Episode 96: Real Example: Coaching a Team to Use ChatGPT for Scalable Research

Episdode Summary 

In this solo episode of The ChatGPT Experiment, host Cary Weston breaks walks through a real-world example where he helped a trade advocacy group automate and streamline their time-consuming research process using ChatGPT’s Projects feature. Cary shares his 4-part framework for setting up successful prompts and emphasizes the importance of engaging ChatGPT in dialogue, not just handing it a task and hoping for the best.

---

3 Key Takeaways

• Use Cary’s 4-Part Framework: When talking to ChatGPT, always explain: 1) What are we doing? 2) Why are we doing it? 3) What does success look like? 4) Do you have questions to help you do your best work?
• Don’t Rush the Task: Jumping too quickly into asking ChatGPT to “do something” often leads to poor results. Instead, let it help you plan, think, and collaborate.
• Structure for Flexibility: When building Projects, keep the instructions (the “brain”) stable, but make supporting documents modular—this makes updates and improvements much easier over time.