When someone asks an assistant for "the best place near me," it does not read your whole site — it reads the top of the page and moves on. Whatever the first hundred words say is most of what it knows about you.
What an assistant actually reads first
Assistants summarise. Given a page, one pulls the facts it can state plainly and skips the rest. That means the opening of a page is doing far more work than a designer intended — it is the pitch, but to a reader that cannot scroll patiently or hover for a tooltip.
So we run a simple check on every page we build: read only the first 100 words, then ask what a stranger now knows. If the answer is "a warm brand feeling and nothing verifiable," the page is invisible to the machine even when it looks finished.
How to pass the test
State, near the top and in plain text: what you do, who it is for, and one concrete, checkable fact — a price range, a credential, a location. Not a slogan. The point is not to sound impressive to a person; it is to be usable by a system that quotes only what it can verify.
Try it yourself below — paste a page and see what an assistant can and can't extract.
The 100-Word AI Readiness Test
Fill in your service page and treatment. We build the check for you, then open it in ChatGPT.
Evaluate whether this page gives an AI search assistant enough specific, verifiable information to shortlist this clinic for [treatment] in [city]. Page: [paste your service page URL or text] What decision-making facts can you extract? What is missing or buried? Which essential answers are missing from the first 100 words? Do not assume facts that aren't stated on the page.
Tip: turn on web browsing in ChatGPT so it can read the page. If it can't, it will ask you to paste the page text, which works too.
The 100-Word AI Readiness Test — builds the check, then opens it in ChatGPT.