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?
The information is clear and concise. It geared closer to what I'm expecting to receive Saving Changes...
Barbi CollinsCox CommunicationsVirginia Beach, Va, United States
It can be the difference between prompting to request assistance with refining an email and going back to set the tone of the response to suit a Vice President vs a coworker or Manager. The output met my needs. 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).
Thanks for sharing, Sergio! Saving Changes...
Anonymous
Giving context really helps in getting the desired output. Saving Changes...
Marci HooverSenior Project Manager| Lockton CompaniesCentennial, CO, United States
Jun 29, 2024 8:47 AM
Replying to Dominic Williams
...
I like to phase my prompts in a series of steps and often map / plan my prompts before engaging with the AI tool. This saves time and less rework in revising one prompt over and over again.
I agree with this approach from a time saving standpoint and fewer prompts being required. Like any good process, you plan it out (as far as you're able) before diving in. Saving Changes...
Marci HooverSenior Project Manager| Lockton CompaniesCentennial, CO, United States
My experience has shown me that planning out my series of prompts prior to embarking on the process saves time and the need for additional prompts. We need to be open to considering new inputs and outcomes, but overall, being prepared (examples ready, word choices prepared, etc) is a great way to start. Saving Changes...
Silvia CastroCommercial Manager| GENPROSão Paulo, Sp, Brazil
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).
Frameworks are an important start point, specially for those that are new to the tools. Saving Changes...
Anonymous
With GenAI, I have found that refining a prompt has changed the broad and unfocused responses to ones where the output's quality is sharp and usable (almost ready to share with my coworkers). Saving Changes...
Now using Prompt dexterously is becoming an art rather than a science - refining, long-chaining, using the RTF and CREATE Frameworks is giving outputs more precise, accurate, predictable and relevant to the context; utility of the responses are on the higher side. These FUNDAs are now more FUN to PLAy with .... Saving Changes...
I think it is important to give the context and also to refine, asking for a different output in case that the first one is not completely suitable to our purpose or to the outcome that we were looking for. I think that consistency and preseverance in looking for the result, is crucial as well.
It is very helpful because the refining techniques allow to narrow down the required output in each iteration, avoiding unnecessary information to be displayed. Saving Changes...
"We should be careful to get out of an experience only the wisdom that is in it - and stop there; lest we be like the cat that sits down on a hot stove-lid. She will never sit down on a hot stove-lid again, and that is well; but also she will never sit down on a cold one anymore."
PMI Team Member
