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?
1. The AI can only work with the information it is given. By providing concise prompts with relevant details and desired output will better enable AI to provide results.
2. Develop a strategy relevant to your organisation´s approach to Project Management in order to help the AI suggest more relevant reponses.
1. To ensure that results from AI systems are accurate, relevant, and aligned with your goals, start by clearly defining your needs.
2. Craft precise instructions, and don’t hesitate to refine and adjust prompts based on initial outputs.
3. Validate the results by comparing them to reliable sources or internal expertise ; for example, if you’re working on a predictive model, check the AI’s results against historical data to ensure consistency. Incorporate feedback loops to continuously improve accuracy.
4. Finally, be vigilant about potential biases by regularly reviewing the AI’s responses to make sure they stay aligned with your expectations. Saving Changes...
- Provide context and background information where necessary.
- Formulate your questions and prompts clearly and specifically.
- Provide feedback on the AI's responses.
- If the initial output isn’t quite what you expected, refine your query and try again
- Use the right AI tools for the job.
- Ensure the AI system adheres to ethical guidelines. Saving Changes...
Draft a strong CREATE question as suggested in these lessons, run and review the AI response. Then try to modify one aspect of the CREATE question, run review. I think the challenge will be which component of CREATE generates the best response for you. But only by testing those componets will we see improvements in the AI deliverable. Saving Changes...
Anonymous
Review the output and tweak your prompt and start over. You're learning along. Saving Changes...
Hi,
Simply appropriate formula and refinement iteration. Saving Changes...
Joe Lagana-JacksonDirector, Agile Practice & ProgramsOakland, Ca, United States
This might've already been said that there are many replies, but I ask the AI what it source of information is. For example, I've noticed that it tends to hallucinate performance data if a report would be enhanced by adding such data. So I just ask it, "Where did you get the data from? I didn't provide it," and the AI usually replies that they've just added it in there, and will then revise the output to eliminate that data. Saving Changes...
Valentine MrozekSenior IT Project Manager| Self Employed - Semi retiredMillersville, Md, United States
Jun 07, 2024 9:24 AM
Replying to Sergio Luis Conte
...
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.
Sergio, I believe you are spot on both in your history and simplification of defining AI. Same is true regarding (At least for the short term 2-5 years) there will be people representing the existing business units (Legal, H/R, sales), etc....
Long term, once AI matures, I expect an oversight group consisting of directors or VP Businesspeople, will exist on an "as needed bases".
I strongly believe in AI and the potential productivity gains when the technology matures. Saving Changes...
The precision and detail of the information and what we want from AI is key. We have to put ourselves in the situation of what happens to us as professionals: We have a background, an experience, we live in a context and receive multiple sources of information every day. The same thing happens with a project, the amount of information received gives a lot of context and clarity of what should be done. These sources of information must be shared with the AI so that it has something to rely on to provide its outputs. Clearly the RTF and CREATE methods are the ones that help the most to have that information as clear, complete and organized as possible. However, once an answer is obtained, it is best to have an iterative refinement conversation with the AI to determine if there is vague information, different from what was expected, incoherent, incomplete; Given this, more information must be provided, the context improved, the prompts reread and refined. Saving Changes...
PMI Team Member
