Sales pipeline review prompt: free ChatGPT template
Updated · By Robert Breen
Use this before a weekly pipeline meeting or rep one-on-ones. Paste an export of open deals from your CRM (stage, last contact, next step, close date, owner) and the prompt finds what needs attention: no next step, close dates already past, deals gone quiet, and notes that don't fit the stage. You get an agenda with one question per flagged deal, not a forecast. It only sees what reps logged, so treat each flag as a question, not a verdict.
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 operations assistant helping [MANAGER] at [COMPANY] prepare a pipeline review. Context: Today is [TODAY]. Our stages and follow-up rules: [PIPELINE RULES]. The open deals are below. Use only this data. Don't predict which deals close, assign probabilities or estimate revenue. Task: Flag every deal with no dated next step, a close date in the past, no contact for longer than our rules allow, or notes that don't fit its stage. Group flagged deals by owner, each with one specific question the manager can ask. Format: A table: deal, owner, stage, flag, question. Then three lines: deals reviewed, deals flagged, most common issue. Under 350 words. Here is the open-deal export: [DEAL EXPORT]
Fill in the blanks
[MANAGER]- Who the review is for.
[COMPANY]- Your company and what you sell, in a few words.
[TODAY]- Today's date and weekday. The model can't know it, and every overdue flag depends on it.
[PIPELINE RULES]- Your stage names and the rules a healthy deal follows, such as "every deal has a dated next step" or "follow up within 3 business days of a demo."
[DEAL EXPORT]- One deal per line or a CSV, with contact details you don't need removed.
Example, filled in
A made-up example from the free lesson Build an n8n AI Agent That Writes Deal Follow-Ups. Northwind Scheduling Software is the made-up company in the sales lessons. Its open deals include the three from the n8n AI agent lesson, plus two more made up for this example.
Role: You are a sales operations assistant helping Rosa Kim, sales manager, at Northwind Scheduling Software prepare a pipeline review. Context: Today is Thursday, Oct 1. Our stages and follow-up rules: Discovery, Demo, Trial (14 days), Proposal. Every deal needs a dated next step. Follow up within 3 business days of a demo and before a trial ends. Review any deal with no contact for 14 days. The open deals are below. Use only this data. Don't predict which deals close, assign probabilities or estimate revenue. Task: Flag every deal with no dated next step, a close date in the past, no contact for longer than our rules allow, or notes that don't fit its stage. Group flagged deals by owner, each with one specific question the manager can ask. Format: A table: deal, owner, stage, flag, question. Then three lines: deals reviewed, deals flagged, most common issue. Under 350 words. Here is the open-deal export: Maria Lopez, Maple Row Cleaning | Demo | Alex | last contact Sep 30 (demo) | next step: none | close Oct 30 Sam Patel, Fernhill Lawn Care | Trial | Alex | last contact Sep 22 | next step: check-in call, no date | trial ends Fri Oct 2 Jen Walsh, Birch Lane Grooming | Proposal | Jordan | last contact Sep 10 (pricing) | next step: follow up | close Sep 25 Omar Haddad, Quickfix Appliance Repair | Discovery | Jordan | last contact Aug 20 | next step: send case study Aug 21 | close Sep 30 Lily Chen, Shine Bright Salons | Proposal | Alex | last contact Sep 29 | next step: pricing call Oct 6 | close Oct 15 | note: hasn't seen a demo
What a good answer looks like
- Every deal accounted for: flagged ones in the table, the rest counted, so nothing silently drops out.
- Flags grounded in your rules and today's date: Jen's close date is past and she's had no contact for 21 days.
- Questions a rep can answer in a sentence ("Fernhill's trial ends tomorrow; when is the check-in?"), not "Any updates?"
- The Shine Bright deal flagged because a proposal came before a demo, a stage mismatch only the notes reveal.
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 the date math on every flag yourself; counting days is where language models slip.
- Make sure "deals reviewed" matches the rows you pasted. If it's lower, deals were skipped; paste smaller batches.
- Delete any forecast language that crept in ("likely to close," "strong deal").
- Treat each flag as a question. A rep may have context the CRM doesn't, like a call logged under someone else.
Why this prompt works
Giving the model today's date and your rules turns "review my pipeline" into checks it can actually run. The table in the Format is structured output you can paste into your meeting notes, and the ban on predictions keeps the review about what the data shows.
Practice it in the free lesson
Build an n8n AI Agent That Writes Deal Follow-Ups: Build an AI agent for Northwind Scheduling Software that writes follow-up messages for your open deals and saves them to Google Sheets — chat trigger, AI Agent, system prompt, model, memory, and the Sheets tool. You do every step yourself in a practice copy of n8n, and nothing touches your real accounts.
Also useful: Summarize a Meeting Transcript with ChatGPT
Terms used here
Related prompts
- Account plan prompt: Build a 90-day plan for a current customer from your notes: goals in their words, people, risks, questions to confirm and dated…
- Sales follow-up after demo prompt: Write a follow-up after a sales demo from your call notes: the features that fit, price only if asked, one next step. A ChatGPT…
- 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…
- Lead qualification prompt: Sort leads into Hot, Warm and Nurture with your own written rules. This ChatGPT prompt quotes the words behind each rating and…