← Back to Competitor & Market Research

Win-Loss Review

Find the patterns in a batch of deals you won and lost, with the count behind every percentage, three changes to test, and the questions to ask a buyer who chose someone else.

IntermediatePASTE & GODecision-making

win-loss · sales analysis · pipeline · closed deals · customer research · conversion

Pro tip

Include the deals that went quiet, not only the clear wins and losses. A deal lost to no decision needs a different fix from a deal lost to a rival.

How to use this prompt

  1. Pick your AI model. Choose the tab for Claude, ChatGPT, Gemini or Copilot. Each variant is tuned for that model.
  2. Copy the full prompt. Click Copy Full Prompt to copy the text to your clipboard.
  3. Paste into your AI tool. Open your chosen model and paste the prompt into a new chat.
  4. Replace the [placeholders]. Swap any bracketed fields for your company name, audience, product or tone.
  5. Run and refine. Review the output. If anything is off, ask the AI to tighten tone, length or format.

Prompt Variants by Model

Claude Sonnet 5
<deals>
[PASTE YOUR WON AND LOST DEALS, ONE PER LINE: OUTCOME, VALUE, SOURCE, WHO THE BUYER WAS, COMPETITOR IF ANY, AND THE REASON AS YOU UNDERSTAND IT]
</deals>

Act as a sales analyst for a small business. Find the patterns in the won and lost deals above and tell me what to change.

What I sell [PRODUCT OR SERVICE] · period covered [DATES] · how the reasons were recorded [BUYER TOLD US / MY GUESS / MIXED] · what I think is going on [MY THEORY, or NONE]

Deliver (count it, don't estimate):
1. The numbers: deals won, lost to a competitor and lost to no decision; win rate overall and by source, by buyer type and by deal size (in bands you choose and state), with the count behind every percentage
2. Why we win: the reasons that recur, each with how many deals support it
3. Why we lose: the same, with deals lost to no decision kept apart from deals lost to a competitor
4. What I believed against what the deals show: my theory checked against the counts (with no theory, write "no theory given")
5. Three changes to test, each tied to a pattern and to a number I can track
6. Interview guide: eight neutral questions for a buyer who chose someone else, and how to ask for the call
7. What the data cannot tell me: gaps in how reasons were recorded, and what to capture from now on

As a working rule, a pattern needs at least three deals behind it; with fewer, write "too few to say", because small counts mislead. Where the reason is my guess and not the buyer's words, mark it "seller's view".

Success means every percentage shows its count, no pattern rests on fewer than three deals, and each change names the number that will show whether it worked.

Apply every rule, limit, and format above to every item in the deliverable, not just the first one. Deliver the complete result in one response, every section filled in, nothing deferred to a follow-up.

If a required input is missing, ask for it once before starting; otherwise proceed and label any assumption you made.

Notes: R54 build; tuned to vendor prompting guidance

Frequently Asked Questions

What does the Win-Loss Review prompt do?

Find the patterns in a batch of deals you won and lost, with the count behind every percentage, three changes to test, and the questions to ask a buyer who chose someone else.

Which AI models is this prompt written for?

Claude, ChatGPT, Gemini and Copilot. Each one gets its own version up top, written the way that vendor says to prompt its own model. Pick the tab that matches yours.

Do I need a paid AI account to use this prompt?

No. This prompt is written to run on the free tier of Claude, ChatGPT, Gemini and Copilot. Paid tiers simply give you longer context windows and faster responses.

Can I customize this prompt for my business?

Yes. Any text inside square brackets is a placeholder you replace with your own business details, such as company name, audience, product or tone. You can also ask the AI to adjust format, length or style after the first output.

When was this prompt last checked?

The date is on each version up top. We check every prompt in full every month, and when a major new model lands we rewrite the prompt for it. One glance tells you how current it is before you paste.

Works with

More in Competitor & Market Research

Browse all prompts →