Voice to Value: I Used ChatGPT Voice to Help Build an Automation | Episode 099

Episode notes

In Episode 99, I do something a little different: I take you behind the scenes as I use ChatGPT in voice mode to design a real automation from start to finish. The goal? Build an internal chatbot for product and engineering that’s trained on CX call transcripts stored in Gong , so teams can ask targeted questions (“What’s frustrating customers in Module X?”) and get instant, concise answers with deep links back to the exact call moments . You’ll hear how I frame the problem, push the model to avoid hallucinations, and pick a stack that balances speed, privacy, and scale : Gong → Airtable as the searchable store → a Zapier-hosted chatbot for querying. We also cover transcript hygiene (auto-removing small talk and personal details), vendor privacy considerations, and a simple habit hack: having AI remind you later to actually implement the ideas you generated while walking the dog. I’ll link the step-by-step PDF I asked ChatGPT to generate in the show notes so you can