Skip to main content
idapt
HomeAI ModelsPricing
Sign inStart free
All prompts

Prompt library

Run win/loss interviews that tell the truth

Chronological walk-throughs recover the real decision sequence that summary questions flatten into rationalization, and the counterfactual question is where losses give up their lesson. The disconfirmation self-test keeps the guide from becoming a machine for confirming what sales already believes.

SalesPlan

Last reviewed July 17, 2026

The prompt
Build a win/loss interview guide.

The deal: {{deal}}
What we currently believe about why it went this way: {{belief}}

Produce:
1. Setup rules: who should NOT run this interview (the account's own rep; people defend their work), the framing that lowers the guard ("we are improving how we sell, not re-selling you"), and the 25-minute cap.
2. Question sequence, 8-10 questions: start at the trigger (what started the search), walk the evaluation chronologically (who else, what criteria emerged, when did the ranking form), locate the decisive moment, then the counterfactual ("what would have had to be different for the other outcome").
3. For each question: the probe for when they give the polite answer, because first answers in loss interviews are diplomatic fiction.
4. The self-test: which questions would confirm our stated belief, and which could DISCONFIRM it. If the guide cannot disconfirm us, rewrite it until it can.
5. The synthesis format: how findings get written so patterns accumulate across interviews (decision criteria heard, moment lost/won, competitor claims heard).

Losses interview better than wins; schedule accordingly.
Run in idaptOpens a new chat with the prompt prefilled. Nothing sends until you press send.

Fill in the variables

VariableWhat it isExample
{{deal}}The won or lost deallost a 60k deal to the incumbent after a 4-month cycle
{{belief}}Your current explanationwe think we lost on integrations depth

Frequently asked

Related prompts

Build a user interview guideTear down a competitor's productSummarize a campaign debrief

Ready to get to work?

Free to start. No credit card. Never trained on your data.

Start free
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Secrets
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • Code Execution
  • Computers
  • Computer Use
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Learn
  • Free tools
  • Prompts
  • Templates
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)