Lost Deal Analysis
Works out why a deal actually died, separating the reason given from the reason it happened.
Free — no card needed
Create a free account
to open Lost Deal Analysis — and the other 364 prompts across 21 categories.
Already have an account?
Running it, start to finish
- Reconstruct the timeline from the CRM, not from memory.
- Find out what they chose instead before accepting the stated reason.
- Change at most two things and test on the next deal.
What you get back
The output this produces, every time.
- Tests the stated loss reason against what they actually did instead.
- Finds the moment momentum changed, usually weeks before the decline.
- Separates unwinnable deals from lost ones, so process changes do not chase the wrong problem.
Getting better results
Where this usually goes wrong, and how to avoid it.
- Answer section 4 honestly. A lot of lost deals were never qualified. That is a much cheaper problem to fix than closing, and a much more common one.
- Find out what they actually bought. It is the single most informative fact and the one most often not asked for. It usually contradicts the stated reason.
- Revisit the no-decision losses. Section 7 is where re-engagement pays. A competitor loss rarely reopens; a stalled decision often does.
More Sales prompts
All Sales →- Sales
Discovery Call Question Set
Builds a discovery script that finds out whether there is a real deal here, including the questions that would disqualify it early.
ClaudeChatGPT000Open → - Sales
Demo That Sells
Demos the two things that solve their stated problem, since a feature tour loses the room and teaches nothing.
ClaudeChatGPT000Open → - Sales
Cold Outreach That Earns a Reply
Writes a short first-touch built on something specific and current about the recipient, with a low-friction ask and a genuine reason to reply.
ClaudeChatGPTGemini000Open →
Written for The AI University. Every prompt in this library is original work — authored, tested and revised here, not collected from elsewhere. 365 of them, free with an account.