RANKING INTELLIGENCE · GPT-5-6

How to get your business recommended by ChatGPT

We record what ChatGPT actually does before it answers - every search it runs and every page it reads - and publish what that says about getting recommended. Every number here comes from those recordings.

6.8%
of recommended businesses got there because of a page someone published. That is the share you can influence.
36.0%
of everything ChatGPT read was a company's own website, not a review or a listing.
3.4
searches run, on average, before it answers a single question.
10
recorded answers behind these figures
30%Checking how current you are: 27.6% of searchesChecking how current you are27.6%Looking for prices: 13.8% of searchesLooking for prices13.8%Reading one site in particular: 13.8% of searchesReading one site in particular13.8%Looking for the official source: 10.3% of searchesLooking for the official source10.3%Looking for reviews: 3.4% of searchesLooking for reviews3.4%Naming a directory or accreditation body: 3.4% of searchesNaming a directory or accreditation body3.4%Looking for a ranked list: 3.4% of searchesLooking for a ranked list3.4%

Live signal scan

Each spoke is something ChatGPT put into its own searches before it answered. Longer means it came up more often.

Read off 29 searches across 10 recorded answers. Re-scanned every time we capture.

Values are the share of searches carrying that signal. Rings mark 10% steps.
Start here

Four ways a business ends up in the answer

We traced every recommended business back to whatever first put it there. Only one of these routes is open to a company that is not already famous.

Already known to the model
22.3%
Pulled from local business records
32.0%
Put there by a page it read
6.8%
No source we could identify
38.8%
What it searches for

The words it looks for, and what to do about each

ChatGPT writes its own searches before it answers a question. Every row below is a signal it put in those searches. Open one to see what it means for your site.

What ChatGPT looks for before it recommends anyone

Share of 29 searches it ran
10 recorded answers
Bars: share of that day’s searches carrying the signal, 2026-08-27 to 2026-09-014 capture days · 28 answers
Checking how current you are
0.0%37.5%18.4%100.0%
08-2708-2808-3109-01
27.6%

27.6% of searches carried a year, and some limited results to the last 30 days.

What to do about itDate your pages and keep the current year in the title where it is honest to do so. Undated pages lose the freshness check silently.
Looking for prices
0.0%27.5%15.8%0.0%
08-2708-2808-3109-01
13.8%

13.8% of searches asked about price, fees or plans.

What to do about itPut real numbers on the page. A quote form is not an answer to this search.
Reading one site in particular
0.0%20.0%10.5%0.0%
08-2708-2808-3109-01
13.8%

13.8% of searches were restricted to a single website.

What to do about itMost of these go to a company's own domain. Your site is the thing being read, so it has to answer the question directly.
Looking for the official source
0.0%20.0%7.9%0.0%
08-2708-2808-3109-01
10.3%

In 10.3% of the searches it ran, ChatGPT added the word "official" - it was hunting for a company's own authoritative page.

What to do about itHave one page that plainly states who you are, what you do, where you operate and what you charge. That is the page this search is trying to find.
Looking for reviews
50.0%0.0%10.5%0.0%
08-2708-2808-3109-01
3.4%

3.4% of searches asked for reviews or ratings rather than price or location.

What to do about itPublish a reviews page with real detail - the job done, the location, the date. Volume of stars alone carries nothing the model can quote.
Naming a directory or accreditation body
0.0%5.0%10.5%33.3%
08-2708-2808-3109-01
3.4%

3.4% of searches named a specific directory, review platform or trade body.

What to do about itFind which body the model names in your trade and market, then make sure you are listed with it and that you say so on your own site.
Looking for a ranked list
0.0%2.5%0.0%33.3%
08-2708-2808-3109-01
3.4%

3.4% of searches looked for rankings or league tables.

What to do about itGet into the ranked lists that already exist in your sector rather than publishing your own.
LLMJESUS.COM · RANKING INTELLIGENCETAP ANY ROW FOR WHAT TO DO ABOUT IT
What it reads

The pages that actually get pulled

"Best" and "top" pages31.7% of pages read
31.7% of the pages it read were framed as best or top.
Do thisBeing listed on someone else's "best of" page is worth more here than publishing your own.
Pages with a year in the title28.1% of pages read
28.1% of the pages it read carried a year in the title.
Do thisDate your commercial pages and refresh them, so the year in the title is true.
Comparison pages9.4% of pages read
9.4% of the pages it read compared named options.
Do thisPublish an honest comparison including your competitors. It is the format most likely to be read back.
Numbered lists8.5% of pages read
8.5% of the pages it read were numbered lists.
Do thisAim to be an entry in the numbered lists that already rank in your category.
Pricing pages6.7% of pages read
6.7% of the pages it read were about cost.
Do thisPublish indicative pricing. It is read directly and it is rarely available.
Review pages5.8% of pages read
5.8% of the pages it read were reviews.
Do thisThird-party reviews of you are worth more than your own claims about you.
Guides and how-tos4.9% of pages read
4.9% of the pages it read were guides.
Do thisA buyer's guide with real numbers gives the model something specific to quote.
Tested or expert-led pages2.2% of pages read
2.2% of the pages it read claimed testing or first-hand expertise.
Do thisShow the work. First-hand detail is what separates a quotable page from a summary of other pages.
Award and accreditation pages0.9% of pages read
0.9% of the pages it read carried award or accreditation language.
Do thisList credentials with the issuing body, and link to the issuer as proof.
What we conclude

Read straight off the data

Retrieval is mostly third-party pages

64.0% of retrieved results were pages the named brands do not own. This is the condition under which placement can move an answer.

measuredbased on 10 recorded answers

The model scoped searches into sites we can get onto

1 of 4 domain-scoped searches targeted a domain no named brand owns. Those are obtainable listings and should be treated as the priority placement targets.

measuredbased on 10 recorded answers

What the pages have to answer

Share of the 29 captured fan-out queries carrying each signal: year_qualified 27.6%, pricing 13.8%, site_scoped 13.8%, official_lookup 10.3%. A page that cannot satisfy the common ones fails the check silently.

measuredbased on 10 recorded answers

Fields present but empty on every record

is_claimed, popularity_score, provider, ranking_score, review_highlights, reviews — anything computed from these on an earlier build is no longer computable from the transport.

measuredbased on 10 recorded answers
Why the instrument matters

An API is not ChatGPT

We put the same 28 questions through a recorded ChatGPT session and through the two API routes that AI-visibility tools are built on. They agreed with the browser on 1.3% and 1.8% of the sources found. Both APIs searched on roughly half the questions the browser searched on, and neither returned a single local business record.

Recorded ChatGPTDataForSEO monitorOpenAI API direct
Sources found3777974
Questions it searched at all28 of 2818 of 2816 of 28
Agreement with the browser-1.3%1.8%
Local business records read14 capturesnonenone

Same questions, same day. The gap is not a vendor problem: one is a third-party monitor, the other is OpenAI’s own API called directly. If a tool reports your AI visibility from an API, it is reporting on a different system from the one your customers use.

Want this run on your market?

We record a real ChatGPT answer for the question your buyers actually ask, then walk you through the trace: the searches it wrote, the pages it opened, and who it recommended instead of you.

Get my ChatGPT visibility scanFree on the call. No pitch deck.

How we measured this

We record the network traffic behind real ChatGPT answers - the streamed response and the stored conversation - rather than scraping the page or asking the model what it did. One question per fresh conversation, on a real account, under a fixed daily limit.

  • 10 recorded answers across 8 categories on gpt-5-6.
  • Findings marked indicative rest on too few recordings to be firm. We publish them as such rather than rounding them up.
  • Answers vary between accounts, locations and settings. These come from a single account and a declared location.
  • Behaviour changes between model versions. Anything here is true of gpt-5-6 and is re-measured rather than assumed.

What would make these numbers wrong

Measured effects we can see in our own data. We publish them because a figure you cannot challenge is not evidence.

  • Our own question wording changes the answer. Prompts containing the word “best” pulled 38.4% best-titled pages; prompts that never said it pulled 24.9%. Read any “best” figure as partly an echo of how the question was asked.
  • Every capture comes from one account on one connection. Personalisation, location and account history all move these answers; we hold them constant rather than sampling across them.
  • The day-by-day bars show when we recorded, not how behaviour moved: our capture days so far covered different categories and markets. They become a trend once the same panel has run twice.
  • Categories here were chosen by us, not sampled at random, so they describe commercial questions of the kind we picked rather than all questions.
LLM JESUS · RANKING INTELLIGENCE · 10 RECORDED ANSWERS