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

Client monthly report prompt: free ChatGPT template

Reports and planningMarketingWorks in ChatGPT, Claude, Gemini and Copilot

Updated · By Robert Breen

Use this at month end, when you have the analytics exports and a list of what your team did, and each client needs a readable report instead of a screenshot dump. It's for marketing agencies and freelancers. The prompt calculates changes only from the numbers you paste, keeps what you did separate from what happened, and doesn't claim one caused the other unless you can show it.

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 an account manager at [AGENCY], writing a monthly report for a busy business owner, not a marketer.
Context: Client and goals: [CLIENT AND GOALS]. This month's and last month's numbers: [METRICS]. Our work this month: [WORK LOG]. Next month's plan: [NEXT MONTH]. Use only these numbers and show how each change is calculated. Don't say our work caused a change unless the work log shows how we know.
Task: Write a three-sentence summary tied to the goals, a table of key numbers (last month, this month, change), what we did, what we think it means (labeled as our read), and next month's plan. If a goal has no number, write "Not in this month's data."
Format: Headings and one table, under 350 words. Define each metric in a few words the first time. No hype.

Fill in the blanks

[AGENCY]
Your agency's name.
[CLIENT AND GOALS]
Who the client is and what they hired you for, in their terms ("more booked appointments"), not yours.
[METRICS]
Both months, by channel, copied from the exports, with what each number measures. Note anything you don't track.
[WORK LOG]
What you changed or launched, with dates.
[NEXT MONTH]
Planned work, in a few bullets.

Example, filled in

A made-up example from the free lesson n8n AI Agent Tutorial: Save Social Media Ideas to Google Sheets. BrightPath Marketing is the made-up agency in the n8n AI agent lesson. One of its made-up clients is Lakeview Auto Repair, which tracks appointment form submissions but not the jobs that actually got booked.

Role: You are an account manager at BrightPath Marketing, writing a monthly report for a busy business owner, not a marketer.
Context: Client and goals: Lakeview Auto Repair wants more booked appointments from Google Search and its Google Business Profile. This month's and last month's numbers (September vs August): Google Ads clicks 412 vs 368; ad spend $1,150 vs $1,150; calls from ads 58 vs 47; Business Profile calls 96 vs 101; website appointment forms 31 vs 22. Booked jobs are not tracked. Our work this month: added a brake-service ad group Sep 8; rewrote the appointment page headline Sep 15; four Business Profile posts. Next month's plan: test a Saturday-hours ad; ask recent customers for reviews. Use only these numbers and show how each change is calculated. Don't say our work caused a change unless the work log shows how we know.
Task: Write a three-sentence summary tied to the goals, a table of key numbers (last month, this month, change), what we did, what we think it means (labeled as our read), and next month's plan. If a goal has no number, write "Not in this month's data."
Format: Headings and one table, under 350 words. Define each metric in a few words the first time. No hype.

What a good answer looks like

  • A table where every change can be recalculated: calls from ads 47 to 58 is up 11, about 23 percent.
  • The down number reported as plainly as the up ones: Business Profile calls fell from 101 to 96.
  • "Not in this month's data" for booked jobs, since only form submissions are tracked.
  • "Our read" clearly labeled, such as the new headline as a possible reason for more forms, not the proven cause.

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.

  • Recalculate every percentage yourself or in a spreadsheet; language models can slip on arithmetic.
  • Check every claim that links work to results. Unless you ran a test, rewrite "the headline increased forms" as a possible reason.
  • Confirm the date ranges match the exports, and that no other client's numbers ended up in the paste.
  • Read it as the owner: could they repeat the main point to a partner in one sentence?

Why this prompt works

Agency reports go wrong in two ways: invented precision and taking credit. "Show how each change is calculated" handles the first and the causal rule handles the second. "Not in this month's data" gives the model an honest exit, the same habit the meeting summary lesson teaches with "Not stated."

Practice it in the free lesson

Summarize a Meeting Transcript with ChatGPT: Paste a long meeting transcript into ChatGPT and get the decisions, an action items table with owners and due dates, and a follow-up email ready to send. You do every step yourself in a practice copy of ChatGPT, and nothing touches your real accounts.

Start the free lesson

Also useful: n8n AI Agent Tutorial: Save Social Media Ideas to Google Sheets

Terms used here

  • Weekly team report prompt: Turn this week's numbers and notes into a short owner report, with both weeks side by side so you can check the math, and no…
  • Project status update prompt: Write an honest project status update: On track, At risk or Off track with the reason, what's done, what's next, blockers and…
  • Case study draft prompt: Draft a customer case study from your notes, approved results and real quotes. This ChatGPT prompt marks gaps as MISSING instead…
  • Survey results summary prompt: Summarize survey responses into counted themes with exact quotes, standout comments and follow-up questions, without overstating…

All free prompt templates · AI glossary