How Perplexity, ChatGPT And Gemini Pick Their Sources

A false trade off gets invented early in most of these projects. Somebody proposes stripping the design, flattening the copy and restructuring everything around what a crawler finds convenient, and somebody else correctly points out that this would make the site worse for customers.

Ask how they will handle being wrong. Every engagement in this field produces at least one confident recommendation that does not work, because the systems change and the published research is thin. What matters is whether that gets reported or quietly dropped from the next deck, and asking the question directly at the outset makes it considerably more likely to be reported.

Observed behaviour leans toward breadth, pulling from a wider set of sources per answer than the others, and it cites forums, documentation and niche trade sources readily. It also appears comparatively responsive to freshness.

You will find your own category's pattern, which frequently contradicts the general one. Some industries are dominated by a single trade directory. Others are dominated by one forum. That specific finding is worth more than any general description of how these systems behave.

Absence is not disqualifying on its own, since their category is crowded and they may serve a niche. But they should have an interesting answer, and the answer should not be defensive. A practitioner who has run this test on themselves will have thought about it and will tell you what they found.

The second is freshness. Because retrieval is live, current figures beat stale ones, and a competitor can displace you by updating a page you have left alone for two years. Dating your content honestly and revising the numbers rather than the timestamp is a small habit with a large effect.

The skill is knowing to sort cited domains by frequency, recognise which of them can be influenced, and understand that a competitor appearing in an answer is usually a story about a third party page rather than about their website. That is a different analytical habit from the one search built.

It is also worth checking which assistant your customers actually use rather than assuming. The answer varies by profession, age and country far more than industry commentary suggests, and several businesses have built measurement programmes around a system their buyers never open. Adding one question to your enquiry form settles it in a fortnight and can redirect the whole effort.

Then add the structural markup, then check the whole thing with a reader in mind rather than a crawler. If a page has become harder for a person to use, something has gone wrong and the change should be reversed.

One practical consequence of the variation between systems is worth planning for. If your customers are split across two assistants that behave differently, resist building separate programmes for each. The shared requirements account for most of the achievable outcome, and the effort spent on system specific tactics is usually better spent widening the number of third party sources that describe you correctly.

The Shared Architecture All three now commonly retrieve live sources rather than answering purely from training. Your question becomes one or more searches, a set of pages is fetched and read, and the answer is composed from what was read.

One warning about testing. If you fix something and immediately re-run a prompt in the same session, the assistant may repeat its earlier answer from context rather than retrieving afresh. Start a new session, and run the prompt several times, before concluding that nothing changed. ai visibility agency

Writing Prompts That Sound Like Customers The foundational skill is deceptively mundane. Somebody has to write the questions your buyers actually ask, in their words, without the category vocabulary your team uses internally.

Expect the timeline to be uneven. Crawler access can change what an assistant sees within days, because retrieval happens at answer time. Identity consistency takes longer, since scattered mentions have to be re-crawled before they join up. Third party coverage is slowest of all and is the part you control least directly, which is exactly why it is worth starting on it before you need the result.

It is also worth checking whether you are being confused with somebody else rather than ignored. Short names, generic names and names that begin with a number collide with other organisations more often than distinctive ones. Where that is happening, the answer will contain facts that are true about a different company, which reads as a hallucination and is usually an identity collision with a specific fixable cause.

You asked it to recommend a supplier in your category. It named four companies, two of which you consider inferior to yours, and one you had never heard of. Your name did not come up, and it did not come up on the follow up question either.

The Rendering Question This is the one real technical constraint. Content that only exists after JavaScript executes may be invisible to a retrieval fetch, which is not a browsing session and does not always run scripts.