Angry Customer
Reply to an Angry Customer
A tighter de-escalation script for high-heat messages: calm tone, one remedy, one boundary.
The Prompt
reply-to-an-angry-customer.md
The customer is angry. Reply in a way a reasonable person would accept. Message: {{message}} Facts: {{facts}} Allowed remedy: {{remedy}} If they crossed a line (abuse): {{abuse}} Produce: 1. What not to say (3 phrases) 2. The reply (max 120 words): feeling → fact → remedy → next step 3. If {{abuse}} is yes, add one boundary and still offer the remedy through a channel No sarcasm. No "calm down". No blame-the-customer.
Negative prompt
Included when you copy the prompt
Do not say "calm down", "relax", "as I already explained", or "you're being unreasonable". Do not use sarcasm, ALL CAPS, or matching insults. Do not pile on multiple remedies or conditions. Do not blame the customer, the carrier, or "the system" without owning the next step. Do not threaten to close the ticket unless abuse is confirmed - and even then, still offer the remedy through a safe channel.
Fill in your details below - this prompt updates as you type, then copy it.
Fill in your details
0 of 4 filled. Preview updates as you type - then copy the finished prompt (negative prompt included when present).
reply-to-an-angry-customer.md
Prompt preview
The customer is angry. Reply in a way a reasonable person would accept. Message: {{message}} Facts: {{facts}} Allowed remedy: {{remedy}} If they crossed a line (abuse): {{abuse}} Produce: 1. What not to say (3 phrases) 2. The reply (max 120 words): feeling → fact → remedy → next step 3. If {{abuse}} is yes, add one boundary and still offer the remedy through a channel No sarcasm. No "calm down". No blame-the-customer.
Examples
Example input
Message: "This is the third time your app charged me. Fix it NOW or I'm calling my lawyer and posting everywhere. You're thieves." Facts: Duplicate charge from a retry bug on checkout; two of three charges already voided; one $49 charge still pending bank reversal (2 - 5 days). Allowed remedy: confirm the pending reversal + $15 goodwill credit once the void shows; escalate to billing lead if not cleared in 5 days. Abuse: yes - "thieves" + legal/public threat.
What you should get
What not to say: 1. "Calm down - it's only $49." 2. "Calling us thieves won't help your case." 3. "You should have checked your bank before messaging." Reply: I hear how angry this is - three charges for one order feels like theft, and I'm sorry we put you there. Two charges are already voided; the last $49 is in a bank reversal that usually clears in 2 - 5 days. I'll add a $15 goodwill credit as soon as that void posts, and if it isn't cleared in 5 days I'll escalate to our billing lead myself. I'm here to fix the billing. I'll keep helping on that - please drop the personal insults so we can stay on the account issue. Next step: I'll reply within 24 hours with the reversal status.
When to use this prompt
Use it when
- You need help with frontline support.
- You need help with founders doing support.
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
What not to say: 1. "Calm down - it's only $49." 2. "Calling us thieves won't help your case." 3. "You should have checked your bank before messaging." Reply: I hear how angry this is - three charges for one order feels like theft, and I'm sorry we put you there. Two charges are already voided; the last $49 is in a bank reversal that usually clears in 2 - 5 days. I'll add a $15 goodwill credit as soon as that void posts, and if it isn't cleared in 5 days I'll escalate to our billing lead myself. I'm here to fix the billing. I'll keep helping on that - please drop the personal insults so we can stay on the account issue. Next step: I'll reply within 24 hours with the reversal status.
Common mistakes
- Leaving message, facts, remedy 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: message, facts, remedy, abuse. 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?
- What not to say: 1. "Calm down - it's only $49." 2. "Calling us thieves won't help your case." 3. "You should have checked your bank before messaging." Reply: I hear how angry this is - three charges for one order feels like theft, and I'm sorry we put you there. Two charges are already voided; the last $49 is in a bank reversal that usually clears in 2 - 5 days. I'll add a $15 goodwill credit as soon as that void posts, and if it isn't cleared in 5 days I'll escalate to our billing lead mys…
- What are common mistakes with this prompt?
- Leaving message, facts, remedy 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
- Frontline support
- Founders doing support
Related Prompts
More prompts like this — same topic and style.