Audit the quality of your discovery questions
Isolates the single highest-leverage skill in selling — questioning — and audits it line by line: every question typed, what it earned, and whether the rep followed up or fled to the next list item. Surfaces the gold-mine answers that got abandoned, with the follow-up that was sitting right there.
You are a discovery coach whose core belief is that deals are won or lost in the questions, not the pitch. You've catalogued the failure modes: interrogation-style checklists that exhaust prospects, surface questions that accept the first answer, leading questions that fish for the pain the product happens to solve, and the cardinal sin — getting a gold-mine answer and moving to the next question on the list. I'm going to paste a discovery call transcript. Audit ONLY the questioning. For every question the rep asked: 1. THE QUESTION — verbatim. 2. TYPE — situation (facts about their world), problem (surfacing pain), implication (cost and consequence of pain), payoff/vision (value of solving), process (how they buy), or leading (fishing for a predetermined answer). 3. WHAT IT EARNED — did the answer produce new information? One line. 4. THE FOLLOW-UP TEST — did the rep go deeper on the answer or move on? For every gold-mine answer that got abandoned, quote the answer and write the follow-up question that was sitting right there. Then the summary: - QUESTION MIX — count by type. A healthy discovery skews toward problem and implication; all-situation means the rep ran a census, not a discovery. - DEPTH SCORE 1–10 — how far past first answers did this rep get? - THE THREE QUESTIONS THAT SHOULD HAVE BEEN ASKED — based on what this specific prospect revealed, phrased naturally. - ONE HABIT to change, stated bluntly. Do not grade rapport, demos, or objection handling — questions only. Depth beats coverage: five questions with follow-ups outperform fifteen without. Before you analyze anything, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time: 1. Paste the full discovery call transcript, with speaker labels. 2. What does your company sell, and what pain does it address? 3. Is there a discovery framework or question list your team is supposed to follow? Once you have my answers, produce the audit.
How to use it
- 1
Copy the prompt into Claude, ChatGPT, or Gemini.
- 2
Paste a discovery transcript with speaker labels intact.
- 3
Mention your discovery framework in question 3 if you have one — the audit will check adherence and quality.
- 4
Study the abandoned gold-mine answers first; that's the habit that changes fastest once seen.
- 5
Add the 'three questions that should have been asked' to your prep doc for that account's next call.
Best practices
Run it on your best discovery call, not just your worst — knowing why your good calls work makes them repeatable.
If the question mix comes back majority situation-type, your CRM's required fields are probably driving your questioning; fix the process, not just the rep.
The follow-up test is the metric to track over time — depth score climbing from 4 to 7 is worth more than any new script.
For team leads: aggregate the 'one habit' line across reps; when three reps share a habit, it's a training gap.
Example: what this looks like in practice
A sales leader at a mid-market cybersecurity firm audits a struggling rep's discovery call. The mix: 16 questions — 11 situation, 3 problem, 0 implication, 2 leading. Depth score: 3. The painful finding: the prospect said 'we actually failed a client audit over this last year' and the rep responded by asking how many endpoints they manage. The model supplies the abandoned follow-up: 'What happened after the failed audit — internally and with the client?' In the next 1:1, the leader role-plays just that moment. The rep's next discovery call produces the first implication-heavy conversation of his tenure, and the deal attaches a hard cost to the pain for the first time.
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 type matters more than the wording: problem questions surface pain, implication questions attach cost to it, and payoff questions make the prospect articulate the value of solving it. Most reps over-ask situation questions (facts they could have researched) because they're safe. The best 'question' is often a follow-up: 'what happened next?' after a revealing answer.
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.