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?
It has made it generate more relatable output Saving Changes...
Akhil Antony Nedumparambil GeorgeStudent Mentor| Northeastern University Toronto, College of Professional StudiesToronto, Ontario, Canada
Refining a prompt can be a game changer when it comes to AI output. It's like asking for directions: the clearer you are, the better the response. By specifying details or clarifying your intent, the AI can focus and deliver exactly what you're looking for. When the prompt is vague, the result might be too broad or generic. It’s about guiding the AI without overloading it. A simple adjustment can shift the response from passable to spot-on, making all the difference in quality and relevance. Saving Changes...
Janelle AlexanderHeritage Petroleum Company LimitedSan Fernando, Sfo, Trinidad and Tobago
Refining the prompts helps me to ask further questions based on the responses received from the AI. When I first started using AI, my questions were vague but as I progressed in using it, became more specific in what I asked. I would define my role, context and outcome. I would break up the questions, allowing me to build on my previous question. Saving Changes...
Anonymous
It has helped in responding with a more human response, interaction instead of just providing facts and challenged me to rethink how to present meeting notes in a softer tone, less demanding especially when it comes down to the action items and next steps. 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).
These methods are quite helpful. Thanks a lot..! Saving Changes...
I have noticed that continuing with a conversation over time improves the quality of out as well overtime. For example, I run a blog series which I have been using AI to write. After about 4 posts of refining the quality of outputs, I noticed that I only needed to iterate my prompts only 20% of the time.
So, if you put in the work earlier on in a project to really set the scene for the LLM, you won't need to work as much during the project.
Saving Changes...
Anonymous
Consistent iteration is key. Over time, learning to spot what does and doesn't work will create efficiencies in the system that save more and more time. Saving Changes...
I used it in tasks related to project planning in R.A.C.I also used it in the risk matrix, which reflected good results related to the project but needed more revision and reproduction to make the results more reliable according to the project. Saving Changes...
It provides more details (specifics) to the AI system which allows the system to generate more efficient and effective responses (responses that aligned with the desired outcomes. Saving Changes...
It provides the AI system with more constraints and instructions to allow the system to focus on responses that aligns with the desired outcome. Saving Changes...
PMI Team Member
