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?
I don't disagree with the answers above, but I keep it very simple. Make sure your data is clean, ask specific questions, and review the outcome. All of this will depend on the AI tools you are using and your needs for using them. Once you have this figured out, you will be good to go.
Continuing review and improvement are essential in this case.
I hope that helps.
Regards,
I agree with your point of view and I belive that it's important to test and verify the result that AI provide, anf then we improve it. 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.
In my experience, ensuring AI outputs are accurate and aligned starts with defining clear objectives and success criteria from the outset. I apply human-in-the-loop validation for critical outputs, use prompt engineering to guide relevance, and test across diverse scenarios to catch edge cases. Regularly reviewing outputs against benchmarks and incorporating feedback loops also help refine accuracy and maintain alignment with project goals. Saving Changes...
In my experience, ensuring AI outputs are accurate and aligned starts with defining clear objectives and success criteria from the outset. I apply human-in-the-loop validation for critical outputs, use prompt engineering to guide relevance, and test across diverse scenarios to catch edge cases. Regularly reviewing outputs against benchmarks and incorporating feedback loops also help refine accuracy and maintain alignment with project goals. Saving Changes...
Simmy Aneena JacobSr. Project Manager| PM SolutionsHuntingdon Valley, Pa, United States
Provide correct context
Provide your role
Provide examples and output format Saving Changes...
Alex ZelayandiaProject Manager| SSA Sistemas El Salvador, S.A. de C.v.Soyapango, San Salvador, El Salvador
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?
Being especific, organizing the information and using a structured format for requesting AI Saving Changes...
Very insightful discussion. The RTF and CREATE formula offers a great way of designing the prompts. Saving Changes...
Anonymous
sbe as concise as possible with the original prompt. Specificity helps. Refine the prompt, using examples and request responses in a specific format. Saving Changes...
Understand AI Capabilities: PMs should familiarize themselves with AI technologies and their potential applications in project management. This includes understanding data analysis, predictive analytics, and machine learning.
Align AI with Business Goals: Ensure that AI initiatives are aligned with the organization's strategic objectives.
Promote a Learning Culture: Encourage continuous learning and experimentation with AI tools. This involves training team members on AI applications and fostering an environment where innovation is welcomed.
Involve Leadership: Secure active involvement and support from leadership to drive AI initiatives. Leadership buy-in is crucial for resource allocation and overcoming resistance to change.
Incorporate Data Strategy: Develop a robust data strategy that includes data collection, management, and analysis. High-quality data is essential for AI systems to function effectively.
Cultivate New Skills: Invest in upskilling team members to handle AI tools and technologies. This includes training in data science, AI ethics, and project management with AI.
Evaluate and Adjust: Regularly evaluate AI performance and make necessary adjustments. This ensures that AI systems remain relevant and continue to meet project and organizational goals.
PMs should focus on understanding AI capabilities, aligning AI with business goals, promoting a learning culture, involving leadership, incorporating a data strategy, cultivating new skills, and continuously evaluating AI performance. Saving Changes...
Understand AI Capabilities: PMs should familiarize themselves with AI technologies and their potential applications in project management. This includes understanding data analysis, predictive analytics, and machine learning.
Align AI with Business Goals: Ensure that AI initiatives are aligned with the organization's strategic objectives.
Promote a Learning Culture: Encourage continuous learning and experimentation with AI tools. This involves training team members on AI applications and fostering an environment where innovation is welcomed.
Involve Leadership: Secure active involvement and support from leadership to drive AI initiatives. Leadership buy-in is crucial for resource allocation and overcoming resistance to change.
Incorporate Data Strategy: Develop a robust data strategy that includes data collection, management, and analysis. High-quality data is essential for AI systems to function effectively.
Cultivate New Skills: Invest in upskilling team members to handle AI tools and technologies. This includes training in data science, AI ethics, and project management with AI.
Evaluate and Adjust: Regularly evaluate AI performance and make necessary adjustments. This ensures that AI systems remain relevant and continue to meet project and organizational goals.
PMs should focus on understanding AI capabilities, aligning AI with business goals, promoting a learning culture, involving leadership, incorporating a data strategy, cultivating new skills, and continuously evaluating AI performance. Saving Changes...
Anurag Alan AzariahManager 1 (Projects), Technical Support| Dell International ServicesNew Delhi, India
Here are key strategies for getting better results from AI systems:
Be specific and clear in your requests Instead of "help me write something," try "write a 300-word professional email to a client explaining a project delay, maintaining a apologetic but confident tone." The more context and constraints you provide, the more targeted the response will be.
Use examples to illustrate what you want Show the AI what good looks like by providing examples of the style, format, or approach you prefer. You can also give examples of what you don't want to help the AI avoid common pitfalls.
Break complex tasks into steps Rather than asking for everything at once, work through multi-step processes incrementally. This lets you course-correct along the way and ensures each piece meets your standards before moving forward.
Ask for reasoning and alternatives Request that the AI explain its approach or provide multiple options. Phrases like "walk me through your reasoning" or "give me three different approaches" help you evaluate the quality of the response and choose the best path.
Verify important information independently AI systems can make factual errors or generate plausible-sounding but incorrect information. Cross-check key facts, especially for critical decisions or current events.
Iterate and refine Don't expect perfection on the first try. Use follow-up prompts to clarify, expand, or redirect based on what you receive. Think of it as a collaborative process rather than a one-shot request.
Specify your role and context Let the AI know if you're a beginner or expert in the subject matter, what industry you're in, or what constraints you're working within. This helps tailor the complexity and relevance of responses.
The goal is to create a clear feedback loop where you guide the AI toward increasingly useful outputs that match your specific needs and quality standards.
PMI Team Member
