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?
Refining prompt is the only most important part in Generative AI usage. The better, accurate and precise the inputs in the prompt, better will be the output from the AI tool. Saving Changes...
Anonymous
I was able to provide a sample document to refine the structure of the output for a status report. Rather than trying to describe the output I wanted I provided the example and it made all the difference. Saving Changes...
I used to use AI to check my paragraphs written in English. When I first started using AI, I wrote very simple prompts. Now, I have a prompt that helps me compare the original version of my text with the suggested version from the AI, and it provides feedback explaining the suggestions. For me, refining the prompt helps me to improve the AI's response by providing clear instructions and context. I know that I am helping the AI understand exactly what I am looking for, which leads to more accurate and helpful responses. In addition, I'm using Notion to create a template and document my prompts. 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).
The commonality among all the prompt frameworks is that the machine needs a precise input so that it can generate a tailor-made responses that are in line with what we are seeking. Saving Changes...
Brian TripicchioConstruction-based Project ManagerAustin, Tx, United States
It's important to give the context and consistently refine with proper analysis of the previous iterations of prompts. Consistency and perseverance in the process as well as the outcome is crucial. Saving Changes...
Specifying the format of the output I am looking for helps a lot in saving time. I need to work with specific table tables and MS word documents with particular structure. When you provide a template or provide specifics of the layout, you get the needed result. Saving Changes...
Anonymous
It makes a big impact on the accuracy and transparency of the output data and information. Help the users to be more detailed and improve the output widely. Saving Changes...
This morning, one of my LinkedIn contacts complained that GenAI tools don't seem to have the ability to craft decent quality PMP practice exam questions. He had used the public version of ChatGPT. I decided to check the same with PMI Infinity and got better results - seven out of ten questions were acceptable.
My first prompt was "Generate ten different questions about project management which would be similar in style and level of difficulty to what is asked on the PMP exam"
It only gave me the questions but neglected to provide any answers. Realizing that this was likely it interpreting what I had asked for "as is", I then added: "Generate ten different questions about project management which would be similar in style and level of difficulty to what is asked on the PMP exam".
With that it was able to provided more useful output.
Kiron
Here I made a variation of the prompt focusing on some areas I wanted to reinforce, also I included "step-by-step answer":
Generate 3 complex, scenario-based project management questions that reflect the challenge and format of the PMP exam, focusing on areas such as risk management, stakeholder engagement, and schedule control. Provide detailed, step-by-step answers, incorporating key project management processes and terminologies.
PMI Team Member
