Extract win and loss signals from a sales call transcript
Reads a transcript the way a seasoned deal reviewer would: separating real buying signals from polite enthusiasm, flagging risk hiding in hedged language, and — most usefully — naming what a healthy deal should have shown that this call didn't. Ends with a deal-health score and one action to test if the deal is real.
You are a deal strategist who has run win/loss analysis for B2B sales teams for a decade. You know deals are usually decided long before the decision email — in throwaway lines on calls: who the prospect compares you to, whether they talk in 'if' or 'when', whether they volunteer internal politics or hide them.
I'm going to paste a call transcript. Extract every buying signal and every risk signal, and be strict about the difference between evidence and vibes.
Output format:
GREEN SIGNALS — each with a verbatim quote and one line on why it matters. Look for: 'when' language, prospect selling internally ('I'd position this to my boss as...'), specific implementation questions, volunteered timeline or budget, references to a pain with a cost attached.
RED SIGNALS — same format. Look for: 'if' language, deferred authority ('I'd have to check'), polite enthusiasm without specifics, unprompted mentions of doing nothing or building in-house, questions that sound like due-diligence for a decision already made elsewhere.
MISSING SIGNALS — what a healthy deal at this stage should have shown that this call didn't. This section matters most; absence of evidence is a finding.
VERDICT — score deal health 1–10, name the single biggest risk, and give one concrete action for the next touch that would test whether this deal is real.
No hedging. If the call reads like a polite no forming, say so.
Before you analyze anything, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time:
1. Paste the full call transcript.
2. What stage is this deal at, and what's the rough deal size?
3. What's your read on the deal right now — and what are you worried about?
Once you have my answers, produce the analysis. Challenge my read if the transcript contradicts it.How to use it
- 1
Copy the prompt into Claude, ChatGPT, or Gemini.
- 2
Paste the transcript and answer honestly about your own read on the deal — the model is instructed to challenge it.
- 3
Read the missing-signals section first; it's the part your own optimism filters out.
- 4
Run the suggested test action on your next touch before updating your forecast.
- 5
For big deals, run this on every call in the thread and watch how the score trends.
Best practices
Run it on deals you feel great about — that's where the polite-no pattern hides longest.
If every signal comes back green, ask 'what would a skeptic say this prospect is doing?' to force the counter-read.
Pair with your CRM notes: when the model's score disagrees with your pipeline stage by 3+ points, that deal needs a review.
Save red-signal quotes from deals you eventually lost — they become your team's early-warning vocabulary.
Example: what this looks like in practice
An AE at a mid-market logistics SaaS has a $60K deal marked 'commit'. She pastes the latest call transcript. Green signals: the champion asked about SSO setup and said 'when we roll this out to the Dallas team'. Red signals: the same champion said 'procurement has their own process, I don't really get involved' — deferred authority on a $60K deal. Missing: no economic buyer has attended any call, and no one has mentioned a signature date. Verdict: 6/10, biggest risk is single-threading past the champion. The test action — asking the champion to bring procurement to a 15-minute process call — surfaces a security review nobody had mentioned. The deal closes, one quarter later than forecast.
Best fit
This prompt is one gear in a bigger machine. We orchestrate 20+ tools into outbound systems our clients own — and guarantee the results.
Apply for a Pilot Spot → →Frequently asked questions
The reliable ones are behavioral, not verbal enthusiasm: 'when' instead of 'if' language, specific implementation or integration questions, the prospect rehearsing how they'd sell it internally, and volunteered detail about budget, timeline, or process. Compliments and 'this looks great' are noise — this prompt is built to ignore them.
More call transcript analysis & coaching prompts
Extract every objection from a call transcript and grade how it was handled
Pulls every objection out of a transcript — including the soft, disguised ones reps miss — with verbatim quotes, a diagnosis of the real concern, a letter grade on the rep's response, and a better line for next time. It's a full objection review in two minutes instead of re-listening to the call.
Score a sales call against MEDDIC or SPICED with a coaching scorecard
Turns any transcript into a framework scorecard with a 0–3 score per element, verbatim evidence behind every score, and the exact question that would close each gap. Stage-aware, so a first discovery call isn't punished for missing decision criteria. It's the deal-review prep that used to take a manager 45 minutes per call.
Analyze talk ratio and question quality from a call transcript
Measures what conversation intelligence tools measure — talk ratio, question count — but adds the layer they skip: classifying every question by type and quality, and pinpointing the exact moments a rep should have dug deeper instead of moving on. Works from any transcript, no Gong seat required.