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?
Thank you Sergio for sharing your Prompting rules. I like it, it is very simple to use and to remain. I will try to think to these rules for my futur Gen AI prompt. Saving Changes...
Thomas O'BryanEngineering Manager| Accessible Technologies IncLouisburg, Ks, United States
Refining prompts shifts AI from producing general information to delivering targeted decision support. The quality of the output scales directly with the quality of the prompt. Saving Changes...
Anil RahejaProject Manager| Tadweer GroupAbu Dhabi, United Arab Emirates
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).
I have found specially use of R-I-S-E (role, input, steps, expectations) very helpful. By assigning a specific role of the Model, accuracy of response improved drastically. 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).
I totally agree, the more context with defined structure best results I've found, reforcin with giving examples for the desired result. 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.
Agree being consistent with refinement will aid in ensuring consistent products across a project. Saving Changes...
Madalyn LindseySenior Project Manager| Lenovo, LtdDurham, Nc, United States
Refining a prompt can completely transform GenAI output quality—think of it as moving from “good enough” to “executive-ready.” Early in my experience, I asked for a “risk summary for a project” and got a generic list of risks that lacked prioritization and actionable detail. After applying best practices from PMI’s Prompt Engineering Workbook, I reframed the prompt: “Generate a table of the top five project risks ranked by impact and likelihood, include mitigation strategies, and format for an executive dashboard.” The difference was night and day—the output was structured, relevant, and immediately usable for stakeholder reporting. The lesson? Precision and context matter. Adding constraints, specifying format, and clarifying success criteria turns AI from a brainstorming tool into a strategic partner. Iteration is key—each refinement sharpens alignment with your goals. In short, better prompts = better outcomes, and mastering this skill elevates your value as a PM in the AI era. Saving Changes...
"When one door closes another door opens; but we often look so long and so regretfully upon the closed door that we do not see the ones which open for us."
PMI Team Member
