Turn each authorized customer call into a traceable account-health signal by cleaning the transcript, resolving the account and owner, extracting evidence-backed risks and next steps, and routing the result to the right team.
Source episode · 10:00
How Suzy's CEO Turns 25,000 Hours of Sales Calls into Automated Marketing and Coaching with One Zapier Workflowwith Claire Vo
Matt triggers on new Gong calls, retrieves and cleans each transcript, enriches it with account and rep data, generates a structured call-health summary, posts it to Slack, and routes low scores to an early-warning channel.
A source-linked call summary with account context, evidence-backed risk signals, commitments, and next steps, plus an alert when defined criteria need human follow-up.
OpenAI conversational AI
Workflow automation platform
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
5 steps
Trigger on a completed authorized call and retrieve its transcript through the supported API or export. If a browser extractor is required, confirm permission and validate the call ID and source URL before use.
The original creator noted this step was the most difficult. Don't give up if a direct integration is missing; web scraping tools can often bridge the gap.
Wait for transcript completion, remove markup without losing speaker and timestamp structure, and join the call to account and employee records using stable IDs. Reject missing or ambiguous joins.
Ask the model for a structured summary with cited evidence, customer-stated concerns, positive signals, commitments, next steps, and a non-binding risk score with confidence.
Analyze this customer call using the attached rubric. Return account and participants, purpose, key topics, customer-stated goals, positive signals, concerns with timestamped evidence, commitments by owner and date, next steps, risk level, confidence, and missing context. Separate direct statements from inference. A score is a triage signal, not a churn prediction.
Post a concise summary to the approved customer-call channel with a link to the governed source. Omit the full transcript and any detail the audience does not need.
Format the following information into a Slack message for the #customer-calls channel. Use Slack's formatting, like bolding for headers, and emojis for sentiment. Customer: [Customer Name] Rep: [Salesperson Name] Sentiment Score: [Score from 1-10] *Summary:* [Paste AI-generated summary] *Next Steps:* [Paste AI-generated next steps]
Route calls that meet the reviewed alert criteria to the restricted account-risk channel. Name the account owner, evidence, required follow-up, and acknowledgment deadline, then record the owner’s final assessment.
Create an account-risk alert from this reviewed summary. Include the evidence, confidence, open questions, accountable owner, next action, and due date. Do not state that the customer will churn. Require the owner to confirm, downgrade, or escalate the signal.
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building
Design a weekly meta-workflow that analyzes your interactions with your AI assistant to make it smarter. This system learns your writing style from edits, suggests new automations for repetitive tasks, and helps you filter valuable AI techniques from hype.
Create a daily AI workflow that summarizes yesterday's meetings, identifies urgent tasks, and proactively learns internal company terms it doesn't understand. This keeps your AI assistant's knowledge current and highly relevant to your work.
Build a recurring AI task that automatically gathers updates from your calendar, Slack, and notes to suggest weekly priorities and prepare you for upcoming meetings. Start every Monday with a clear, comprehensive plan without the manual effort.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.