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?
As project Manger it's our responsibility to check the information that we had from AI, and of course they will never replace human Saving Changes...
Yogesh DeochakkeSumitomo Pharma AmericaShrewsbury, Ma, United States
Refining the prompt to include more specifics and follow up questions/responses based on previous outputs gets the GenAI to generate outputs that are more specific and complete for the set context. Saving Changes...
Girish Kumar DharanSenior Management Specialist| SAPBangalore, Karnataka, India
Few prompt refining techniques which has helped me a lot are
1. Providing the context in the prompt.
2. Adding in the prompt a statement like "if you need any additional information to provide a better outcome, ask me the same".
3. Asking the AI tool to refine the prompt :-). Saving Changes...
Ling Yu TSOIProgramme officer| The Hong Kong Academy of Gifted EducationYuen Long, -, Hong Kong
I would add more details to the prompt by specifying the roles, tasks, and format. Sometimes I drafted my own outline and examples so as to make the outcome more satisfactory. I might try to save some of my prompts next time so as to save time later when encountering similar tasks! Saving Changes...
In my experience, refining a prompt with GenAI can completely transform the quality of the results. A simple example is when you need a summary of a technical report. If the prompt is general, like “summarize this report,” the result can be inaccurate. But if you specify “summarize this report focusing on safety, efficiency aspects and improvements opportunities” you get a much more relevant and useful information. Refining the prompt guides the AI ​​to provide information you actually need. Saving Changes...
Russell SandidgeDirector Cybersecurity| Varada ConsultingSterling, Va, United States
A PMI term stuck in my head is progressive elaboration. This is how I use generative AI. I am learning about prompt engineering but have always tried to revise my output by continuing to iterate my prompts. I have learned to keep revising until I am satisfied. As I master prompt engineering I will not need as many iterations. Saving Changes...
Shin MikamiHPC Support Escalation Engineer| Microsoft JapanSaitama, 11, Japan
I was not farmiliar with GenAI framework, but I now knew there're some frameworks for project management: R-T-F, C-R-E-A-T-E.
Iterative approach is also helpful. Saving Changes...
You need to be able to create effective prompts to get the most out of AI.
04 tips to help you get the most out of AI
1 - Make prompts clear and specific
When creating your prompts, make sure they are clear and clearly specify the desired format, tone and output you want.
2 - Provide context
The more context you can give the AI, the better the results will be. Provide as much relevant information as possible in your prompts to help the tool understand the context of your request.
3 - Anchor your prompts with examples
Providing examples is a powerful way to anchor your prompts and give ChatGPT a frame of reference to work from.
4- Break it down into steps
Breaking it down into steps is a powerful way to create prompts that get better results. Saving Changes...
Jose InsenserServices Portfolio Manager| AirbusMadrid, Spain
In my experience managing technology in large defense programs, refining prompts for GenAI has substantially increased output quality and response times. Initially, broad prompts led to generic results, but by cross-checking requirements from various projects and optimizing large sets of requirements, we fine-tuned the prompts for specific needs. Tailoring AI outputs to align with our processes and deliverables made the results much more actionable. Additionally, refining prompts to identify gaps and opportunities for improvement allowed us to continuously enhance our processes. Overall, precise and tailored prompts significantly improved the relevance and usefulness of the AI’s output, making a substantial impact on our project outcomes. 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. Saving Changes...
PMI Team Member
