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?
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
Sounds like your colleague might benefit from 'chaining' his prompt(s) using the C[R]EATE formula described in the PMI "Talking to AI: Prompt..." online course. 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).
Thanks so much for these additional AI Prompt formulas.
I have RTF [role task format] and CREATE [character request examples adjust types of output evaluate] from the PMI online course. Your formulas are new to me:
_ BAB: Before After Bridge
_ CARE: Context Action Result Example
_ RISE: Role Input Steps Expectations
_ TAG: Task Action Goal
Except for BAB, yours seem to be pretty intuitive. Yet I think the RTF and CREATE forms encapsulate all the above. Thanks again!
...
2 replies by Sergio Luis Conte and Shauna VanderHoek
Jul 14, 2024 7:10 AM
Sergio Luis Conte
...
You are welcome. I made the post before the course of the PMI was delivered. This formulas were created time ago when the first version of ChatGPT was published. But they work for me. In my personal opinion and experience, the use of CREATE made too large propmpts and I prefer to use the others depending of the results I need to obtain and the information I have to create the propmpt. For example, to use CARE, I have to provide and example in the prompt and sometimes I do not have it.
Dec 08, 2024 4:19 PM
Shauna VanderHoek
...
Vanessa, I appreciate your succinct recap of the formulas. There is a lot of great info in PMI's AI-prompt Engineering course!
Saving Changes...
Sergio Luis ConteHelping to create solutions for everyone| Worldwide based OrganizationsBuenos Aires, Argentina
Jul 13, 2024 6:31 PM
Replying to Vanessa Wright
...
Thanks so much for these additional AI Prompt formulas.
I have RTF [role task format] and CREATE [character request examples adjust types of output evaluate] from the PMI online course. Your formulas are new to me:
_ BAB: Before After Bridge
_ CARE: Context Action Result Example
_ RISE: Role Input Steps Expectations
_ TAG: Task Action Goal
Except for BAB, yours seem to be pretty intuitive. Yet I think the RTF and CREATE forms encapsulate all the above. Thanks again!
You are welcome. I made the post before the course of the PMI was delivered. This formulas were created time ago when the first version of ChatGPT was published. But they work for me. In my personal opinion and experience, the use of CREATE made too large propmpts and I prefer to use the others depending of the results I need to obtain and the information I have to create the propmpt. For example, to use CARE, I have to provide and example in the prompt and sometimes I do not have it. Saving Changes...
Hari Krishna ThadepalliProject Manager| Hexaware Technologies IncChittoor, Andhra Pradesh, India
I used Gen AI so far for personal takas and more or less I did receive effective outcome. I am working towards identifying the best use cases from my project routines to leverage Gen AI for optimizing productivity & reduce data issues, within the agreed regulatory compliance limits Saving Changes...
The prompt structure is key for outcomes, the iteration is a constant in my experience. The complex the task the number of iteration increase. Saving Changes...
Aaron PorterIT Project Manager| Sunland Asphalt & Construction, LLCMoore, OK, United States
Example 1: Generating Detailed Project Plans
Initial Prompt: "Create a project plan for a new software development project."
Improved Prompt: "Create a detailed project plan for a new software development project, including phases for requirements gathering, design, development, testing, and deployment, with estimated timelines and key milestones."
Changes Made: Added specificity by outlining the phases and requesting estimated timelines and key milestones.
Result: The improved prompt generated a comprehensive project plan with clear phases, timelines, and milestones, making it more actionable and relevant.
Example 2: Writing a Marketing Strategy
Initial Prompt: "Write a marketing strategy for a new product launch."
Improved Prompt: "Write a marketing strategy for the launch of a new eco-friendly water bottle, targeting environmentally conscious consumers, including social media campaigns, influencer partnerships, and sustainability messaging."
Changes Made: Specified the product type, target audience, and key components of the strategy.
Result: The improved prompt produced a more tailored and effective marketing strategy, with specific tactics aligned with the target audience and product features. Saving Changes...
We are transferring our Intelligence to GenAI. Saving Changes...
Paul JacksonPresident/CEO| PAP Consulting ServicesFarmington Hills, Mi, United States
By carefully crafting a clear and specific prompt, you can guide the AI model to focus on relevant information and deliver more accurate and coherent outputs. Adjusting the language, tone, and structure of the prompt can help steer the AI towards producing content that better aligns with your experience and requirements.Refining the prompt based on iterative feedback and optimizing it for the desired output can lead to substantial improvements in the quality, relevance, and coherence of the generated content. Saving Changes...
Visukumar GopalCEO - Chief Enabling Officer| SuVi Veratile ServicesChennai, Tamilnadu, India
Refinement is very important to extract the close to accurate details. When I used for charter preparation with KPIs, it elaborated the roles and responsibilities of each member very clearly. Saving Changes...
Just like all life skills that are perfected over time by trial and error,refining prompts will improve the results from AI and the person writing the prompts. Saving Changes...
PMI Team Member
