Customer Review Response Generator
Draft personalized, sentiment-aware email responses to customer reviews in seconds.
Customise & copy
Add the context you have. The prompt updates as you work.
The name of the customer who left the review
The star rating given by the customer
The overall sentiment of the customer feedback
Paste the exact review left by the customer
Your company name and relevant team or product context
Live prompt
5 fieldsAnalyze the following customer review and draft a personalized, professional email response. Review Details: - Customer Name: Jane Doe - Rating: 5 out of 5 stars - Sentiment/Type: Positive - Review Text: The product exceeded my expectations and shipping was incredibly fast! - Company Context: Acme SaaS Support Team Instructions: 1. Write a clear, professional subject line. 2. Include a personalized salutation using Jane Doe. 3. Directly acknowledge the specific points raised in the review text. 4. Match the tone to the review sentiment (empathetic and solution-oriented for negative/neutral; appreciative for positive). 5. Do not invent specific refund amounts, discount codes, or policies not provided. 6. Provide a professional sign-off representing Acme SaaS Support Team.
Proof before you use it
A real example
Tested on gemini-3.1-flash-lite on 2026-09-03
{
"customer_name": "Marcus Vance",
"review_rating": "2",
"company_context": "Apex Mobile App Support",
"customer_review": "The mobile app crashed three times today while I was trying to submit my weekly report. Very frustrating experience.",
"review_sentiment": "Negative"
}A small ritual that works
How to use it
- 01Input the customer's name, rating, and the review text.
- 02Select the sentiment (Positive, Negative, or Neutral).
- 03Provide your company name and context to ensure brand alignment.
- 04Review the generated draft and send it directly to the customer.
Why it works
The prompt establishes clear constraints, such as matching the tone to the review sentiment, utilizing specific variables for context, and prohibiting the invention of unsupported details like refund amounts, discount codes, or policies.
Where it fails
INSUFFICIENT_EVIDENCE
Customisation tips
Ensure the customer review text and company context variables are populated with accurate, specific details so the drafted response can directly address the points raised without requiring the model to extrapolate operational actions.
Watch-outs
- Avoid politeness padding and overly enthusiastic or hype-like wording in the generated response.
- Do not make unsupported operational claims, such as stating that a technical team is currently investigating an issue when that action is not provided in the context.
- Ensure the model does not include generic claims or filler text beyond the actual review details.
Works in
Was this useful?
Submit your variation
If your version helps, it may be published with your name and a link back to you.
Want to make AI useful across your team? Explore Atul's training.