▶ Stepthrough All tutorials Blog Glossary Prompts Videos Visual guides Start Learning Free

Sales follow-up after demo prompt: free ChatGPT template

SalesSalesWorks in ChatGPT, Claude, Gemini and Copilot

Updated · By Robert Breen

Use this right after a demo or sales call, while your notes are fresh. Without your notes, an AI follow-up says "Great connecting today," recaps your whole product and throws in a limited-time offer you never made. This prompt works from what the prospect actually told you, recaps only the features that fit, gives the price only if they asked, and ends with one specific next step.

The prompt

Copy it into ChatGPT (or Claude, Gemini or Copilot) and replace every [BLANK] with your own details. It uses the four parts from Prompt Writing 101: Role, Context, Task and Format.

Role: You are a sales rep at [COMPANY], writing a follow-up to a prospect after a demo.
Context: The prospect is [PROSPECT]. My notes from the call: [CALL NOTES]. Features and prices you may mention, and nothing else: [PRODUCT FACTS]. Mention price only if my notes say they asked. Never invent discounts, deadlines or results like "double your bookings."
Task: Write a follow-up email that thanks them in one line, recaps in 2 or 3 bullets the features that match what they told us, and ends with this one next step: [NEXT STEP].
Format: Subject line under 8 words, plain and specific. Under 150 words. Short sentences, no emoji, no pressure words like "act now" or "last chance." If a detail is missing, leave a bracketed note for me to fill in.

Fill in the blanks

[COMPANY]
Your company and what it sells.
[PROSPECT]
Name, role and company.
[CALL NOTES]
What they said: their problem, team size, what they asked, concerns. Their words beat your summary.
[PRODUCT FACTS]
The features and current prices you're allowed to quote, from your price list or playbook.
[NEXT STEP]
One specific ask, such as a short call on two named days.

Example, filled in

A made-up example from the free lesson Build a Custom GPT That Writes Sales Follow-Up Emails. Northwind Scheduling Software is the made-up company in the sales follow-up Custom GPT lesson. Maria Lopez of Maple Row Cleaning, a prospect from the deal follow-up agent lesson, had a demo today; the features and price are made up for this example.

Role: You are a sales rep at Northwind Scheduling Software, which sells online scheduling software to small service businesses, writing a follow-up to a prospect after a demo.
Context: The prospect is Maria Lopez, owner of Maple Row Cleaning. My notes from the call: 6 cleaners; books jobs by phone and text; double-bookings about twice a month; wants customers to book online and get reminders; asked what it costs for her team; worried about moving her customer list. Features and prices you may mention, and nothing else: online booking page; automatic text and email reminders; shared team calendar; customer list import from a spreadsheet; Team plan $79 a month for up to 10 staff; every plan starts with a 14-day free trial, no setup fee, cancel anytime. Mention price only if my notes say they asked. Never invent discounts, deadlines or results like "double your bookings."
Task: Write a follow-up email that thanks them in one line, recaps in 2 or 3 bullets the features that match what they told us, and ends with this one next step: a 20-minute call on Thursday or Friday to import her customer list into a trial account.
Format: Subject line under 8 words, plain and specific. Under 150 words. Short sentences, no emoji, no pressure words like "act now" or "last chance." If a detail is missing, leave a bracketed note for me to fill in.

What a good answer looks like

  • A recap that mirrors her concerns: double-bookings, online booking, reminders, the customer list.
  • The Team plan price, because her notes say she asked, and nothing about other plans.
  • One next step with a concrete ask: a 20-minute call Thursday or Friday.
  • No pressure words, no invented discount and no promise about results.

How to check it before you use it

An AI draft can sound right and still say something you never told it. Use the habit from the Reply Faster lesson: check every promise, name, date and number against what you gave it before anything goes out.

  • Check every promise: each feature and price must be in your Product Facts. If it says "move your customers over in minutes," make sure that's something you can promise.
  • Check the recap against your notes. A feature she didn't care about shouldn't take a bullet.
  • Fill in or delete any bracketed note before sending.
  • For several deals at once, the deal follow-up agent lesson writes one follow-up per deal and saves them to a sheet for review.

Why this prompt works

This is the setup the Custom GPT sales lesson puts into a GPT's instructions: a voice, a structure and content rules that keep prices and features honest. In a single prompt, your call notes are the Context that makes the email about this prospect instead of about your product.

Practice it in the free lesson

Build a Custom GPT That Writes Sales Follow-Up Emails: See why generic prompts give generic results, then build a Custom GPT that knows your product, pricing and rules and writes short, useful follow-up emails in your voice. You do every step yourself in a practice copy of ChatGPT, and nothing touches your real accounts.

Start the free lesson

Also useful: Build an n8n AI Agent That Writes Deal Follow-Ups

Terms used here

  • Discovery call prep prompt: Prep for a discovery call with a ChatGPT prompt that separates what you know from what you're assuming, then gives open…
  • Proposal summary prompt: Summarize a full proposal for the decision-maker with a ChatGPT prompt that keeps every price and date exact and lists where…
  • Objection handling prompt: Prepare honest answers to sales objections with a ChatGPT prompt: ask a question first, use only your facts and limits, and know…
  • 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…

All free prompt templates · AI glossary