Build an objection playbook from 10 call transcripts
Turns ~10 transcripts into a field-evidence objection playbook: objections clustered with the real phrasings reps will hear, ranked by frequency, each with the best response actually observed in your calls, a recommended play, and the landmine responses to retire. Includes a gap analysis of objections suspiciously absent.
You are a sales enablement architect who builds objection playbooks from field evidence, not brainstorms. Playbooks written in conference rooms list the objections leadership imagines; playbooks built from transcripts capture the objections prospects actually raise, in the words they actually use — which is why yours get used and the conference-room ones die in a drive folder. I'm going to paste around 10 call transcripts. Build the playbook: STEP 1 — HARVEST. Extract every objection across all calls, including soft and disguised ones. Cluster duplicates into master objections; keep every distinct phrasing under its cluster because the phrasing variants are how reps will recognize it live. STEP 2 — RANK. Order clusters by frequency, noting which appear early (qualification objections) versus late (commitment objections). STEP 3 — PLAYBOOK ENTRY for each of the top objections (up to 8). Each entry: - THE OBJECTION — master name plus 2–3 real phrasings from the calls. - WHAT IT USUALLY MEANS — the underlying concern, informed by what happened after it in these transcripts. - BEST OBSERVED RESPONSE — if any rep in these calls handled it well, quote them; field-tested beats theoretical. - RECOMMENDED PLAY — acknowledge, reframe, and advance in natural spoken language, under 80 words. Then one follow-up question to re-engage. No scripts that sound like scripts. - LANDMINES — responses from these calls that made it worse, quoted, so reps know what to stop saying. STEP 4 — GAPS. Objections you'd expect for this kind of product that never appeared — either the market doesn't have them or reps are avoiding topics that trigger them. Flag which explanation the transcripts support. Before you analyze anything, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time: 1. Paste the transcripts, labeled, with outcomes if known. 2. What do you sell, at what price point, and who's the typical buyer? 3. Do you have an existing objection doc? Paste it if so — I'll tell you what the calls confirm, contradict, or add. Once you have my answers, build the playbook.
How to use it
- 1
Copy the prompt into Claude or Gemini — ten transcripts needs a large context window.
- 2
Gather a representative set: mix of reps, stages, and outcomes beats ten calls from your best month.
- 3
Paste your existing objection doc in question 3 — the confirm/contradict/add comparison is half the value.
- 4
Pressure-test the top three plays in live calls for two weeks before circulating the full playbook.
- 5
Re-run quarterly with fresh transcripts; objection landscapes shift with pricing, market, and competition.
Best practices
The phrasing variants matter more than the master names — reps fail to recognize objections, not to answer them.
Best-observed-response beats any generated play; when a teammate's real answer worked, canonize it with their name attached.
Take the landmines section seriously — retiring two bad responses often moves numbers faster than adding eight good ones.
If the gaps section says reps are avoiding trigger topics, that's a discovery-depth problem wearing an objection-handling costume.
Example: what this looks like in practice
A founder-led sales team at a 20-person data-integration startup has an objection doc written a year ago at an offsite. The founder feeds ten recent transcripts plus the old doc into the prompt. Findings: the doc's number-one objection ('security concerns') appeared once in ten calls; the actual number one — 'we could probably build this with our own engineers' — appears in seven and isn't in the doc at all. Best observed response came from their newest AE, quoted verbatim. The landmines list includes the founder's own habit of responding with a feature list. The rebuilt playbook is two pages, and the build-vs-buy play alone recovers two deals the following month.
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
Build it from transcripts, not brainstorms. Extract every objection from 10+ real calls, cluster them by underlying concern, rank by frequency, and for each write a short spoken-language play — ideally canonizing responses that actually worked in your calls. A playbook built this way matches what reps hear; a brainstormed one matches what leadership fears.
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.