Win/loss synthesis at scale: close the gap between how buyers talk and how you sell
Export a quarter of call transcripts, run them through Claude, and get the five most common buying triggers, the objections that actually killed deals, and the language your buyers use before they ever heard of you.
Most positioning is 12 months stale. It was written once, lives in a Google Doc, and hasn’t been updated because synthesising call transcripts is time-consuming, awkward to coordinate with sales, and the output usually sits in a doc nobody opens by the time the next planning cycle starts.
The gap closes slowly. The language on your homepage drifts from how buyers actually describe their problem. Email sequences use internal product terms instead of the words prospects use on discovery calls. Nobody notices until pipeline converts at a lower rate and the debate about channel mix begins.
The win/loss synthesizer runs quarterly. Export closed-won and closed-lost transcripts from Gong, Chorus, or Fathom. Feed them into Claude with a prompt focused on three outputs: the five most common buying triggers in won deals with direct quotes, the five most common objections in lost deals with direct quotes, and the customer-native language for the problem you solve: the words buyers used before they knew your product existed.
That third output is where most positioning improvements come from. It also gets skipped most often because it requires the most discipline: strip out all your category language and let the transcripts surface what buyers say.
What to do with it: the customer-native language section goes directly to demand gen. Those phrases belong in email subject lines, ad copy, and homepage headings, not in a research document. The buying trigger patterns belong in your ABM play logic, not just in the marketing deck. If Tier 1 accounts are triggered by a specific event type, that event belongs in your signal monitoring layer.
Include churned customers alongside lost deals. Churn calls surface product-market fit gaps that messaging alone can’t address. If the same objection appears in both lost deals and churn calls, you have a product problem, not a positioning one.
The prompt:
You are a B2B positioning analyst reviewing a quarter's worth of sales conversations to surface patterns that should improve marketing and messaging.
I will provide call transcripts and summaries from closed-won deals and closed-lost deals this quarter.
Analyze all transcripts and return the following, with direct quotes from the source material for each finding:
The five most common buying triggers in won deals: What was happening in the buyer's world that made them start looking? Quote their exact language.
The five most common objections or hesitations in lost deals: What specifically blocked the deal? Quote the language buyers used, not the rep's interpretation of it.
Customer-native language for the problem: How did buyers describe their pain before they knew about our product? List the specific words and phrases they used. Do not use any of our product language or category terms in this section.
What distinguishes won deals from lost deals: Identify 2 to 3 patterns that clearly separate the two groups. These might be firmographic, behavioral, or related to the buyer's stated situation.
Be specific and quote directly. If the transcripts don't support a finding, say so rather than inferring.
Transcripts to analyze: [paste call transcripts and summaries here]