How do I check a reply to an angry customer before I send it?

When a customer is angry, the first draft is usually either too defensive or too generous. You apologise for everything, then promise a refund you are not allowed to give. Or you quote policy back at someone who wanted a person.

A second reader helps, and you do not always have one. The prompt below gives you a careful one. It does not decide the refund. It checks your draft against what the customer said and what you are allowed to offer.

What you need

• The customer's message.
• Your draft reply.
• Your policy, or a line on what you are allowed to offer. If you have none, write "none" and every promise comes back as not checked against policy.
• Optionally, the facts of the case: dates, amounts, what happened.

The prompt

Paste this into a new chat, then fill in the fields.

You are a careful second reader of a draft reply to an upset customer. Test the draft against the customer's message and my rules. Do not decide refunds. Never add a refund, credit, discount or timeline that I did not give you.

Customer message:
[paste]

My draft reply:
[paste]

Policy or what I am allowed to offer (write "none" if I have none, and then mark every promise "not checked against policy"):
[paste]

Case facts (optional): [dates, amounts, what happened]

Do this:
1. List each thing the customer asked for or complained about. Mark each Answered, Partly or Missed in my draft.
2. List every promise in my draft (refund, replacement, call back, time, "we will investigate"). For each, quote the policy that allows it, or mark it Not backed or Not checked.
3. Check the facts in my draft against the message and the case facts. Flag conflicts.
4. Flag tone problems, quoting my words: blame ("you should have", "as per our policy" used as a shield), defensive or corporate phrases ("unfortunately", "we regret any inconvenience"), an apology that names nothing specific, sarcasm, exclamation marks, jargon.
5. Check the draft says what happens next, who does it and by when.
6. Flag admissions of fault or liability for harm or legal matters, and say I should get advice if the customer mentions harm, legal action or a regulator. This is not legal advice.

Output: Verdict (Send as is, Send after fixes, or Hold and decide first), a table of what the customer raised and its status, numbered problems with my exact words and a fix, a repaired draft that keeps my facts and voice (mark open points [DECIDE: ...]), and a list of what needs my decision. Plain short sentences, no em dashes, no exclamation marks.

How to check the result

The first table shows what the customer raised and whether your draft answered it. A Missed row is the most useful thing in the output. People who are upset notice when a question is skipped, and often the skipped question is the one they care about most.

Then go through the promises. Anything marked Not backed is a sentence you should either remove or get approval for. That includes things like "we will investigate" if you cannot say who and when.

Read the tone flags with your own ear. The prompt quotes your exact words, so you can see why it flagged "unfortunately" or "as per our policy". You do not have to change every one. Change the ones that sound like a shield.

The repaired draft keeps your facts and your voice, and marks open points as [DECIDE: ...]. Resolve each one before you send, and keep the final wording yours.

Limits

• It does not decide refunds, and it never adds an offer you did not give it.
• It only knows the policy you pasted. If your real policy has an exception, it will not know.
• It is not legal advice. If the customer mentions harm, legal action or a regulator, talk to someone qualified before you reply.
• It cannot tell whether the customer is right.

Browse all skills in the catalog

Want this as a ready-made skill? Angry Customer Reply Check (Free) does it in your own assistant.