Sales & Outreach Prompts

Win-Loss Interview and Insight Analyzer

Prepare neutral buyer interviews and convert win-loss evidence into recurring decision insights, corrective actions, and confidence-rated themes.

FreeClaudeChatGPT
Best for

Sales enablement, product marketing, and revenue leaders who want reliable lessons from won and lost opportunities rather than anecdotal explanations.

Suitable LLM groups
FrontierReasoning
Download Prompt.md
Prompt
You are a win-loss research specialist who investigates buyer decisions without turning interviews into sales calls or blame exercises.

Inputs:
1. Opportunity outcome and account context: {{deal_context}}
2. CRM history, proposal, participants, and internal hypotheses: {{internal_evidence}}
3. Available buyer interview, survey, or feedback material: {{buyer_evidence}}
4. Product, pricing, process, competitive, and market context: {{business_context}}
5. Research scope, anonymity, and reporting constraints: {{constraints}}

Do the following:
1. Separate known facts, internal interpretations, and open questions about the decision; identify where seller memory or CRM data may be incomplete.
2. Create a neutral interview guide covering problem priority, evaluation process, decision criteria, experience with the seller, solution fit, implementation confidence, price and value, alternatives, and decisive moments.
3. Analyze supplied buyer evidence using coded themes and representative quotations, distinguishing stated reasons from inferred contributors and one-off comments from recurring patterns.
4. Compare buyer evidence with internal hypotheses, identify process, product, positioning, pricing, or qualification lessons, and rate each insight by evidence strength and applicability.
5. Produce an interview guide, coded insight table, decision timeline, recommended actions with owners, and leadership summary that avoids naming or blaming individuals. Do not pressure the buyer to reopen the decision or disclose confidential competitor information.

How to use

  1. Separate internal hypotheses from buyer evidence.
  2. Use a neutral interviewer when possible.
  3. Ask about the decision process before asking why you lost.
  4. Aggregate findings before declaring a broad pattern.

Example input

Outcome: Lost EUR 140,000 analytics opportunity to an incumbent provider. Internal hypothesis: price was too high. Evidence: CRM notes mention the buyer valued our forecasting but worried about implementation; post-decision interview says the incumbent offered a lower-risk migration and involved IT three weeks earlier. Context: our price was 8% higher, but the buyer said price was not decisive. Scope: anonymized quarterly analysis across 12 completed opportunities; no seller names in leadership reporting.

Example output

The analysis codes implementation confidence and late technical engagement as strong decision themes, while price receives weak support as a decisive factor. The timeline shows IT entered after commercial evaluation, leaving migration questions unresolved. The action plan assigns sales engineering to create an early migration-discovery step and product marketing to develop verified implementation proof. The leadership summary labels the finding as a pattern only if it recurs across the remaining interviews.

Customization tips

  • Protect buyer anonymity in internal reporting.
  • Code both decisive and supporting factors.
  • Include won deals to avoid loss-only bias.
  • Assign actions only where evidence suggests a repeatable mechanism.

Tags

#win-loss-analysis#buyer-research#sales-insights#competitive-intelligence#revenue-enablement

FAQ

What is this prompt for?
It helps conduct neutral post-decision research and turn buyer evidence into actionable win-loss insights.
How should I customize it?
Provide opportunity history, internal hypotheses, buyer feedback, decision context, reporting scope, anonymity rules, and the actions your teams can own.
Are there any limitations?
Buyer recollection may be incomplete or diplomatic, and a small sample cannot establish a reliable market-wide pattern.
How is it different from a basic prompt?
It separates internal stories from buyer evidence, codes themes and timelines, rates insight strength, and prevents one interview from becoming a universal conclusion.
Free

Sales Proposal Value Case Builder

Build a buyer-specific value case that connects verified problems to measurable outcomes, assumptions, implementation costs, and decision evidence.

ClaudeChatGPT
#value-selling#business-case#sales-proposal
Free

Mutual Action Plan Builder

Create a buyer-and-seller action plan with shared milestones, owners, evidence, dependencies, and decision gates instead of a seller-only close schedule.

ClaudeChatGPT
#mutual-action-plan#sales-process#deal-coordination
Free

Stalled Deal Rescue Planner

Diagnose why an opportunity stopped progressing and select a respectful next move based on evidence, buyer value, and decision friction.

ClaudeChatGPT
#stalled-deal#deal-recovery#pipeline-management

Related Skills

Revenue & Sales SystemsFree

Sales Objection Intelligence Analyst

Turn calls, emails, and loss notes into an evidence-based objection taxonomy, root causes, response guidance, product insights, and enablement priorities.

ClaudeChatGPT
#sales objections#win loss analysis#sales enablement
Client WorkflowsFree

UX Research Interview and Insight Synthesizer

Plan user interviews and synthesize evidence into needs, pain points, behaviors, opportunity areas, and product decisions.

ClaudeChatGPT
#UX research#user interviews#research synthesis
Search & Content GrowthFree

Competitive Research Brief Builder

Create a rigorous competitive-research brief with scope, evidence standards, comparison criteria, source tracking, and decision-focused outputs.

ClaudeChatGPTCursor
#competitive research#market analysis#competitor comparison

Related Articles

Article · Research & Summarization

How to Use AI for Customer Research

Learn how to use AI to organize customer research, prepare interview questions, summarize feedback, find patterns, and turn insights into product decisions.

Jul 5, 20267 min read
Read How to Use AI for Customer Research