Season 3, Episode 17: The Scientific Approach to Prompt Engineering (with Mike Taylor)

In this episode of the Mobile Dev Memo podcast, I speak with Mike Taylor, the co-author of a new book, Prompt Engineering for Generative AI: Future-Proof Inputs for Reliable AI Outputs, published by O'Reilly. Taylor was previously the founder of a 50-person growth marketing agency, Ladder.

In our conversation, among other things, Mike and I discuss:

• How Prompt Engineering is a skill that can be improved upon over time;
• The non-obvious ways in which prompt engineering can be approached in order to improve outcomes;
• How Prompt Engineering can be approached procedurally and programmatically, and how companies should think about building systems that improve their LLM interactions over time;
• Whether the growth hacking model has fallen out of favor;
• The principal challenges of running an agency;
• Whether marketing generally suffers from a lack of statistical literacy.

Thanks to the sponsors of this week’s episode of the Mobile Dev Memo podcast:

• ⁠⁠⁠Clarisights⁠⁠⁠. Go to⁠⁠⁠ clarisights.com/demo⁠⁠⁠ to try it out for free. You’ll see why thousands of performance marketers trust Clarisights every day.⁠⁠
• INCRMNTAL⁠⁠. True attribution measures incrementality, always on.

Interested in sponsoring the Mobile Dev Memo podcast? Contact ⁠Marketecture⁠.