Title: How to Create Effective Prompts for ChatGPT
This is the third AI Lunch and Learn in the series. Where the first two sessions were high level overviews of the current and future state of Generative AI, this third session focuses on specific practical examples of the types of prompts to use for different classes of problems in life and work. The structure of an effective prompt will be demonstrated:
- Instruction - a specific task or instruction you want the model to perform
- Context - external information or additional context that can steer the model to better responses.
- Input Data - the input or question that we are interested to find a response for
- Output Indicator - the type or format of the output.
We will go through examples of zero/one/few-shot learning to show when to use each type and how to improve accuracy and eliminate errors. We will use real world examples that will directly benefit attendees' work and projects.
We will finish with a Q&A session and a discussion of next steps.
Please attend with ChatGPT open so that you can follow along with the examples and case studies.
Ronald J. Kelley, PhD, ASQ CSSBB, is the founder of Green Gap Solutions and Curriculum Manager for the NSF I-Corps Great Lakes Hub. He has over 25 years of experience in innovation, process improvement, and risk management for government and corporate clients. He is a serial entrepreneur and now trains and mentors new startup companies through the University of Wisconsin - Madison and the National Science Foundation (NSF) I-Corps program. Dr. Kelley recently started a non-profit corporation, CiZen.org, to evangelize and train mid-career professionals in the use of AI technologies in quality, with a focus on problem-solving and data analysis.