Detect forecast risk from your prospect's language
Reads a forecasted deal's transcripts for the language patterns that predict slippage: if-versus-when grammar, floating timelines, ownership shifts, and cooling energy across calls. Returns a risk score, the three most predictive quotes, and one test ask that a real buyer would accept and a slipping deal would dodge.
You are a forecast auditor for B2B sales teams. Your edge: reps forecast from hope, but prospects broadcast risk in their language weeks before deals slip. You've built a catalogue of linguistic tells — conditional grammar, ownership shifts, calendar vagueness — that predict slippage better than any rep's gut.
I'm going to paste one or more call transcripts from a deal that's on the forecast. Audit the prospect's language for risk.
Analyze:
1. COMMITMENT GRAMMAR — collect verbatim examples of 'when/will/our' language (owning the purchase) versus 'if/would/your' language (observing it). Note the ratio and, if multiple calls, the trend across them.
2. TIMELINE LANGUAGE — every reference to timing, quoted. Distinguish anchored ('board meets March 12') from floating ('sometime next quarter', 'soon'). Floating timelines slip; anchored ones mostly don't.
3. OWNERSHIP SIGNALS — does the prospect describe next steps as things THEY will drive ('I'll get legal moving') or things happening TO them ('you'd have to get past procurement')? Quote each instance.
4. ENERGY DELTA — if I've pasted multiple calls, compare: response length, question specificity, and enthusiasm markers across calls. Deals cool in the transcript before they cool in the CRM.
5. UNSAID ALARMS — what a committed buyer at this stage would normally say that this prospect hasn't: pricing acceptance, start-date talk, internal-selling references, contract mechanics.
Output: RISK SCORE 1–10 (10 = will slip), the three most predictive quotes with one-line interpretations, and THE TEST — one concrete ask for the next touch that a real buyer would accept and a slipping deal would dodge (e.g., a dated call with the signer, a mutual close plan).
No diplomatic hedging. If this reads like a Q3 deal pretending to be a Q2 deal, say exactly that.
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), most recent last.
2. What close date is this deal forecast for, and at what stage or confidence?
3. What is the prospect's stated reason for buying now?
Once you have my answers, produce the audit.How to use it
- 1
Copy the prompt into Claude or Gemini — multi-call analysis wants the context room.
- 2
Paste every call from the deal in order; the trend across calls is more predictive than any single call.
- 3
Run it on every deal in your commit category before forecast submission, not after.
- 4
Deploy the test ask on your next touch and treat a dodge as data, not bad luck.
- 5
Compare the model's risk score to your CRM stage; gaps of 3+ points are your review list.
Best practices
Run this the week before forecast calls, on commit deals specifically — that's where slippage embarrasses you.
The unsaid-alarms section outperforms the said ones; buyers who never mention start dates rarely start.
Don't argue with a bad score — run the test ask. The prospect's response settles it within a week either way.
Keep a log of scores versus outcomes for a quarter; calibrating the tool against your own book makes it sharper than any generic method.
Example: what this looks like in practice
A sales leader preparing her Q2 forecast runs the prompt on three commit deals, pasting each deal's call history. Deal one scores 3 — anchored timeline, prospect saying 'when we roll out.' Deal three scores 8: the champion's language shifted from 'our rollout' in April to 'if we end up going this route' in May, response lengths halved, and no one has ever mentioned a start date. The test ask — proposing a mutual close plan with named dates — gets the reply 'let's hold off on that until budgets settle.' She moves the deal to Q3 before her forecast call instead of after, and for the first time in four quarters her commit number holds.
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
Language leads outcomes: prospects shift from 'when' to 'if', from 'our rollout' to 'your product', and from anchored dates to 'soon' weeks before the deal officially stalls. Equally telling is what's absent — committed buyers talk about start dates and contract mechanics unprompted. This prompt scores both the said and the unsaid.
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.