Research

Good writing alone is not enough. A page must pass each stage—access, discovery, retrieval, evidence selection, and answer use.

We compare a conventional product description with a question-and-exception format to see whether factual accuracy and omission of conditions change.

We test whether AI omits conditions more often when exceptions appear at the end of a document rather than beside the relevant claim.

We propose keeping the campaign intact, changing supporting explanations, and measuring human and AI responses separately.

Do not stop at whether the name appears. Read the reason for the recommendation.

AI recommendations and customer purchases must be measured separately.

We select one of the first two experiments using criteria fixed in advance and repeat the same procedure with five new products.

We review the results and counterexamples from weeks one to three alongside the status of earlier Lab experiments to define what the evidence supports.