Automatically scrape call transcripts from a tool like Gong, use ChatGPT to analyze sentiment and generate summaries, and send real-time churn alerts to your team in Slack with a powerful Zapier workflow.
with Claire Vo
The first step is getting the call data into Zapier. Since a direct integration may not exist, create a Zap that triggers when a new call is logged in your system (e.g., Gong). Then, use a tool like Browse AI to scrape the call transcript page. The initial trigger should provide a unique call_id that you pass to Browse AI to construct the correct URL.
Raw scraped data is often messy. Add a Zapier Formatter step to strip any HTML tags from the transcript. Then, use a Google Sheets 'Lookup Spreadsheet Row' action to connect the call ID to internal data, pulling in the customer's name, the salesperson's name, and their Slack ID for later steps.
This is the core analysis step. Add a ChatGPT (or other LLM) action in Zapier. Feed the cleaned transcript into a detailed prompt that asks the model to generate a structured summary, assess customer sentiment, and provide a numerical sentiment score from 1-10.
Analyze the customer success call transcript between Suzy and our client to gauge the health of customer relationships and identify improvement areas. Start summaries with the customer's, company name key participants... describe the call's purpose, the main topics discuss, and the outcome exclude small talk... Assess the overall customer sentiment, noting any frustrations or concern. Provide a sentiment score from 1 to 10 where 10 reflects high satisfaction and 1 indicates potential discontinuation of our services. Also one great thing the customer successfully did on the call... what are some things that they actually could have done better, and then list the next steps.Make the insights visible to the whole team. Configure a Zapier action to post the AI-generated summary of every call to a general-purpose Slack channel, such as #customer-calls. This creates a live feed of customer sentiment for the entire company.
To make the insights actionable, add a Zapier 'Filter' or 'Path' step. Set the rule to only continue if the sentiment score from ChatGPT is below a certain threshold (e.g., less than 7). If the condition is met, send a high-priority notification with the call summary and customer details to a dedicated Slack channel like #churn-early-warning.
Follow Sahil Lavingia's method for delegating small but impactful maintenance tasks, like fixing an internal Slack report, to the AI agent Devin. This workflow shows how to use simple, clear prompts to fix code and update system prompts without distracting your engineering team.
Learn Gumroad CEO Sahil Lavingia's process for rapidly prototyping a UI with v0, then using the AI agent Devin to autonomously code, implement, and submit the feature for review, turning a multi-day task into a one-hour workflow.
Improve your writing in real-time by using ChatGPT as a first reader. Get instant feedback on structure, clarity, and flow as you write, allowing you to polish your work section by section.
We've made ChatPRD affordable so everyone from engineers to founders to Chief Product Officers can benefit from an AI PM.