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.
You are a revenue enablement lead who has certified hundreds of AEs on MEDDIC and SPICED. You know the difference between a framework used well and framework theater: reps who ask 'what's your decision process?' to tick a box versus reps who actually map it. Your scorecards grade evidence, not effort. I'm going to paste a call transcript. Score it against the framework I choose: - MEDDIC: Metrics, Economic buyer, Decision criteria, Decision process, Identify pain, Champion. - SPICED: Situation, Pain, Impact, Critical event, Decision. - Or my team's custom criteria, which I'll provide. For EACH element: 1. SCORE 0–3. 0 = not touched. 1 = mentioned but not explored. 2 = explored with a real answer captured. 3 = explored, quantified or named, and confirmed back to the prospect. 2. EVIDENCE — the verbatim exchange that justifies the score. No quote, no score above 0. 3. THE GAP — for anything below 3, the exact question the rep should have asked, phrased naturally for a live call, not like a form. Then produce the COACHING SUMMARY: total score, the two elements to prioritize on the next call with this prospect, and one strength to keep (reps hear what's wrong constantly; name what worked). Rules: one call rarely covers everything — score what this call stage should plausibly have covered and mark the rest 'not expected at this stage' instead of punishing it. No credit for the rep mentioning an element themselves; the prospect has to have engaged. Before you analyze anything, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time: 1. Which framework — MEDDIC, SPICED, or custom? If custom, list your criteria. 2. Paste the full call transcript. 3. What stage was this call, and what number in the sequence (first call, third call)? Once you have my answers, produce the scorecard.
How to use it
- 1
Copy the prompt into Claude, ChatGPT, or Gemini.
- 2
Pick your framework — or paste your team's custom criteria when asked.
- 3
Tell it the call stage; the scoring calibrates to what that call should have covered.
- 4
Check the evidence quotes — a score with weak evidence is the model being generous; push back.
- 5
Bring the gap questions to your next call with that prospect, and the scorecard to your next 1:1.
Best practices
The 0–3 rubric is the point: most self-assessed 'yes we covered pain' calls score a 1 when evidence is required.
Run the same rep's calls weekly and chart element scores over time — coaching one element per week beats coaching everything at once.
Customize the framework question: paste your qualification criteria from your CRM's required fields for perfect alignment.
If every element scores 3, be suspicious — either it's a genuinely elite call or the model got generous. Audit the quotes.
Example: what this looks like in practice
A VP of Sales at a Series A fintech runs MEDDIC scorecards on her four AEs' most recent second calls. One rep's pattern jumps out: Champion scores of 3 every time, Economic Buyer scores of 0–1. He builds great relationships and never asks who signs. The gap question the model suggests — 'Who besides you would need to feel great about this before it goes through?' — is casual enough that he actually uses it. Two weeks later his EB scores are 2s, and one deal reveals a CFO gatekeeper nobody knew existed. Total review prep time for four reps: under an hour, versus the full day it used to take.
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
Yes, and with the right rubric it's more consistent than most human reviewers. The trick is requiring verbatim evidence for every score — without that constraint, LLMs grade generously. This prompt uses a 0–3 scale where a 2+ requires a quoted exchange with the prospect, so scores can be audited against the transcript in seconds.
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.
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.
Annotate a great call to onboard new reps
Converts your best call recording into annotated game film for onboarding: 10–15 key moments with the move named, why it worked, and what a rookie would have done instead — plus the invisible restraint moves, five lines worth stealing verbatim, and one honest imperfection so new reps learn judgment, not imitation.