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?
Specificity with the initial prompt helps get you in the ballpark. By iteratively prompted the AI with appropriate follow ups, the tool is able to better define the output toward what you are looking for. I keep going layers deep with the questions to refine the response and it helps immensely. 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).
Very clear about the frameworks (acronyms 😉) and 1 point that i learned is that you can add a file to be used as input or sample .
The latter really made a positive difference. 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).
Adding your Prompt Design Discipline references to my notebook. Thanks...kl Saving Changes...
Refining a prompt is crucial for obtaining high-quality outputs from GenAI models. By providing clear, specific, and detailed instructions, you can significantly enhance the relevance, depth, and usefulness of the generated content. This process involves considering the context, desired format, tone, and specific details to guide the AI in producing the best possible response. Saving Changes...
Christina DietrichCustomer Project Manager| Nokia of North AmericaSeattle, Wa, United States
Jun 23, 2024 5:15 PM
Replying to Booma Pugazhenthi
...
To improve getting answers from GenAI tools, try adding specific instructions to your prompt, such as "Generate ten different questions about project management, similar in style and difficulty to the PMP exam, and provide detailed answers for each." This ensures the tool understands the need for questions and answers in the output.
Appreciate your explicitly stating that answers were wanted, Booma. I didn't see that in the original modified text and was confused about how one would get an improved response from posting the same request twice. Saving Changes...
Continuing with the comparison to when the internet first came out, refining prompts greatly improves output by narrowing the dataset from which results are pulled thereby increasing relevancy, accuracy, and appropriate context. 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
Excellent example of what refining prompts will do for the PM Saving Changes...
Refining a prompt really makes a difference. The clearer and more specific you are, the better the results. When the prompt’s vague, you get generic answers. But with the right details, the AI can give you exactly what you need. It’s all about asking the right questions.
Absolutely, breaking down prompts, refining persona, altering tone, changing key works and being more clear and concise have brought better output. Even better is to evaluate and ask questions back. Saving Changes...
PMI Team Member
