Spot multi-threading gaps from attendee talk time
Maps who actually shows up and speaks across a deal's calls: voice share per attendee, roles read from their words, silent lurkers flagged, and the stakeholder roles nobody on any call fills. Then gives you a specific, champion-safe play to open each missing thread before the deal's single thread snaps.
You are a deal strategist who specializes in multi-threading — and in diagnosing its absence. Your rule of thumb: the org chart on the calls is the deal you actually have, not the deal in the CRM. A 'multi-stakeholder deal' where one champion does 90% of the prospect-side talking is a single-threaded deal wearing a disguise, and it dies the day that champion gets busy, blocked, or poached. I'm going to paste one or more call transcripts from a deal. Map the threading: 1. ATTENDEE CENSUS — every prospect-side person who appears across the calls: name, title if stated or inferable, and which calls they attended. 2. VOICE SHARE — for each attendee, estimate their share of prospect-side words per call. Flag the silent attendees: people who joined and said almost nothing. Silence in a meeting they chose to attend is a signal — evaluators, skeptics, and hidden approvers all lurk quietly. 3. ROLE READ — from their words alone: who champions, who evaluates, who controls budget, who can veto. Quote the evidence. Mark unknowns as unknown rather than guessing. 4. THE GAPS — name the roles a deal of this kind needs that no attendee fills (economic buyer, technical evaluator, end-user voice, procurement/legal), and any attendee whose silence needs explaining. 5. THREADING PLAYS — for each gap, one specific move: who to ask for the intro, how to frame it so the champion doesn't feel bypassed, and the exact ask phrased naturally. Include a play for re-engaging the most important silent attendee. Rules: distinguish 'attended and agreed' from 'attended and engaged' — nodding along is not threading. If every call has the same single voice, say plainly: this deal is single-threaded. Before you analyze anything, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time: 1. Paste the transcript(s), labeled by date, with attendee names if the transcript doesn't show them. 2. What's the deal size and what does your product touch (which teams would use or approve it)? 3. Who does your CRM say the key stakeholders are? Once you have my answers, produce the threading map.
How to use it
- 1
Copy the prompt into Claude or Gemini, especially for multi-call deal histories.
- 2
Paste every call from the deal — threading gaps only show across the sequence, not in one call.
- 3
Give it your CRM's stakeholder list in question 3; the gap between CRM fiction and call reality is the finding.
- 4
Run the threading plays through your champion first — the framing that avoids bypassing them is built into each play.
- 5
Repeat monthly on every deal above your average deal size; threading decays silently as deals age.
Best practices
The silent-attendee flag is the most actionable output — someone who attends twice and says ten words is evaluating you without giving you a chance to respond.
Voice share is an estimate from words in the transcript; treat 85/15 versus 50/50 as the signal, not the decimal points.
If the economic buyer has never attended by the proposal stage, fix that before sending the proposal, not after it stalls.
Compare the model's role reads against your champion's descriptions — where they conflict, believe the transcript.
Example: what this looks like in practice
An AE at an enterprise workflow platform has a $120K deal at proposal stage that 'has full buy-in.' She pastes four call transcripts. The census: six prospect-side attendees across the calls, but her champion holds 88% of prospect-side voice share in every one. The flagged silent attendee: a director of engineering who joined calls two and four and spoke 23 words total, including 'we'd have to see about that' during the integration discussion. Role gaps: no budget owner has ever attended. The suggested play — asking the champion to co-host a technical session where the director's team drives the agenda — surfaces two integration blockers and, eventually, the real approver. The deal takes six weeks longer and actually closes.
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
Building relationships with multiple stakeholders in a deal instead of relying on one contact. It matters because single-threaded deals die from things you never see: your champion changes jobs, loses an internal fight, or just gets busy. The test isn't how many people your CRM lists — it's how many people actually talk on your calls.
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.