APromptAura
0

Customer testimonial mining and rewrite for credibility

auto-checked, 3 days old
AauraNovice

The prompt

0 copies
I have raw, messy customer feedback (reviews, support tickets, survey responses) below. Help me find and shape the strongest testimonials without fabricating anything. Raw feedback: raw_feedback_text Do this: 1. Identify the 3-5 strongest candidate quotes, ranked by specificity (a testimonial that names a specific number, before/after, or use case is far more credible than generic praise like 'great product, highly recommend'). 2. For each candidate, note whether it can be used verbatim or needs light editing for clarity, and show ONLY grammar/clarity edits, never add claims, numbers, or sentiment the customer didn't express. 3. Flag any quote that sounds strong but is actually too vague to be useful ('this changed everything for us') and explain why it won't perform in actual marketing use even though it sounds positive. 4. Suggest what specific follow-up question I could ask that customer to get a more specific, usable quote, if the raw material is thin. 5. Organize the good ones by which page/use case they're best suited for (homepage social proof vs. a specific feature page vs. a case study).

Run it in your model, then come back and report whether it worked, including the model and version.

Where it has been run

People and our automated sweep are counted separately. Only the People column is someone vouching for this prompt.

ModelVersionPeopleBrokeAutoLast
ClaudeHaiku 4.5001/13 days ago

Example output

Top candidate: 'We went from spending 6 hours a week on manual reconciliation to about 20 minutes' ranked highest for specificity, usable verbatim, no editing needed. Second candidate needed light cleanup only: original had a run-on sentence, split into two for readability, no content changed. Flagged as too vague despite positive tone: 'This tool is a game changer for our team,' recommend not using, it makes no falsifiable claim and reads as generic regardless of genuine enthusiasm. Suggested follow-up question for that customer: 'What specifically changed about your week because of this?' to extract something concrete. Placement recommendations: the reconciliation-time quote fits the homepage hero (broad, quantified, immediately credible); a more feature-specific quote about the reporting dashboard fits that feature's dedicated page instead.

0 comments

Sign in to comment or report what this prompt did for you.

Sign in

No comments yet. Run the prompt and report what you got.