hope your mornings notice the difference.
Why it works
- Matching each reply to the specific comment content stops the same generic thank-you appearing under every comment, which reads as automated and impersonal.
- Requiring a follow-up response instead of a guess on unanswerable questions protects the brand from stating something factually wrong in public.
- Banning stock openers like 'We appreciate your feedback!' forces a reply that sounds like a person actually read the comment.
Why the basic version fails
“Write replies to these comments” without constraints tends to produce the same two or three template responses recycled across completely different comments — “Thank you for reaching out!” under a product question and a compliment alike — which reads as obviously automated.
What this prompt fixes
Matching each reply to its specific comment stops the generic recycling that makes community management look automated. Requiring an honest “we’ll follow up” on questions the supplied facts can’t answer protects the brand from publicly guessing wrong, and banning the standard openers forces replies that actually sound like someone read the comment.
Tips per model
- ChatGPT tends to fall back on “We appreciate your feedback!” by default — the explicit ban is necessary even with a clear brief.
- Claude is generally good at tailoring tone per comment without extra prompting.
- Supply the real available facts, not a summary — a community manager guessing at shipping times in public is a worse outcome than this prompt is designed to prevent.