# KPI commentary prompt: free ChatGPT template

> Explain a month's numbers in plain words: what moved, likely reasons you confirm, what to watch next, and no conclusions the data can't support.

Source: https://learn.ynteractive.com/content/prompts/kpi-commentary-prompt · Updated 2026-10-02 · Free from Stepthrough (https://learn.ynteractive.com)

[Reports and planning](https://learn.ynteractive.com/content/prompts#job-reports-and-planning) · [Operations](https://learn.ynteractive.com/content/prompts#industry-operations) · [Finance](https://learn.ynteractive.com/content/prompts#industry-finance) · Works in ChatGPT, Claude, Gemini and Copilot

Updated October 2, 2026 · By [Robert Breen](https://learn.ynteractive.com/content/about)

Use this when you have the monthly numbers and the leadership team wants "what happened and why" in a paragraph, not a spreadsheet. The prompt reads your figures, states what moved and by how much, and offers possible reasons for you to confirm. It also separates what the numbers show from what you only suspect, which is the part busy writers skip. The reasons are hypotheses, so check them with the people who ran the work before you present them.

**Have a professional review it.** This prompt helps you explain your own numbers, not give financial advice. Have your accountant or financial advisor review anything you will act on.

## 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](https://learn.ynteractive.com/content/prompt-writing-101-role-context-task-format): Role, Context, Task and Format.

Copy prompt

```text
Role: You are a business analyst writing the monthly KPI commentary for [AUDIENCE].
Context: Here are this month's figures next to last month's and the target: [NUMBERS]. What I know happened this month: [EVENTS]. The numbers that matter most to this audience: [PRIORITIES].
Task: Write commentary with three parts. First, "What the numbers show": state each priority metric, the change from last month and from target, in plain words, using only the figures above. Second, "Possible reasons": link changes to the events I listed, and label anything else clearly as a guess to verify. Third, "What to watch next month": two or three items. Calculate changes carefully and show the arithmetic for any percentage. Don't claim a cause the events don't support.
Format: Under 250 words with the three headings, short paragraphs and no jargon. Then a separate "Numbers to double-check" list showing each calculation you made.
```

## Fill in the blanks

**`[AUDIENCE]`**

Who reads it, such as the owner or the leadership team.

**`[NUMBERS]`**

A small table or list: metric, this month, last month, target. Copy it from your report.

**`[EVENTS]`**

Things that actually happened: a promotion, a holiday, a system outage, a price change, a person on leave.

**`[PRIORITIES]`**

The two or three metrics your readers will ask about first.

## Example, filled in

**A made-up example** from the free lesson [Build an n8n AI Agent That Writes Deal Follow-Ups](https://learn.ynteractive.com/content/n8n-ai-agent-sales-deal-follow-ups). Northwind Scheduling Software is the made-up software company from the sales lessons. The numbers and events below are invented for this example.

Copy example

```text
Role: You are a business analyst writing the monthly KPI commentary for the sales leadership team.
Context: Here are this month's figures next to last month's and the target: demos booked 42 (last month 51, target 50); deals closed 9 (last month 8, target 10); average days to close 31 (last month 36, target 30); new pipeline value $118,000 (last month $140,000, target $135,000). What I know happened this month: the summer promotion ended on the 1st; one salesperson was out for two weeks; we started sending follow-ups within a day of every demo. The numbers that matter most to this audience: demos booked, deals closed and days to close.
Task: Write commentary with three parts. First, "What the numbers show": state each priority metric, the change from last month and from target, in plain words, using only the figures above. Second, "Possible reasons": link changes to the events I listed, and label anything else clearly as a guess to verify. Third, "What to watch next month": two or three items. Calculate changes carefully and show the arithmetic for any percentage. Don't claim a cause the events don't support.
Format: Under 250 words with the three headings, short paragraphs and no jargon. Then a separate "Numbers to double-check" list showing each calculation you made.
```

## What a good answer looks like

- Demos are stated as 42 against 51 last month and a target of 50, with the percentage drop shown.
- The faster close (31 days against 36) is tied to your new one-day follow-up habit, but described as a possible link.
- Guesses are labeled, such as "the end of the promotion may explain fewer demos".
- A "Numbers to double-check" list lets you verify every calculation in a minute.

## 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](https://learn.ynteractive.com/content/chatgpt-reply-to-customer-emails): check every promise, name, date and number against what you gave it before anything goes out.

- Recalculate each percentage from your own figures. AI makes arithmetic slips, and a wrong percent in a leadership email gets quoted.
- Ask the people who ran the work whether the possible reasons are real before you present them as facts.
- Make sure "target" and "last month" aren't swapped anywhere.
- Have your accountant or finance lead review any commentary that you will act on or share outside the company.

## Why this prompt works

Writers often turn correlation into a cause. Asking the model to label each reason as confirmed or a guess builds [human-in-the-loop](https://learn.ynteractive.com/content/glossary/human-in-the-loop) review into the draft itself.

## Practice it in the free lesson

**[Prompt Writing 101: Role, Context, Task, Format](https://learn.ynteractive.com/content/prompt-writing-101-role-context-task-format)**: Ask ChatGPT for the same customer email twice, once vaguely and once with a four-part prompt, and see exactly why structure gets a better answer. You do every step yourself in a practice copy of ChatGPT, and nothing touches your real accounts.

[Start the free lesson](https://learn.ynteractive.com/modules/prompt-writing-101)

Also useful: [Build an n8n AI Agent That Writes Deal Follow-Ups](https://learn.ynteractive.com/content/n8n-ai-agent-sales-deal-follow-ups)

## Terms used here

[Human in the loop](https://learn.ynteractive.com/content/glossary/human-in-the-loop) · [Self-check prompt](https://learn.ynteractive.com/content/glossary/self-verification) · [AI summarization](https://learn.ynteractive.com/content/glossary/ai-summarization)

## Related prompts

- [Budget variance explanation prompt](https://learn.ynteractive.com/content/prompts/budget-variance-explanation-prompt): Turn a budget-versus-actual report into a plain-English explanation of what moved and why, using only the reasons you give, plus…
- [Weekly leads summary prompt](https://learn.ynteractive.com/content/prompts/weekly-leads-summary-prompt): Paste a week of form leads from your Google Sheet and get counts by type, who is still waiting, patterns with row numbers and…
- [Weekly team report prompt](https://learn.ynteractive.com/content/prompts/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…

## More reports and planning prompts

- [Legal research memo outline prompt](https://learn.ynteractive.com/content/prompts/legal-research-memo-outline-prompt): Outline a legal research memo: question, facts, issues and the kinds of sources to find, with no invented cases and every…
- [NDA key terms summary prompt](https://learn.ynteractive.com/content/prompts/nda-key-terms-summary-prompt): Pull the key terms out of a nondisclosure agreement into one table with clause numbers, and flag anything beyond confidentiality…
- [Plain-English document summary prompt](https://learn.ynteractive.com/content/prompts/plain-english-document-summary-prompt): Paste a contract, lease or policy and get a plain-English summary with section numbers, every date and dollar amount, and…

[All free prompt templates](https://learn.ynteractive.com/content/prompts) · [AI glossary](https://learn.ynteractive.com/content/glossary)
