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?
When using AI systems is very hard to set the precision or accuracy of the responses. I love bringing in the Agile mindset here pretty much imagine if you are mentoring someone you do a Q&A and based on the reponses of your Mentee you give the feedback so that Mentee can align his/her thoughts in the direction that we hint similarly review the AI responses and using our rationale judgement
1- Give Feedback to the AI system
2- Rework on your promp and be specific on what is expected
3- Keep it short and conscise, guage the responses and slowly we can tune the AI system in a way to get the best output
4- Now the Tech. Solution that comes in for accuracy is havig specific set of APIs that talk to real and accurate data sources or use 2-3 outputs of LLMs and then analyze and bring the best in output.
I have definitely done this before... giving feedback to the AI system because inherently it will get smarter and helps the next individual that interacts with it for a similar prompt.
It is important that all your local sources of information are organized and classified allowing the IA system recognize its elements and process them to combined with other sources to produce a good response. When prompting, it will be necessary to include a command that request the system take all these local sources into account.
I think after this course - some of my alignment issues will be fixed with better prompting. I have gotten into the habit if asking for sources. I will then go directly to the source and attempt to locate the primary data. There have been a few times where the source is not something that I am comfortable using.
I also rarely give feedback to the LLM - something that I will do more of in the future! Saving Changes...
Tanmay VoraProject Manager| Majesco Ltd.Mumbai, Maharashtra, India
I agree with some of the comments posted. Articulating what we want clearly is the first step in getting right response and may avoid going to multiple iterations or using different techniques. More precise we are in asking the right questions, we are more likely to get a better response we expect to resolve the situation.
Saving Changes...
Richa SharmaQuality Engineering Manager| Optum Technologies, IndiaNoida, India
For AI system, best practices should be
1. Be Clear About Your Goal Upfront - Clearly state your objectives ; if possible specify the intended audience for level of details etc.
2. Provide Complete and Precise Context - Assumptions, exclusions or constraints if any
3. Ask for Focused & Well-Structured Prompts
4. Request Reasoning, Not Just Answers
5. Verify Critical Information using facts and details available
6. Iterate and Refine the Output
7. Watch for biasedness and hallucination
8. Use AI as Decision Support, Not Final Authority
Use a clear, specific prompt that defines your goal, the context, and the format you want the answer in. Ask the AI to state its assumptions or reasoning so you can spot gaps or inaccuracies before relying on the output. Validate the result by cross‑checking key points, refining the prompt, or requesting an alternative version to ensure alignment with your original intent.
When working with AI systems, particularly Generative AI, ensuring that outputs are accurate, relevant, and aligned with original goals requires a structured and disciplined approach. First, I define clear evaluation criteria based on the intended use case, such as accuracy, completeness, tone, and format. This helps establish a consistent standard for assessing outputs. Second, I use iterative prompt refinement and prompt chaining techniques to continuously improve results. By testing and adjusting prompts, I can reduce ambiguity and guide the AI toward more reliable and context-aware responses. Third, I ensure human-in-the-loop validation, where subject matter experts review outputs to identify hallucinations, bias, or gaps, especially in critical business scenarios. Fourth, I apply strong validation practices by comparing AI outputs against trusted sources, benchmarks, or expert judgment to ensure correctness and consistency. Fifth, I follow data governance best practices by avoiding the use of sensitive or proprietary data and leveraging anonymized or synthetic data when necessary. Finally, I document prompts, outputs, and observed patterns to enable continuous improvement and build organizational knowledge over time. Overall, combining structured prompting techniques, human oversight, and continuous validation ensures that AI outputs remain reliable and aligned with business objectives. Saving Changes...
PMI Team Member
