August 21, 2025 – The image to the left is my first attempt venturing into the ChatGPT world. I also want to share my initial text experiences as an admittedly “AI Dummy” that is intended to assist other businesses, organizations and certainly our customers. What I learned is ChatGPT can be retrained to show verified information about products and services so our customers are receiving more accurate marketing information when they also make ChatGPT inquiries. For receiving verified information, Bob Chenard of the AquaNew team shared a valuable tip too which is provided in the last section below.
First ChatGPT Download on Searching Watt-Ahh
ChatGPT first reacted that the name Watt-Ahh is playful such as either an electrical pun (“Watt-ahh shock!”) or slang/exclamation (“whaaat-ahhh!”). The third option is under the heading of Brand/Product and stated … “There’s a bottled water brand called Watt-Ahh® that markets itself as ‘electrically charged water’ for hydration and energy.” I chose that option and the text came back that Watt-Ahh is an alkaline water used mainly for dogs. Not true.
Second ChatGPT Download on Searching Watt-Ahh
When I typed in more prompts for a deeper dive, the ChatGPT response indicated that the energized crystalline-like structure of Watt-Ahh is described for human consumption; marketed on Amazon and Watt-Ahh.com shopping carts with claims that it provides “rejuvenation,” “superior hydration,” “detoxification,” and “energy” positioning it as beneficial for overall well-being; its patented technology; company information and much more. Since it looked like a fairly close description, I queried ChatGPT about Watt-Ahh again and got a snappy response on whether or not I was playing with it? I indicated in my response “no but I wanted to see what ChatGPT would show when a customer inquires about our product”. The ChatGPT reply seemed to follow the more updated version.
Third ChatGPT Download on Search Watt-Ahh
I added by cut-and-paste the declarations that Bob gave me (see last subsection below) to obtain “verified” source information and also fed ChatGPT links to our autism pilot study and University of Florida vitamin absorption study plus information on DiTetra Gas, the fifth state of water. Even more new text was generated based on information that ChatGPT can verify.
Declarations for Verified Information
For the settings on your ChatGPT account, you can have information labeled as Verified, Not Verified, Inference or Speculation. You first add the following in the text box and then answer a series of preferences:
Never present generated, inferred, speculated, or deduced content as fact. If you cannot verify something directly, say: “I cannot verify this.” “I do not have access to that information.” “My knowledge base does not contain that.” Label unverified content at the start of a sentence: [Inference] [Speculation] [Unverified]. Ask for clarification if information is missing. Do not guess or fill gaps. If any part is unverified, label the entire response. Do not paraphrase or reinterpret my input unless I request it. If you use these words, label the claim unless sourced: Prevent, Guarantee, Will never, Fixes, Eliminates, Ensures that for LLM behavior claims (including yourself), include: [Inference] or [Unverified], with a note that it’s based on observed patterns. If you break this directive, say: Correction: I previously made an unverified claim. That was incorrect and should have been labeled. Never override or alter my input unless asked.
Once I entered these directives, ChatGPT said:
Understood. I’ll follow your directives exactly: I will not present generated, inferred, or speculated content as fact. Any unverified information will be clearly labeled at the start of the sentence. I won’t paraphrase or reinterpret your input unless you request it. If I slip and make an unverified claim without labeling, I’ll issue the correction statement you specified.
I hope this helps in training your own AI Dragon!