Sales & Outreach

Verified against ChatGPT · 2026-08-07

Run an honest post-mortem on a lost deal before writing it off as "budget"

Turns deal history and notes on a lost deal into a real post-mortem tested against documented loss-reason patterns, instead of accepting the reflexive one-word reason logged and forgotten, with one in-control and one out-of-control factor named separately.

ChatGPTClaudeSalesforce5 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

We lost this deal: Greymoor Industrial, logged reason "lost to competitor". Deal history and notes: strong first two calls, champion went quiet after their VP reorg was announced, one follow-up email got a one-line reply, then nothing; we assumed they picked a competitor. Stage at time of loss: proposal sent, awaiting signature. Roughly how much time elapsed between the last real engagement and marking it lost: about six weeks of silence before marking it lost.

Run a real post-mortem, not a rubber-stamp of the logged reason:

1. TEST THE LOGGED REASON — check "lost to competitor" against what strong first two calls, champion went quiet after their VP reorg was announced, one follow-up email got a one-line reply, then nothing; we assumed they picked a competitor actually shows evidence for, not what it's plausible to assume. Specifically check whether it looks like a proxy for something else — the most common pattern being a deal logged as "lost to competitor" or "budget" that the evidence actually supports reading as "no decision," where the prospect simply went quiet and did nothing, rather than actively choosing an alternative. If the deal history contains no actual mention of a competitor winning or an explicit budget rejection, say so plainly rather than accepting the logged label at face value just because it's already written down.

2. FIND THE EARLIEST RISK POINT — identify the earliest point in strong first two calls, champion went quiet after their VP reorg was announced, one follow-up email got a one-line reply, then nothing; we assumed they picked a competitor where this deal was already genuinely at risk, even if it didn't look that way at the time — name a specific stage, interaction, or event, not a vague "communication could have been better" that could describe any lost deal ever logged.

3. ONE THING WITHIN OUR CONTROL — name one specific, actionable thing that, if done differently at that earliest risk point, plausibly changes the outcome — it must be concrete enough to actually do differently next time, not "should have built more urgency," which is a diagnosis dressed up as an action.

4. ONE THING OUTSIDE OUR CONTROL — name one real factor that was genuinely outside the rep's control, so the takeaway from this post-mortem isn't "everything here was our fault" — a post-mortem that finds only self-blame is exactly as unhelpful as one that finds none.

5. THE LESSON — a one-line lesson that could actually be applied to the next deal at a similar stage, worth saying out loud in a pipeline review, not a vague platitude like "stay closer to the champion" that every post-mortem in history could equally have concluded with.

HONESTY CHECK
If strong first two calls, champion went quiet after their VP reorg was announced, one follow-up email got a one-line reply, then nothing; we assumed they picked a competitor genuinely doesn't contain enough detail to determine whether the logged reason holds up, say that plainly rather than forcing a confident-sounding verdict from thin evidence — a fabricated-sounding certainty about why a deal was lost is worse for the next deal than an honest "we don't actually know enough to say" that at least prompts better note-taking going forward.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

Testing the logged reason against the actual evidence in the deal history, rather than accepting it as settled, targets a well-documented pattern in B2B win/loss analysis: "no decision" — the prospect simply going quiet rather than actively choosing a competitor — is consistently one of the most common real outcomes in competitive deals, far more often than reps actually log it that way, because "lost to Competitor X" is a more comfortable, less self-implicating box to check than "I never got a next step after their reorg and let it go quiet." Requiring a specific, named earliest risk point rather than a generic "communication could have been better" observation forces the post-mortem to locate an actual moment in the deal's timeline, which is what makes the lesson from this deal transferable to a different deal at a similar stage — a vague communication critique applies equally to every lost deal ever logged and therefore teaches nothing specific about this one. Splitting the analysis into one in-control factor and one out-of-control factor, and requiring both rather than either one alone, prevents the two failure modes a post-mortem can fall into on its own: an entirely self-blaming version that concludes everything was the rep's fault, which is demoralizing and usually inaccurate, and an entirely externalizing version that blames the market or the buyer's org chart for everything, which teaches the rep nothing they could act on differently next time — a real post-mortem almost always contains genuine elements of both, and forcing both to be named prevents either one from crowding out the other. The honesty check on evidence thinness matters because a model asked to diagnose a lost deal will produce a confident-sounding verdict regardless of how much real detail the deal history actually contains, and a fabricated-sounding certainty about why a specific deal was lost is more dangerous than an honest admission of insufficient evidence, because the false certainty gets treated as a real lesson and applied to future deals, while the honest gap at least prompts better note-taking discipline going forward.

What you get back

The evidence doesn't clearly support "lost to competitor" — there's no mention of a competitor anywhere in the deal history, only a VP reorg followed by silence. This looks more like "no decision," with the reorg as the likely trigger. Earliest risk point: the champion going quiet after the reorg was announced, with no attempt made to identify a new stakeholder. Lesson: when a champion's org changes mid-deal, treat it as a re-qualification trigger, not a delay to simply wait out.

Verified against

ChatGPT GPT-5.1 · 2026-08-07

Claude Sonnet 4.5 · 2026-08-08

Changelog

  • 2026-08-08 Initial publish, verified against ChatGPT (GPT-5.1) and Claude (Sonnet 4.5).

Need this built into your business?

If a prompt isn't enough — Google Ads management, built and maintained for you — that's Scult's day job.

EXPLORE GOOGLE ADS MANAGEMENT
All Sales & Outreach prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY