Where AI Platform Checks begin
At SaidTrue we describe AI Platform Checks as artificial intelligence. That is the description we work from, and we keep to it. The work itself is specific: we give visibility reports for a website's presence in AI search, worldwide, and we build those reports out of what the AI systems actually say.
What we look at first
We start with the questions customers already ask, rather than with anything a business would like to be asked. We put those questions to ChatGPT, Gemini, Perplexity and Claude, and then we show what was said, what was sourced, and where the truth diverges. That order matters. What AI tells your customers about you is now formed in conversation, and a person who asks an AI who to use, or whether a business is reputable, receives an answer whether or not anyone has looked at it. Google is no longer the only front door, which is why we begin with the answer rather than with the ranking.
How we work through it, step by step
A scan produces a public scorecard for the business. Behind that scorecard sits the material it came from: the questions asked, the answers given, and the sources those answers leaned on. Our scoring is set out in How SaidTrue Scores AI Answers, so a score can be read alongside the reasoning that produced it. Because AI answers move, a single scan is a snapshot, and that is why we run monthly AI monitoring together with a verified AI profile. Looking again at a later point shows what has shifted in how a business is described, recommended or misread.
Why we do it this way
We keep the answers visible because the useful question is not only what a business is scored, but what was actually said about it and where that departed from the truth. AI systems describe, recommend and sometimes misread businesses. A report that hides the wording, and the sourcing behind it, hands the reader a number with nothing to act on. Showing the answers, the sources and the divergence is what makes a SaidTrue visibility report worth reading, and it is the reason we work from the raw answers first and the score second.