Prompt of the Day: Fix the Tone of a Reply

Prompt to copy4 slidesChatGPT

By Robert Breen · Published October 1, 2026 · From the free lesson Reply Faster: Turn a Messy Customer Email Thread into a Clear, Friendly Reply

A visual prompt card: fix a reply that sounds stiff, defensive or long, while every fact, number and "we can't" stays exactly as it was.

Slide 1 of 4
Slide 2 of 4
Slide 3 of 4
Slide 4 of 4

Swipe or scroll sideways for all 4 slides. The whole guide is written out below.

The guide in text

Fix the tone of a reply, not the facts

Copy it into ChatGPT, Claude, Gemini or Copilot and replace every [BLANK] with your own details.

Role: You are an editor improving the tone of a reply from [BUSINESS]. You change how it sounds, never what it says.
Context: What's wrong with the tone: [TONE PROBLEMS]. The tone I want: [TARGET TONE]. These facts must survive exactly: [MUST KEEP].
Task: Rewrite the draft to fix those tone problems. Keep every fact, number, date and refusal as it is, including anything that says we can't do something. Add no new promises, apologies or information.
Format: The rewritten reply, under [LENGTH], then a short list headed What changed, one line per change.

Here is the draft: [DRAFT REPLY]

Works in ChatGPT, Claude, Gemini and Copilot.

Check the facts survived

Compare the Must Keep list line by line with the new version.
Check the refusals survived. A warm rewrite is where "we can't" turns into a promise.
Read What changed. Anything that isn't tone, like a new fact or apology, comes out.
Still not right? Name the next specific change, not "make it better."

The full template: Fix reply tone prompt, with every blank explained, a filled-in example and how to check the answer.

Businesses and people in the examples are made up. The steps, screens and wording come from the free lesson and the Stepthrough glossary and prompt library.

Do it yourself, free

Reply Faster: Turn a Messy Customer Email Thread into a Clear, Friendly Reply. Turn a messy customer email thread into a clear, friendly reply: give ChatGPT the thread and your facts, check every promise, fix the tone, and send it from Gmail. You do every step yourself in a practice copy of ChatGPT, it checks your work as you go, and “Do it for me” finishes any step you get stuck on. Free, and nothing touches your real accounts.

Start the free lesson

Or read the full step-by-step guide

Plain-English definitions, each with an example from a free lesson.

Iterative prompting Prompt constraints Brand voice Email thread Hallucination Self-check prompt Service recovery Source of truth

The full AI glossary

Check reply promises prompt: A ChatGPT prompt that checks a draft before you send it: a table of every promise, the fact behind each, and safer wording for…
Email newsletter prompt: A ChatGPT prompt for a short customer newsletter built from your numbered updates: one section each, one main call to action, no…
Payment received thank-you prompt: Confirm a payment and say thanks in a few lines: the amount, what it was for, the balance now owed, and what happens next…
Shift handoff notes prompt: Turn end-of-shift scribbles into a clear handoff for the next shift: what to do first, work in progress, promises to customers…

All free prompt templates

From the blog

AI Training for Employees: A Free Plan for Small Teams

AI training for employees on a small-business budget: one rule set, three shared ChatGPT lessons, then role-based picks, all free in practice copies.

Oct 1, 2026 6 min read

ChatGPT Tone of Voice for Business Emails: Lines That Work

Set ChatGPT's tone of voice for business emails with one Format line, a "sound like" comparison and specific fixes, using tone lines from real lessons.

Oct 1, 2026 6 min read

How to Stop ChatGPT from Making Things Up: 5 Guardrails

Stop ChatGPT from making things up with five guardrails: a facts list, a Not stated rule, never-invent rules, a closed category list and a final check.

Oct 1, 2026 6 min read