Director, Learning Design & Development| PMIAsheville, NC, United States
With Generative AI, iteratively refining and optimizing prompts can lead to better AI-generated results. This may involve adjusting the specificity or clarity of the prompt to increase relevance and accuracy of results.
What examples do you have of how improving a prompt drastically changed the output quality? What specific changes did you make that led to the improvement?
Yes. for sure. Our experience from real life has been exactly what is explained in this module in the course, and we have also created a library like you propose though without a scoring system. But that could be good, so we will think about that. Saving Changes...
Still doing the course and getting my head around prompting; yet could not but wonder at how Ai-ism can be used in alternative worlds, say for example in my area of interest diplomacy and global politics and not strictly project management. It holds fascinating potential for cutting reporting workloads, introducing novel ideas for unlocking conflict or sticky bi-lateral issues between countries can support with briefings on country positions and policies on specific issues and matters of concern for active and personal diplomacy. Limitless and exciting Saving Changes...
Anonymous
Lots of great information and can't wait to try some of the recommended techniques for building/ writing solid prompts Saving Changes...
Ashwini ApteSan Francisco Bay Area, California, United States
Prompt chaining helped me to improve the AI results. Breaking down the tasks like we do in WBS helps the AI to learn and produce specific results as we do to get the estimates as closer to the actuals. Saving Changes...
Emily BoudreaultProduct Management ConsultantGeorgetown, Ma, United States
Jun 21, 2024 7:28 AM
Replying to Sergio Luis Conte
...
There are framewoks to create prompt. This is part of the Prompt Desing discipline. Those that gave me and the initiatives where I was included are:R-T-F (Role-Task-Format), T-A-G (Task, action, goal), B-A-B (Before, after, bridge), C-A-R-E (context, action, result, example), R-I-S-E (role, input, steps, expectations).
Thank you for sharing the prompt frameworks, Sergio. I am interested to try these and research other examples Saving Changes...
WILLIAM COSTAProject ManagementSão Bernardo do Campo, SP, Brazil
By refining a prompt we ensure the output according to the quality we expect. It's crucial to sustaining an iteractive process with GenAI through refining and learning.
Saving Changes...
Maria Thompson-SaebSenior Manager Governance, Risk, and Compliance| Illumio, Inc.Laguna Niguel, Ca, United States
Once I was looking for information on a specific subject matter and I wanted the LLM to give me a more refined list of items, I included “be specific” in my prompt which gave much better results. Saving Changes...
Refining my prompt has changed the output quality for the better, especially when I continue to respond to the outputs to get it to where it needs to be. The output ends up being more clear and more concise than the original output. Saving Changes...
There are framewoks to create prompt. This is part of the Prompt Desing discipline. Those that gave me and the initiatives where I was included are:R-T-F (Role-Task-Format), T-A-G (Task, action, goal), B-A-B (Before, after, bridge), C-A-R-E (context, action, result, example), R-I-S-E (role, input, steps, expectations).
For simple situations, use RTF formulae to get responses from AI LLMs. For complex situations or scenarios, use CREATE formulae by chaining of simple prompts to receive better and more accurate responses from AI. Saving Changes...
PMI Team Member
