AI engines rewrite the buyer’s question instead of searching for it: often into English, and sometimes they don’t search at all. Those rewritten queries can be read in the engines’ API responses, with no guesswork. At Fast Growth Advisors, we logged them on a fixed panel of buyer questions rather than inferring them. Here is what they change for content work, and where the measurement still goes blind.
Most writing about GEO and AEO (generative engine optimisation and answer engine optimisation) is inference. Someone watches a chatbot answer, notices their brand missing, and reasons backwards to a cause. At Fast Growth Advisors, no finding about AI engines is produced that way, because inference and measurement are not the same claim.
We wanted to see rather than infer.
Our setup: a fixed panel of buyer questions, actual questions in natural language, sent on a schedule to the four engines that expose an API (application programming interface). For each response we log three things: whether the model searched at all, which queries it issued, and which sources it named. On the receiving end, server logs, not an analytics tag.
Two independent instruments, no circularity.
What follows is a field report. Citations come from the API side, traffic from the log side, and neither validates the other. That’s the point.
What happens when AI engines rewrite the buyer’s query?
Rewritten queries replace the buyer’s question, and that reorganises how you think about content.
The model doesn’t hand the user’s string to an index. It rewrites it into several queries of its own phrasing, then retrieves against those. Those queries come back from the APIs in a dedicated field: Fast Growth Advisors reads them instead of guessing them.
Which means keyword work aimed at the buyer’s phrasing targets a string that was never sent anywhere.
Ask about choosing a vendor, and the question can expand into queries about pricing, integration constraints, and alternatives. None of them contain the words the buyer typed.
And the language doesn’t always survive the rewrite.
A French prompt frequently produces English queries. Those English queries retrieve English pages, and the English page is what gets summarised and quoted back to a French-speaking buyer. For any company operating outside English, this reverses a common assumption: your local-language site does not automatically represent you locally.
A thin English version nobody maintains becomes your representative.
Caveat worth stating, because it matters: query language is inferred from the query text by heuristic, and a meaningful share stays undetermined. Its direction is clear. The precise ratio isn’t, on a sample of this size.
Why does an AI engine sometimes not search at all?
Because some answers are composed entirely from training data: no queries, no fetches, and nothing published this quarter can reach them.
Whether retrieval happens depends on the pairing of question and engine, not on the engine alone. One question can trigger a search on one engine and pure recall on another. Which is why “engine X never cites us” is usually a statement about a category of question rather than about the engine.
This distinction is operational.
If you don’t log the queries, you can’t tell “we weren’t retrieved” from “nothing was retrieved”. The first case is a content problem. In the second, your effort belongs elsewhere entirely, and telling the two apart is why Fast Growth Advisors logs every query issued. Publishing more this quarter cannot fix that second case.
Where does the instrumentation of AI engines go blind?
On the server side first, with bots claiming to be AI agents, then on the engine side, with Google AI Overviews and Copilot.
A hit claiming to be an AI user-agent proves nothing. User-agent strings are declarative and forged constantly; verification is a reverse DNS (Domain Name System) lookup against the address ranges the vendors publish themselves. What survives that check is far below what dashboards report. Fast Growth Advisors covered that work in full, with the numbers: 876 impostors over thirteen days.
One operational thing to take from it here: bots don’t execute JavaScript, so your analytics tag sees none of this. It’s in the server logs or it’s nowhere.
On the engine side, Google AI Overviews and Copilot expose no official API.
Nobody measuring this way is measuring those two, and a tool reporting a unified score across all engines is filling that gap with something other than measurement. Generative output is non-deterministic, so a single reading is noise.
What makes it data is repetition on a fixed protocol, plus control pages that receive no optimisation. Without them, nothing observed can be attributed to your work rather than model drift.
Then there is sample size. A panel of a few dozen prompts over one pass supports no statistical inference: large gaps are readable, a five-point difference would mean nothing.
Where should you start with rewritten queries?
Read the queries before optimising anything.
Get the actual expansions for the questions that matter in your category, in whatever language they came back in, and compare them with what your pages answer. Most teams find content answering questions no engine ever asked, and queries landing on pages they never wrote.
Then fix the extractable layer. An engine restitutes what a page states plainly: it won’t infer positioning from a layout, open a PDF, or read logos rendered as images. Fast Growth Advisors took that layer apart in your site isn’t invisible, it’s unreadable.
Whatever isn’t written explicitly doesn’t exist to retrieval.
The narrow, checkable version is the only version worth having. Less impressive than a dashboard, it survives being asked how it was produced.
I’d rather be corrected on the method than right by assertion. If you’re measuring this differently, or if something above contradicts what your own logs show, I want to know.
FAQ
Why does an AI engine rewrite the user’s query?
Because it doesn’t hand the string it received to an index.
An AI engine derives several phrasings of its own, then retrieves sources against those. The engines’ APIs return those rewritten queries in a dedicated field, which lets Fast Growth Advisors read them rather than guess at them.
Does a French prompt produce French queries?
Not reliably: a share comes back in English.
Those English queries retrieve English pages, so the page summarised for a French-speaking reader is not always yours. Query language is inferred from the query text by heuristic, so the direction is clear while the precise ratio is not, and a meaningful share of queries stays undetermined.
How do you know whether an engine searched at all?
By logging the queries issued for every answer.
Without that log, nothing separates a page that was not retrieved from an answer composed with no retrieval at all. The two call for opposite decisions: the first is a content problem, and the second moves the effort elsewhere.
Can Google AI Overviews be measured this way?
No, since neither Google AI Overviews nor Copilot exposes an official API.
Nobody measuring through API queries is measuring those two engines. A tool that still reports one unified score across every engine is filling that gap with something other than measurement, and its figures for those two rest on no observed answer.