Turn your customer conversations into a powerful content engine. This workflow uses Zapier and an LLM to extract Google Ads keywords and write fully anonymized, SEO-optimized blog posts based on real customer problems.
with Claire Vo
Begin with the cleaned call transcript from your Gong/Browse AI trigger in Zapier. Add a ChatGPT action and prompt the model to analyze the transcript to identify keywords and phrases the customer used to describe their problems and needs.
Use the Google Ads integration in Zapier to automatically add the keywords extracted by the LLM to a relevant ad campaign. This creates a powerful feedback loop where the exact language of your customers is used to attract new ones.
Analyze the following customer call transcript. Identify and list 5-10 long-tail keywords and phrases the customer used when describing their business problems and desired outcomes. Focus on their natural language. Format the output as a comma-separated list.Before generating public content, you must protect customer privacy. Add another ChatGPT action with a specific prompt to redact all personally identifiable information (PII) from the transcript, such as names, company names, and project details, replacing them with generic placeholders.
Use a final ChatGPT action to transform the anonymized conversation into a blog post. Prompt the model to write an article focused on the business problem discussed, including an SEO-optimized headline, a body that explains the challenge and solution, and a call-to-action.
Using the provided anonymized transcript, write an SEO-optimized blog post about the core business problem discussed. Create a compelling headline, a body that explains the challenge and solution in a general way, and a call-to-action for our company. Do not use any real names or companies.To create a consistent content pipeline, add a Zapier 'Delay' step to schedule the post for a future date (e.g., 21 days later). Finally, connect to your CMS (like WordPress or Webflow) to create a draft of the generated blog post, allowing for a final human review before it goes live.
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.