LLMs are basically big “text predictors” that try to generate outputs based on what it expects is the most likely desired output based on what the user provides as the text-based input, the prompt. Prompts are natural language instructions for an LLM provided by a human so that it will deliver the desired results you’re looking for. In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer dig into using a prompt pattern. They explain what prompts are, why good prompts are so important, and why using prompt patterns are a prompt engineering best practice.

To ensure your prompt contains all essential elements for optimal results, adopt a structured "formula" approach. Most of the popular prompt pattern formulas for creating prompts include aspects of the following: Act as a [ROLE], Performing a [TASK], Responding in a [FORMAT]. There are many different prompt patterns out there, and the right one for you depends on your needs. There are a number of considerations for determining which Prompt Engineering pattern or formula to consider. In the podcast we discuss the RTP and CREATE patterns and provide examples of when to use both prompt patterns.

This is part 1 in our 6 part series on Prompt Engineering Best Practices. Subscribe to AI Today to get notified of upcoming episodes in this series and learn the best practices for prompt engineering from Cognilytica AI thought leaders.

Show Notes:

• Free Intro to CPMAI course
• CPMAI Certification
• Subscribe to Cognilytica newsletter on LinkedIn
• Properly Scoping AI Projects [AI Today Podcast]