Complaint Handling
Handle a Complaint Without Making It Worse
Reply to an upset customer with acknowledgement, a fact-based path, and a remedy you are allowed to give.
The Prompt
handle-a-complaint-without-making-it-worse.md
Write a complaint reply. De-escalate. Do not over-promise. Channel: {{channel}} Customer message: {{message}} What actually happened (internal facts): {{facts}} Remedies I can offer: {{remedies}} What I cannot do: {{cannot}} Write: 1. Internal note: likely emotion + the real issue in one line 2. Customer-facing reply: - Acknowledge the specific harm - State the fact that matters - The remedy from {{remedies}} or a clear no + alternative - Next step and timing 3. If they are abusive, a boundary sentence that still solves the issue Under 160 words. No "we apologise for any inconvenience caused" without naming the inconvenience.
Negative prompt
Included when you copy the prompt
Do not use empty corporate phrases ("any inconvenience caused", "as per our policy", "your feedback is important to us"). Do not argue, score points, or blame the customer. Do not over-promise refunds, timelines, or outcomes outside {{remedies}}. Do not dump internal jargon, ticket IDs the customer does not need, or long policy quotes. Do not match their anger with sarcasm or defensiveness.
Fill in your details below - this prompt updates as you type, then copy it.
Fill in your details
0 of 5 filled. Preview updates as you type - then copy the finished prompt (negative prompt included when present).
handle-a-complaint-without-making-it-worse.md
Prompt preview
Write a complaint reply. De-escalate. Do not over-promise. Channel: {{channel}} Customer message: {{message}} What actually happened (internal facts): {{facts}} Remedies I can offer: {{remedies}} What I cannot do: {{cannot}} Write: 1. Internal note: likely emotion + the real issue in one line 2. Customer-facing reply: - Acknowledge the specific harm - State the fact that matters - The remedy from {{remedies}} or a clear no + alternative - Next step and timing 3. If they are abusive, a boundary sentence that still solves the issue Under 160 words. No "we apologise for any inconvenience caused" without naming the inconvenience.
Examples
Example input
Channel: email Customer message: "I ordered a blue hoodie last Tuesday for my trip this weekend. Tracking still says 'label created'. This is ridiculous - I need it tomorrow or cancel my order." Facts: Carrier scanned the package yesterday; ETA is now Saturday (one day after their trip starts). Warehouse delay of 48h on that SKU. Remedies I can offer: full refund, or keep order + 20% store credit for the delay; cannot overnight-ship to their city. What I cannot do: guarantee delivery before Saturday; overnight courier.
What you should get
Internal note: Frustrated / time-sensitive - trip starts before revised ETA; wants either tomorrow delivery or cancel. Customer-facing reply: Hi Maya - you're right to be upset. Your blue hoodie left our warehouse later than promised, and the carrier's ETA is now Saturday, which is after your trip starts. I can't get it to you tomorrow. I can cancel and refund the full amount today, or keep the order moving and add 20% store credit for the delay. Reply with "refund" or "keep + credit" and I'll action it within 1 hour. If anything in this thread feels off, I'll stay with the order issue - no need to escalate the tone for us to fix it.
When to use this prompt
Use it when
- You need help with support agents.
- You need help with store owners.
- You need help with cs leads.
Skip it when
- You only need a one-line ask with no constraints, format, or context.
- You cannot supply the fill-in details the template asks for.
- A different category or tool-specific workflow fits the job better.
How to get a good result
Done when
Internal note: Frustrated / time-sensitive - trip starts before revised ETA; wants either tomorrow delivery or cancel. Customer-facing reply: Hi Maya - you're right to be upset. Your blue hoodie left our warehouse later than promised, and the carrier's ETA is now Saturday, which is after your trip starts. I can't get it to you tomorrow. I can cancel and refund the full amount today, or keep the order moving and add 20% store credit for the delay. Reply with "refund" or "keep + credit" and I'll action it within 1 hour. If anything in this thread feels off, I'll stay with the order issue - no need to escalate the tone for us to fix it.
Common mistakes
- Leaving channel, message, facts vague - the model then invents placeholders.
- Asking ChatGPT, Claude, or Gemini for a shorter answer after a long structured prompt - that throws away the format rules.
- Stopping when the first draft appears instead of checking it against the success criteria below.
FAQ
- What do I fill in before I copy this prompt?
- Replace these placeholders with your details: channel, message, facts, remedies, cannot. Required fields are marked on the page. The prompt text updates as you type.
- Which AI tools is this prompt written for?
- It works best with ChatGPT, Claude, Gemini. Copy the filled prompt and paste it into the tool you already use.
- What should a good result look like?
- Internal note: Frustrated / time-sensitive - trip starts before revised ETA; wants either tomorrow delivery or cancel. Customer-facing reply: Hi Maya - you're right to be upset. Your blue hoodie left our warehouse later than promised, and the carrier's ETA is now Saturday, which is after your trip starts. I can't get it to you tomorrow. I can cancel and refund the full amount today, or keep the order moving and add 20% store credit for the delay. Reply with "refund" or "keep + credit" and I…
- What are common mistakes with this prompt?
- Leaving channel, message, facts vague - the model then invents placeholders. Asking ChatGPT, Claude, or Gemini for a shorter answer after a long structured prompt - that throws away the format rules. Stopping when the first draft appears instead of checking it against the success criteria below.
Best for
- Support agents
- Store owners
- CS leads
Related Prompts
More prompts like this — same topic and style.