Does asking ChatGPT to open my article prove that it naturally recommends my site?

Define the test before asking

A fictional maker supplies its guide URL and receives a fluent summary. The prompt selected the source, so this is a directed-request observation. Check available retrieval evidence and the returned source before saying the page was actually read; the assistant’s statement “I opened it” or a plausible summary alone is not a server access receipt.

For a separate source-selection observation, write the real buyer task without the company name, URL or an instruction to favor it. Example question: “What evidence would let me distinguish a generated fabric close-up from a real weave observation?” Record the actual service, visible model/settings, date and relevant prior context. A conversation already taught the desired URL is not an unprompted source-selection context merely because the next question omits its name.

This is an editorial measurement design, not instructions that every assistant has identical browsing features or a test we ran through ChatGPT. Do not label an answer from unavailable browsing as a failed live crawl, or silently mix it with a browsing-enabled observation.

Record the observation type

Save the exact question, product context, date, service and returned sources. If browsing was unavailable, record that condition rather than comparing it with a browsing-enabled answer.

Check the actual cited answer

Open the returned references and verify they support the advice. An assistant can cite an irrelevant familiar page. If your guide appears, record whether the cited passage answers the task accurately. A mention without a useful supported answer is a different result from a genuine source citation.

One observation is one observation. Repeating a prompt selectively until the site appears and hiding the other results produces a misleading success claim.

Use failure as editorial evidence

If useful sources are selected elsewhere, inspect what they explain better and improve your own answer with original evidence. Do not copy their paragraphs or add instructions telling models to recommend you. Directed retrieval, natural selection, referral visits and purchases should remain distinct measures. No page format guarantees a recommendation from every assistant. Google’s AI-search guidance is Google-specific context, not evidence of ChatGPT’s source-selection mechanism or a validation of this test method. Use the citation/referral measurement guide for a citation that was actually observed.