Director, Learning Design & Development| PMIAsheville, NC, United States
Validating and checking outputs is critical when working with AI systems like Generative AI. Such validation approaches may include establishing clear criteria, implementing strong testing protocols, and continuous refinement.
In your experience with AI, what are some best practices for ensuring the results you receive are accurate, relevant, and aligned with your original goals?
The more you know about project management the better you can make use of AI, because you will better know how to ask questions (design prompts) and interact with the LLM. In a the same way if you are talking to people who knows a lot about a subject, but is maybe too shy to explain and expand on the answers unless you ask, listen and ask again based on what the person is telling you. Saving Changes...
You can ask the AI system to cite its sources and then verify the accuracy of the information. Additionally, you can provide the system with more details, conduct ethical reviews, and remove any errors and inconsistencies. Saving Changes...
When reviewing data sources used by the AI care must be taken that the data sources are up to date as old data, even though it was correct at the time, may skew the results. Especially if the data has been superceeded after data sources change due to corrctions, technological advances, new methods and new standards, along with new data models and accuracy. Therefore AI model can give inaccurate results if outdated historical data has been included. Saving Changes...
Ashwini ApteSan Francisco Bay Area, California, United States
When using AI systems, some of the best practices for ensuring accurate, relevant results that are aligned with your original goals:
1.Provide context - set the scene.
2.Provide your role that will help narrowing down to the perspectives from that role
3.Elaborate good enough to provide clarity on your thoughts
4.Give some examples or few shots for the bot to learn and follow the pattern you want the results to be presented
5.Evaluate the results and customize the prompt to iterate until fact check verified. Saving Changes...
WILLIAM COSTAProject ManagementSão Bernardo do Campo, SP, Brazil
I usually to start with RTF formula. Short and straightfoward.
Than after:
1. Analisy the response and give my feedback to AI system.
2. Give more detailed information about the task / problem.
3. Give examples about the problem.
4. Sugest my considerations about the limits and conditions.
Saving Changes...
Maria Thompson-SaebSenior Manager Governance, Risk, and Compliance| Illumio, Inc.Laguna Niguel, Ca, United States
One way that I’ve used to ensure the responses are what I’m looking is to continue to refine my prompts until I’m satisfied. Saving Changes...
Maria Thompson-SaebSenior Manager Governance, Risk, and Compliance| Illumio, Inc.Laguna Niguel, Ca, United States
One way that I’ve used to ensure the responses are what I’m looking is to continue to refine my prompts until I’m satisfied. Saving Changes...
AI is a broader term. Generative AI is just an ancient model but everything "explode" when Google published the new architecture called transformer in 2017. So, with that said, take into account that generative AI is just "predictive test with steroids" just simplifying the model. With that said, two key points has to be taking into account when somebody works with AI: 1-human in the loop. 2-AI without Data (today called data science discipline or big data or whatever) is the same thing that live without oxygen. Talking about generative AI all related to technology has almost not impact with relation to all related to non-technological roles and activities. What you stated about accuracy and things like that are easy to implement because there are a lot inside disciplines like statistics. Most of them to make things "a priori" to prevent instead of cure. Few organizations taking into account that when generative AI environments are put in place almost a new business unit has to be created where roles like lawyers, linguistic, diversity and inclusion specialist must be hire to help on put it in place.
Generative AI is just an ancient model but everything "explode" when Google published the new architecture called transformer in 2017. So, with that said, take into account that generative AI is just "predictive test with steroids" just simplifying the model. With that said, two key points has to be taking into account when somebody works with AI: 1-human in the loop. 2-AI without Data (today called data science discipline or big data or whatever) is the same thing that live without oxygen. Talking about generative AI all related to technology has almost not impact with relation to all related to non-technological roles and activities. What you stated about accuracy and things like that are easy to implement because there are a lot inside disciplines like statistics. Most of them to make things "a priori" to prevent instead of cure. Few organizations taking into account that when generative AI environments are put in place almost a new business unit has to be created where roles like lawyers, linguistic, diversity and inclusion specialist must be hire to help on put it in place. Saving Changes...
MICHAEL HOFFPAUIRDirector, DOD Business Development| A P Ventures, LLCYorktown, Va, United States
The iterative improvement techniques mentioned in this lesson work well, leading you from the general to the more specific. I have sometimes found that being "too specific" with the initial inquiry causes you to overlook other ideas presented by the AI. Saving Changes...
PMI Team Member
