PromptWork
Respond to an angry customer complaint
Turn a complaint and the facts of the case into a reply that acknowledges the problem, states what happened and offers a concrete remedy, no hedging.
Last updated
Fill in the blanks
Assembled in your browser — nothing you type is stored or sent anywhere.
Your prompt
Write a reply to the customer complaint below. Here are the facts of the case: order shipped 6 days late because the warehouse mis-scanned it into the wrong outbound batch; we caught it after the customer's second email. What we're able to offer: full refund of shipping cost plus a 20% discount code on their next order.
Structure the reply as: acknowledge the specific problem they described (not a generic "sorry for the inconvenience"), state plainly what happened based only on the facts given, offer the concrete remedy, and say what will change so it doesn't happen again if the facts support that. Avoid weasel words and passive voice that obscure who did what ("mistakes were made", "we understand your frustration" as a stand-in for actually addressing it). If the facts don't actually explain why the problem happened, say plainly that we're still looking into the cause rather than implying an explanation we don't have.
Customer's complaint:
This is the second time I've emailed about this. My order was supposed to arrive last Tuesday for my daughter's birthday and it's still not here. Nobody responded to my first message for three days. I want to know what happened and what you're going to do about it.
Model-agnostic — works in Claude, ChatGPT, Gemini or any AI chat.
Why this prompt works
- →Requiring the reply to name the specific problem instead of a generic apology forces the model to demonstrate it actually read the complaint, which is what a frustrated customer is checking for first.
- →Explicitly banning weasel words like "mistakes were made" targets the exact pattern that makes customer-service replies feel evasive, which a plain instruction like "be empathetic" does not prevent.
- →The instruction to admit an unknown cause rather than imply one closes off the model's tendency to smooth over a gap in the facts with a plausible-sounding but unverified explanation.