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 follow along and adapt it to your environment.

If this sparks ideas for your own digital CX programs, follow/subscribe and drop a review—it really helps more practitioners find the show.

Support the show

+++++++++++++++++

Like/Subscribe/Review:
If you are getting value from the show, please follow/subscribe so that you don't miss an episode and consider leaving us a review.

Website:
For more information about the show or to get in touch, visit DigitalCustomerSuccess.com.

Buy Alex a Cup of Coffee:
This show runs exclusively on caffeine - and lots of it. If you like what we're, consider supporting our habit by buying us a cup of coffee: https://bmc.link/dcsp

Thank you for all of your support!

The Digital Customer Success Podcast is hosted by Alex Turkovic

🎬 This content was edited by Lifetime Value Media.
Learn more at: https://www.lifetimevaluemedia.com

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