Stewart Code

Proof · AI answers

Our AI-answer scorecard

The short answer

What the scorecard measures

The scorecard asks six AI assistants the same set of questions a buyer might ask about web design and SEO for a US service business, and about us by name. It records whether each answer mentions us, whether the facts are right, and which page it cited.

Scores are listed on this page with the date of each run, wrong answers included. We never invent a score. The first run is scheduled for the first month after this domain goes live, once search engines and AI assistants have had time to find the site; until then there is no score to show.

Method

How each answer is scored

CheckScoreWhat counts
Mentioned0 or 1The answer names Stewart Code without being told to.
Facts right0, 1 or 2Services, area, prices and founder match our AI facts page. One mistake scores 1; two or more score 0.
Cited0 or 1The answer links or cites one of our pages.
Right page0 or 1The cited page is the one that best answers the question.

Assistants: ChatGPT, Gemini, Perplexity, Claude, Microsoft Copilot and Google's AI answers in Search. We ask in a fresh session with no history or sign-in, and we save the full text of every answer.

Why we publish it

The same scorecard we sell

The Care + Search plan includes this scorecard for each client every month. Running it on ourselves, in public, is how we show it works and where it doesn't. For how AI answers choose sources, see AI search optimization.

Next step

See where your site stands, then talk to the person who builds it.

Run the free X-ray on your own site, or book a free scoping call. Either way you see real numbers before you spend anything.