ChatGPT Already Knows Who It'll Recommend Before It Searches — Suganthan inline style so that every rule<br>using var(--color-*) resolves correctly before the external stylesheet<br>loads. This fixes Safari dark-mode where links were invisible because<br>the CSS variables still held their light-mode :root defaults during<br>first paint. --><br>~/about ~/projects ~/research ~/tools ~/blog ~/notes ~/work ~/newsletter

ChatGPT Already Knows Who It'll Recommend Before It Searches<br>ChatGPT writes brand names into its own search query before it fetches a single page. I read the traffic across 60 conversations to work out when it happens, what being named is worth, and what actually gets you onto that list.

By Suganthan Mohanadasan<br>10 Aug 2026 17 min read

Tags:<br>#geo<br>#ai-seo<br>#chatgpt<br>#content-strategy

I asked ChatGPT for the best AI note taking app. Seven words, no brand names.

Before it fetched anything, it wrote itself this search.

best AI note taking apps 2026 official pricing features Granola Notion AI Otter Fireflies Fathom Mem Limitless<br>Read the tail of that string. Granola. Notion AI. Otter. Fireflies. Fathom. Mem. Limitless. Seven products in one search. I’d named none of them , and nothing had come back from the web search yet, so no result put them there. Those names came out of the model.

Then it ran nine more searches.

site:granola.ai pricing features AI meeting notes 2026<br>site:otter.ai pricing AI meeting notes 2026<br>site:fathom.video pricing AI meeting assistant 2026<br>site:notion.com product AI Meeting Notes official 2026 pricing<br>site:fireflies.ai pricing official AI meeting notes 2026<br>site:mem.ai pricing AI notes official 2026<br>site:notebooklm.google official features pricing 2026<br>That’s the fan-out I wrote about in the first two parts, and now you can see what it’s made of. One search to name the shortlist, then one search per name on that shortlist, each pointed straight at that company’s own website.

So the fan-out was never a search for candidates, it was ChatGPT going down a list it already had, one name at a time.

In the first two parts I wrote that you need to survive a site:yourdomain.com probe, because ChatGPT runs them. It only runs one on you if you were named in that first search. Miss the shortlist and your website never gets looked at, however well built it is. The decision happens before anything touches your server.

I’ve spent two months reading this traffic for part 1 and part 2. This is the first thing I’ve found that changes what I’d tell a client to do.

Before you read any further, all of this comes off one account, so every percentage below is a direction rather than a measurement. The mechanism is a different matter. You can reproduce that on your own account in two minutes and I’ll show you how at the end.

The four ideas behind this

Each one sets up the next.

ChatGPT writes its own search queries, and you can read them.

Those queries already contain brands nobody mentioned.

Being in that query is worth about 33 times more than being findable.

Once you’re in, a second and much harsher filter decides who gets cited.

Idea 1. It writes its own searches, and they’re readable

When you ask a question, ChatGPT rewrites it into search queries of its own, runs them, reads what comes back, then writes an answer.

Those queries sit in the response your browser downloads, under a key currently called search_queries. OpenAI renamed it from search_model_queries in early August 2026. Nothing about this is a leak. Your own browser needs that JSON to draw the page, and you can read it in DevTools on your own account in about two minutes. Recipe’s at the end.

Here’s one from a question about live chat software.

best AI live chat customer support software 2026<br>Intercom Fin Zendesk AI pricing official<br>I asked for “best ai based live chat support software”. It added the year, “official”, “pricing” and three names.

Everything below comes from reading a few hundred of these.

Start here. Open ChatGPT, ask the “best [your category]” question your buyers ask, and read the query it writes back. That one string shows you whether ChatGPT knows your brand exists, which is what AI visibility audits are sold to answer. Everything else in this article is about what to do with what you find in it.

Idea 2. The shortlist exists before the search runs

The obvious objection to my note taking example is timing. Maybe ChatGPT searched once, saw those brands, then wrote a smarter second query. That’d make the names a result of retrieval rather than a cause.

So I tested it properly. For each conversation I took the first user message and the first search query, ordered by timestamp. At that point nothing’s been fetched, so there’s no earlier result to have learned from.

In 21 of 27 conversations, that first query contained brands the user never typed.

What I askedWhat ChatGPT searched for, before any resultsbest AI note taking app 2026…official pricing features Granola Notion AI Otter Fireflies Fathom Mem...