Call Transcript Analysis & Coaching prompts
Turn raw call transcripts into objection intel, coaching scorecards, follow-ups, and playbooks — no call review software required.
36 prompts · paste-ready, no variables to fill · free
Every sales call you record is sitting on insight your team never extracts: the exact words prospects use to object, the moment a demo lost the room, the deal risk hiding in polite language. These prompts turn any LLM into a call review engine — paste a transcript from Gong, Fireflies, Fathom, Zoom, or Google Meet and get structured analysis a sales leader would charge for.
They're built for sales leaders coaching a team, AEs reviewing their own calls, and founders selling without a manager to learn from. Most prompts need one transcript; the pattern-analysis and playbook prompts want 5–10. Use a large-context model like Claude or Gemini for long or multiple transcripts, answer the short interview honestly, and treat the output as a first read you pressure-test against the recording.
Build a discovery question bank tailored to one persona
Generates a 15-question discovery bank built around one persona's actual responsibilities and failure modes, organized by call stage, with listening notes on what strong and weak answers sound like. Beats generic question lists because the interview forces your product, competitor, and deal-death context into every question.
Cold call role-play: the AI plays a skeptical VP and scores your performance
Turns the model into a realistic, interruption-prone VP buyer who objects, tests, and warms or cools based on how you actually perform, then scores you across five dimensions with the exact moment you lost them and a drill to fix it. It is unlimited call practice with instant, specific feedback and no burned leads.
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.
Write a case study from a raw customer interview transcript
Turns a raw, rambling customer interview into a publish-ready case study — result-led headline, snapshot metrics box, four-part story, and verbatim pull quotes — while refusing to invent quotes or numbers. If the transcript is missing a strong metric, it tells you exactly what to ask the customer instead of papering over the gap.
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.
Annotate your script with tonality, pacing, and pause marks
Turns your script into a performance document: inline pause marks, stress caps, pacing shifts, and falling-inflection notes on your exact words, plus your three danger zones, mandatory silences with durations, and a 60-second vocal warm-up. It coaches the half of cold calling that word-focused script work never touches.
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.
Audit whether your call secured a real next step
Grades the end of your call against the four criteria of a real next step — specific, mutual, advancing, confirmed — finds the moments mid-call where you could have asked for more, and drafts the recovery email if the ending was soft. It turns 'I think it went well' into a pass/fail you can act on.
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.
Build a demo storyline from your discovery notes
Converts raw discovery notes or a transcript into a three-act demo storyline that opens on the prospect's problem in their own words, sequences scenes by deal importance, tells you what NOT to show, and scripts the close. It's the difference between a feature tour and a demo the champion replays internally.
Build a monthly coaching plan from a rep's call patterns
Reads a month of one rep's calls and produces a complete coaching plan: a scored skill audit with evidence quotes, the single keystone weakness chosen for leverage, four weekly blocks of observable behaviors and drills built from the rep's own call moments, and the strength-first script for presenting it in the 1:1.
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.
Build an objection playbook from your last 50 real replies
Turns your reply inbox into the objection playbook your team actually needs — clustered from real replies with verbatim quotes, counts, and percentages, not a brainstormed fiction. You get model responses for the top three objections in your voice, a blunt diagnosis of what the objection mix says about your targeting and copy, and an audit of which of your past responses reopened threads.
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.
Drill turning objections into questions until it's automatic
Runs a live drill session that builds the objection-to-question reflex: worked examples of the reframe pattern, rapid-fire objections from your actual market with instant pass/fail grading, escalation to stacked and emotional objections, and a session report exposing your pressure pattern. It trains the muscle that reading rebuttal lists never builds.
Extract win and loss signals from a sales call transcript
Reads a transcript the way a seasoned deal reviewer would: separating real buying signals from polite enthusiasm, flagging risk hiding in hedged language, and — most usefully — naming what a healthy deal should have shown that this call didn't. Ends with a deal-health score and one action to test if the deal is real.
Find patterns across 5–10 call transcripts: objections, drop-offs, momentum
Analyzes a batch of transcripts as a dataset instead of one-off reviews: objections recurring across calls, the exact points where prospect energy dies, the moments that reliably create engagement, and gaps between what you pitch and what prospects care about. Ends with three evidence-backed changes your team can start Monday.
Generate a note-taking template for your sales motion
Designs a discovery note template where every field has a downstream customer — the follow-up email, demo build, forecast, or handoff — plus a during-call versus after-call split, one-keystroke red-flag codes, and both plain-text and markdown formats. Kills both blank-page notes and the 40-field CRM form nobody fills.
Generate a post-call self-review checklist from your call notes
Builds a personal review system in three layers: a 90-second yes/no checklist tuned to your script and weaknesses, a weekly pattern tracker that outputs exactly one fix, and a transcript deep-dive protocol for recorded calls that finds the moment each call was decided. It converts call volume into compounding skill instead of repeated experience.
Generate the follow-up email directly from the call transcript
Drafts the post-call email straight from the transcript: opens with the prospect's own most important point, advances exactly one thread instead of recapping everything, honors every commitment made on the call, and locks a dated next step. The not-included list explains what it left out so you don't stuff it back in.
Mine competitor mentions across your call transcripts
Harvests the competitive intel buried in your calls: every rival mentioned, in what context, with real sentiment separated from negotiation theater, plus concrete nuggets like pricing figures and renewal dates. Ends with battlecard updates your current talking points probably miss — sourced from prospects, not marketing pages.
Objection flashcards for 'I'm busy' and 'send me an email'
Produces six drill-ready flashcards for the two most common cold call brush-offs, each with the decoded meaning, an exact sub-25-word response ending in a question, the psychology behind it, and the mistake to avoid. It turns the two moments that kill most calls into rehearsed, automatic responses.
Objection flashcards for 'not the right person', 'we're all set', and 'how did you get my number'
Produces six flashcards covering three structurally different objections, each with decoded meaning, an exact response under 30 words ending in a question, and the mistake to avoid. It stops you handling a trust question, a status-quo reflex, and a referral opportunity with the same generic rebuttal.
Practice written objection handling against a role-play sparring partner
Gives reps unlimited reps against a prospect that behaves like a real inbox: terse, distracted, unimpressed by pitch dumps, and willing to go silent when your response deserves it. Every three exchanges you get a graded coaching report that quotes your actual weakest sentences and rewrites them — deliberate practice for the written objection skills most teams only train verbally.
Pull verbatim prospect quotes to power your follow-up email
Mines a transcript for the prospect's exact words — pains, goals, deadlines, politics, objections — and sorts them by whether it's safe to quote them back, paraphrase them, or just privately know them. You get a ready quote bank plus the three strongest lines for your follow-up, deployed naturally.
Refine your ICP with win/loss data
Puts your ICP on trial against actual deal outcomes: every criterion gets a confirmed/challenged/untested verdict, hidden win and loss pockets get surfaced, and loss reasons get sorted into targeting versus execution problems. You leave with an evidence-backed revised ICP and one clean hypothesis to test next quarter.
Review demo call effectiveness from the transcript
Audits a demo the way a coach watching the recording would: maps every segment to a stated prospect pain (flagging pure feature tour), charts engagement through prospect interjections, finds the peak-interest moment and whether the rep capitalized on it, and grades the close. Names the segment to cut and the moment that deserved more.
Role-play a negotiation against a tough procurement lead
Turns the LLM into a realistic procurement sparring partner that anchors low, weaponizes silence, and punishes free concessions — calibrated to your actual deal. PAUSE gets you mid-fight coaching; DEBRIEF gets a scored breakdown of your concession discipline with the exact words you should have used.
Role-play your discovery call with the LLM as the prospect
Turns the LLM into a realistic discovery sparring partner with a hidden agenda you must dig to uncover — a buried pain, a held-back objection, internal politics — plus a curveball. Ends with a scorecard revealing what you missed and the two highest-impact fixes. It's rep practice with none of the scheduling and all of the honesty.
Run a 'why we lose' analysis on your lost deals
Reclassifies your CRM's fictional loss reasons into a real cause taxonomy, finds the dominant patterns and the cheapest one to fix, arms you with buyer interview questions that get past politeness, and installs a twice-monthly loss review — turning 'we lose on price' folklore into a fixable diagnosis.
Sequence your discovery questions from surface to impact
Builds a four-layer question sequence — facts, friction, consequence, stakes — with the bridge phrases that make deepening feel natural, the prospect phrases that signal 'dig here', and rules for when to stop. Fixes the universal discovery flaw: surfacing a pain signal and pitching instead of digging one layer deeper.
Spot multi-threading gaps from attendee talk time
Maps who actually shows up and speaks across a deal's calls: voice share per attendee, roles read from their words, silent lurkers flagged, and the stakeholder roles nobody on any call fills. Then gives you a specific, champion-safe play to open each missing thread before the deal's single thread snaps.
Turn a call transcript into structured CRM notes
Converts a rambling transcript into a sub-250-word CRM note structured around what deals actually run on: ranked pains with owners and costs, stakeholder map, timeline triggers, agreed next step, and open questions. Consistent enough that anyone on the team can pick up the deal cold — and consistent enough to automate.
Turn customer conversations into LinkedIn posts your ICP actually reads
Mines a real customer or prospect conversation for its sharpest insight and shapes it into a phone-readable 80–180 word post with a working hook, ruthless anonymization, and no engagement-bait. Also banks the leftover insights as future post ideas, so one good call can feed a week of content.
Frequently asked questions
Yes, with the right constraints. LLMs are strong at exactly what call review requires: finding every instance of a pattern (objections, questions, next steps), quoting verbatim, and scoring against a rubric you define. The failure mode is vague prompts that produce vague summaries — these prompts force structured output, verbatim evidence, and explicit scoring criteria so you can verify every claim against the transcript.
More prompt categories
Want this running on autopilot instead?
We wire prompts like these into a full outbound system — data, personalization, sending, and replies orchestrated end to end. You own the infrastructure. We guarantee the results.
Apply for a Pilot Spot →