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.
You are a RevOps consultant who has cleaned up hundreds of CRMs, and you know the pattern: call notes are either three vague words ('good call, interested') or a wall of AI-notetaker summary nobody reads. Useful CRM notes are structured, scannable in 20 seconds, and written so a colleague could pick up the deal cold.
I'm going to paste a call transcript. Convert it into a structured note with these exact sections:
PAIN POINTS — each as one line: the pain, who owns it, and its stated or implied cost. Quote the prospect's phrasing in parentheses where it's vivid. Rank by severity as the prospect described it, not by what our product fixes best.
CURRENT STATE — what they use or do today for this problem, including 'nothing' or 'spreadsheets' if that's the truth.
STAKEHOLDERS — every person or role mentioned, with their stance if detectable: champion, neutral, skeptic, unknown.
TIMELINE & TRIGGERS — dates, deadlines, contract renewals, or events driving urgency. If none surfaced, write 'No timeline established' — that absence is information.
NEXT STEP — what was agreed, with owner and date. If fuzzy, say so.
OPEN QUESTIONS — the 2–4 things we still don't know that most affect this deal.
Rules: no full sentences where a fragment works. No pleasantries, no 'they seemed positive'. Total length under 250 words — if it doesn't fit, you're summarizing the call instead of extracting the deal. Never invent a stakeholder stance from tone alone; mark it unknown.
Before you analyze anything, interview me. Ask me these questions ONE AT A TIME, waiting for my answer each time:
1. Paste the full call transcript.
2. What does your company sell, in one sentence?
3. Any specific fields your CRM requires that I should map to (or should I use the default sections)?
Once you have my answers, produce the note.How to use it
- 1
Copy the prompt into Claude, ChatGPT, or Gemini.
- 2
Paste the transcript right after the call, while you can correct anything it gets wrong.
- 3
If your CRM has required fields, list them in question 3 and the note maps to them directly.
- 4
Skim the output against your memory of the call — fix stakeholder stances especially — then paste into the CRM.
- 5
Once the format proves out, wire it into n8n or Zapier: recorder webhook in, LLM call, CRM note out.
Best practices
The open-questions section is your next-call prep — start every pre-call review there.
Keep the model's severity ranking honest: if it ranks pains by what your product solves, re-run with 'rank by what the prospect emphasized.'
Standardize this across the team; identical note structure is what makes pipeline reviews fast and handoffs painless.
This prompt is the manual version of an automation — once you trust the output, the same instructions become your n8n system prompt.
Example: what this looks like in practice
A RevOps lead at a 80-person SaaS company is tired of pipeline reviews stalling on 'what's this deal about?' She rolls this prompt out to the AE team with their five required Salesforce fields mapped in. A typical output: three ranked pains (top one: manual onboarding costing 'probably a full head, honestly'), a stakeholder list flagging the IT director as unknown-stance, 'No timeline established' in triggers, and open questions including who owns the budget line. Reviews get noticeably faster, and two months in she connects the same prompt to their Fireflies webhook via n8n — reps now edit a pre-drafted note instead of writing one.
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
From the transcript, yes — and better than most AI notetakers' native summaries, which summarize the conversation instead of extracting the deal. The difference is structure: pains ranked with owners and costs, stakeholder stances, and explicit gaps like 'no timeline established.' You review for 30 seconds and paste, instead of writing from memory.
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.