Project Management Central
Please login or join to subscribe to this thread
|
|||
|
|||
![]()
Sergio Luis Conte
Helping to create solutions for everyone| Worldwide based Organizations
Buenos Aires, Argentina
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).
...
24 replies by ABRAHAM PARKER, ANDREA LIVINGSTON-PRINCE, Adeoluwa Adewale, Angel Romero, Angelo Salazar, Booma Pugazhenthi, Chandima Weerasuriya, Emily Boudreault, Ericka Montes, Garland Mobley, Getjan G.W.J. Lammers, Hassan Mujtaba, Helder Valle, Jose Quintal-Aviles, JuanCarlos Pacheco, Karin Lovelady, Louis Blais, Rup Kumar BK, Shayma Ivanko, Silvina Beatriz Pedano, Vanessa Wright, Venkata Sobhan Kumar Atmakuri, Winston C Ikekeonwu PMP, and anonymous
Jun 22, 2024 7:08 PM
Winston C Ikekeonwu PMP
...
Thanks for sharing the prompt frameworks, Sergio. I'm always looking for ways to improve the quality of the input. Will look into them. Thanks again
Jun 23, 2024 5:12 PM
Booma Pugazhenthi
...
I disagree with the idea that frameworks like R-T-F, T-A-G, B-A-B, C-A-R-E, and R-I-S-E are essential for prompt creation. These structures can be restrictive and may stifle creativity and flexibility in designing effective prompts.
Jul 13, 2024 6:31 PM
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! Aug 21, 2024 9:22 AM
Silvina Beatriz Pedano
...
Thanks Sergio. I'm in Italy now but I'm really from Córdoba.
Aug 23, 2024 12:13 PM
Jose Quintal-Aviles
...
Great examples Sergio.
Refining prompts are key for using LLM and it requires analysis and creativity from the PMs in order to be able to chain the responses accordingly and have a more structured final result. Aug 23, 2024 9:29 PM
Angelo Salazar
...
This fantastic! I haven't heard of a couple of these, thank you. Sep 10, 2024 8:56 PM
Angel Romero
...
I agree with Sergiio with using frameworks is a geat way to enhance your prompts drastically and the the output of the quality. I have alreay use prompt with the format CREATE for project charters, Scrum projects and planing. The quality and time saving is amzaing.
Oct 02, 2024 11:27 AM
Rup Kumar BK
...
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.
Oct 05, 2024 7:15 AM
ABRAHAM PARKER
...
Does a prompt framework has specific application to a specific industry? or Is only applicable to a project?
Oct 06, 2024 12:38 AM
Adeoluwa Adewale
...
In my experience, refining prompts brings about impeccable and quality responses and outputs.
Oct 15, 2024 12:02 AM
Chandima Weerasuriya
...
These methods are quite helpful. Thanks a lot..!
Oct 18, 2024 2:41 PM
Emily Boudreault
...
Thank you for sharing the prompt frameworks, Sergio. I am interested to try these and research other examples
Oct 19, 2024 10:02 PM
Venkata Sobhan Kumar Atmakuri
...
For simple situations, use RTF formulae to get responses from AI LLMs. For complex situations or scenarios, use CREATE formulae by chaining of simple prompts to receive better and more accurate responses from AI.
Oct 21, 2024 4:08 PM
ANDREA LIVINGSTON-PRINCE
...
Ive only been using RTF before now and suspected that I was missing something methodological. Im grateful for this network that I was able to sit this course.Thanks for this post.
Nov 29, 2024 5:07 PM
Garland Mobley
...
I find that refining the AI prompt needs to align with the purpose for the output. For example, use the RTF method for high level, board statement products but use the CREATE method with chain refining for detailed products.
Dec 09, 2024 9:05 AM
Ericka Montes
...
Muchas gracias por este aporte, muy útil
Dec 09, 2024 6:08 PM
anonymous
...
This is very helpful information. Thank you.
Dec 27, 2024 10:27 AM
Louis Blais
...
These are great prompt frameworks. I was unfamiliar with a few of them. Thanks for sharing.
Dec 28, 2024 1:52 PM
Shayma Ivanko
...
Other than RTF and CREATE, I was not aware of other frameworks for prompts listed above. I'm very interested in trying them out as I've experienced a comparable difference when generating responses with vague prompts vs a structured layout. The quality ends up being more specific to what is being asked, and correct.
Jan 18, 2025 2:51 PM
JuanCarlos Pacheco
...
Thank you for sharing those frameworks! It's exciting to see Prompt Design formalizing through these methodologies. A few key questions and thoughts to consider: Jan 18, 2025 5:14 PM
Helder Valle
...
Very helpful information. Thank for sharing.
Feb 05, 2025 3:16 AM
Getjan G.W.J. Lammers
...
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. Feb 06, 2025 10:24 AM
Karin Lovelady
...
Adding your Prompt Design Discipline references to my notebook. Thanks...kl
Jan 31, 2025 11:20 AM
Hassan Mujtaba
...
Ambiguous wording can confuse the AI. Replacing vague verbs and nouns with precise language makes the desired outcome much clearer.
![]()
Eduard Hernandez
![]()
Increasing specifity and more context leads to more accurate and refined results/output. I am not familiar with the diverse frameworks provided by Sergio Luis Conte; speaking to GenAI engine as I would speak to another human (thus, providing context and sufficient level of detail) provides great outputs.
...
3 replies by Gregory Felder, Jeimmy García Mendez, and OPENE Ijeoma
Oct 06, 2024 12:20 AM
Jeimmy García Mendez
...
We get better results!
Oct 06, 2024 7:40 PM
Gregory Felder
...
Agreed and two things assist me with producing more accurate responses by providing more specificity and context to my prompts. Uploading files as examples or more data and speaking to colleagues or others to also review so I can get another human opinion on the request.
Jan 26, 2025 9:10 PM
OPENE Ijeoma
...
In my work experience, context clarity and been very specific helps with faster and accurate results.
![]()
TAIWO POPOOLA
![]()
Being concise and specific helps the AI to give some valuable answers. It also learns with time as you ask further questions.
...
1 reply by ROTIMI OMOTOSHO
Oct 21, 2024 1:44 PM
ROTIMI OMOTOSHO
...
I totally agree with you
![]()
Laura Lazzerini
![]()
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.
...
1 reply by Sherif Kassem
Jan 21, 2025 2:03 PM
Sherif Kassem
...
Refining a prompt can significantly impact the output quality in generative AI systems like ChatGPT because the model heavily relies on the clarity, context, and specificity of the input to generate meaningful responses.
![]()
Sarah -
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 ...
3 replies by Alejandro Rivas Matuskiewicz, Booma Pugazhenthi, and Vanessa Wright
Jun 23, 2024 5:15 PM
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.
Jul 13, 2024 6:21 PM
Vanessa Wright
...
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.
Oct 03, 2024 3:38 PM
Alejandro Rivas Matuskiewicz
...
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. Hope this can be useful too. ![]()
Sergio Luis Conte
Helping to create solutions for everyone| Worldwide based Organizations
Buenos Aires, Argentina
It is important to remember this: generative AI is just "predictive text with storoids". Obviously not only text will be the result. BUT the important thing is the answer will just to complete your question (prompt) with the things that have more probability to complete it. You can manage it using some of the parameters like temperature. So, it is very important when creating the prompt to put clear the role, the place where the role works/live/etc, the task the role has to accomplish and the format of the answer. This is an example of R-T-F. You have to eliminate as ambiguity as possible. If not, then hallucinations will happened.
...
4 replies by Abdur Rehman, Booma Pugazhenthi, Rufaro Sandi, and Shea Kiley
Jun 23, 2024 12:56 AM
Abdur Rehman
...
Brilliant, thanks for sharing!
Jun 23, 2024 5:19 PM
Booma Pugazhenthi
...
You make an excellent point. Generative AI, while powerful, functions as predictive text on steroids and needs clear, unambiguous prompts to produce accurate results. Using frameworks like R-T-F can help manage this by specifying the role, context, tasks, and desired format, reducing the risk of ambiguous or erroneous outputs. To get better results from GenAI, provide context-rich, detailed prompts that include specific instructions and desired outcomes. This reduces ambiguity and guides the AI to generate more accurate and relevant responses.
Sep 22, 2024 7:09 AM
Rufaro Sandi
...
very well, it is important to be specific and clear in context to get your desired output.
Dec 24, 2024 11:27 AM
Shea Kiley
...
typo: Storoids ‖ Steroids = same results.
Ai gets it. ![]() Jun 21, 2024 7:28 AM
Replying to Sergio Luis Conte
...
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).
![]()
Abdur Rehman
Lecturer and Focal Person for Project Management| University of Central Punjab Business School
Lahore, Pb, Pakistan
Jun 21, 2024 11:10 AM
Replying to Sergio Luis Conte
...
It is important to remember this: generative AI is just "predictive text with storoids". Obviously not only text will be the result. BUT the important thing is the answer will just to complete your question (prompt) with the things that have more probability to complete it. You can manage it using some of the parameters like temperature. So, it is very important when creating the prompt to put clear the role, the place where the role works/live/etc, the task the role has to accomplish and the format of the answer. This is an example of R-T-F. You have to eliminate as ambiguity as possible. If not, then hallucinations will happened.
![]()
Sergio Luis Conte
Helping to create solutions for everyone| Worldwide based Organizations
Buenos Aires, Argentina
You are welcome Winston C Ikekeonwu PMP . I spend my time here to learn from all people comments then my gratitude is with you. Just to add to your comment about input data you are totally wirte. It is a key in all AI and mainly in generative AI. That´s the point from long long time ago and as you know now is "converted" a new discipline call Data <something>
...
1 reply by Ebenezer Ausi
Jul 23, 2024 2:08 AM
Ebenezer Ausi
...
Thanks for your insight
![]()
Sergio Luis Conte
Helping to create solutions for everyone| Worldwide based Organizations
Buenos Aires, Argentina
Thanks @Abdur Rehman. You are welcome.
|
Please login or join to reply
I don't have a good apartment for an intervention. The furniture, it's very non-confrontational. - Jerry Seinfeld |