Build a QBR-ready customer insight summary from calls
Mines a quarter of one account's calls into QBR material: the customer's stated priorities and how they shifted, value moments in their own words, a ranked friction log, expansion needs they've described but not bought, a relationship map with weakening-champion warnings, and a five-item agenda built around discussion questions instead of slides.
You are an account strategist who prepares QBRs that customers actually want to attend. Your standard: a QBR built from usage charts and a renewal ask is a vendor meeting; a QBR built from what the customer said across a quarter of calls is a strategy meeting. The raw material is sitting in the transcripts — most account teams just never mine it. I'm going to paste transcripts of calls with one customer account from the recent period (check-ins, support escalations, project calls — whatever we have). Build the insight summary: 1. STATED PRIORITIES — what this customer said they're trying to achieve, in their words, with quotes. Note when priorities shifted across the quarter; the shift is often the headline. 2. WINS TO CLAIM — moments where they described value received, quoted verbatim. These are the proof points that open the QBR; their words, not our dashboard. 3. FRICTION LOG — every complaint, workaround, or frustration mentioned, however casually, with who said it. Ranked by repetition and emotional weight, not by ease of fix. 4. UNBOUGHT NEEDS — problems they described that our product could address but they haven't bought or adopted. Quote the evidence. Flag each as expansion conversation or adoption conversation. 5. RELATIONSHIP MAP — who we actually talk to versus who they mention internally (bosses, teams, new hires, departures). Note champions strengthening or weakening and any names that appeared or vanished during the period. 6. RISK READ — renewal risk signals: sentiment trend across calls, mentions of budget review, reorganizations, competitor references, or our tool described as optional. Then: THE QBR AGENDA — five items in the order that serves the customer, each tied to a finding above, with the discussion question to ask rather than the slide to show. Rules: their words over our interpretation, always. If the transcripts are all operational check-ins with no strategic content, say so — that itself is the QBR finding. Before you analyze anything, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time: 1. Paste the call transcripts, labeled by date and call type. 2. What does this account pay annually, and when is renewal? 3. What are you hoping to accomplish in this QBR — defend, expand, or repair? Once you have my answers, build the summary.
How to use it
- 1
Copy the prompt into Claude or Gemini — a quarter of account calls is a lot of context.
- 2
Gather every call type: support escalations and project calls often hold more truth than scheduled check-ins.
- 3
State your real QBR goal in question 3 — defend, expand, or repair changes the agenda's shape.
- 4
Verify the wins-to-claim quotes and lead the QBR with them, in the customer's words.
- 5
Route the friction log to product or support before the QBR so you arrive with responses, not surprises.
Best practices
The priority-shift finding is QBR gold: opening with 'in January you were focused on X, lately it's Y — what changed?' proves a quarter of listening in one question.
Treat the relationship map's vanished names seriously — a champion who stopped appearing on calls mid-quarter is a renewal risk no dashboard shows.
Unbought needs framed as their words ('you mentioned twice that reporting eats your Fridays') expand accounts without a pitch.
If the risk read comes back elevated, move the QBR earlier — risk found in transcripts compounds quietly.
Example: what this looks like in practice
A CSM-turned-account-manager at a workforce-management platform preps a QBR for a $85K account renewing in five months. She pastes eleven calls from the quarter. Findings: priorities shifted in March from rollout speed to audit-readiness (a compliance hire appears in the transcripts, then starts dominating them); two quotable wins ('the scheduling piece has basically given me my Sundays back'); a friction log topped by a permissions complaint raised in four separate calls by three people; and one vanished name — the original champion, absent since February. The QBR agenda leads with the audit-readiness shift and includes a permissions-fix commitment. The meeting runs 20 minutes long because the customer keeps talking, and the renewal conversation starts itself.
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
Less reporting, more strategy: the customer's priorities in their own words (and how they've shifted), value moments they described themselves, honest acknowledgment of their friction, and forward-looking discussion questions. Usage dashboards are fine as backup. The test of a good QBR agenda: every item could start a conversation the customer wants to have.
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.