How to get cited by ChatGPT: how to show up, rank and get mentioned in its answers · Citable

Description

written for teams no score out of 100 no ten-step checklist written for teams no score out of 100 no ten-step checklist written for teams no score out of 100 no ten-step checklist

How ChatGPT decides which pages to cite

When somebody asks ChatGPT a question that needs current facts, it searches, opens a handful of pages, writes the answer from what it could read, and lists the pages it used. Three crawlers do the reading: OAI-SearchBot builds the index it searches, ChatGPT-User fetches a page at the moment of the question, and GPTBot collects pages ahead of time for training.

So “how do I rank in ChatGPT” is really four questions: can it reach you, can it read you, does it believe you, and does it pick you. You control the first two completely, the third partly, and the fourth not at all. Start where you have control.

1. Let its crawlers in

A page ChatGPT cannot fetch cannot be cited. Check robots.txt for a rule that refuses OAI-SearchBot or ChatGPT-User — plenty of sites have one they never chose, inherited from a template. Then check the layer in front of the site: a CDN setting that blocks AI bots refuses the crawler before robots.txt is ever read. The rule, platform by platform, is on the OAI-SearchBot page ; Cloudflare’s switch is covered under AI crawlers on Cloudflare .

2. Make the page readable without JavaScript

ChatGPT’s crawlers take the HTML your server sends and do not run the scripts in it. A price drawn by a script, a review widget, a pricing table that loads after the page — none of it is there for them. This is the most common reason a good page is quoted badly: the facts were on the screen and not in the HTML. Can ChatGPT read my website? walks through the check.

3. Answer the question in the first lines

ChatGPT is looking for a sentence it can use. Put the question in a heading, the way a person would type it, and answer it directly underneath — the number, the yes or no, the definition — before the background. A page that builds up to its point for three paragraphs is read as a page without one.

4. Be the source, not the summary

An answer engine credits where a fact came from. If your page repeats what ten others say, the citation goes to whoever said it first. Your own prices, your own measurements, your own policy in exact words, a named person saying something specific — these are things only your page can be the source of.

5. Say who you are the same way everywhere

ChatGPT builds its picture of a brand from every place the name appears. One clear description of what you do, repeated on your site, in your structured data and on your profiles elsewhere, makes you one thing it can recognise. Three different taglines make you three vague ones. It is also why mentions on other sites matter — reviews, directories, press — and that part of the work is outside your website.

6. Measure it, so you know what changed

ChatGPT adds utm_source=chatgpt.com to the links it shows, so a visit from an answer can be counted — see what that tag means and how to track it . The other half is knowing what its crawlers read before the visit: which pages, how often, and whether somebody was waiting. Without both, you are guessing which change worked.

What does not work

Paying to be cited. There is no placement to buy in an organic ChatGPT answer.

Stuffing a page with the question forty times. It is reading for an answer, not counting words.

A special file alone. llms.txt is cheap and harmless, and it is not what ChatGPT search reads.

Anyone’s guarantee. The choice of what to cite is the model’s. A promise of “rank #1 in ChatGPT” is a promise about something the seller does not control.

You cannot make ChatGPT choose you. You can make sure that when it looks, the answer is there, in text, at the top — and that you can see it looked.

Where Citable fits

Steps one and two are mechanical, and they are where most sites lose. Citable takes them off your hands: when ChatGPT’s crawlers — or any of the others on the list — ask for a page, they are given the content alone, with every fact present as text, at the same address. People and Google still get the page you designed. Then the panel shows the reads as they happen, and the people ChatGPT sent back.

Start with the free scan : it fetches one of your pages the way ChatGPT does and shows what survived the trip. The rest of what ChatGPT does with a site is on the ChatGPT page .

The chain, drawn Access, then comprehension, then the choice.

Access — an engine you refuse never reads anything.

Comprehension — the facts have to survive the markup.

Choice — which stays the model’s, whatever anyone sells you.

Read next The rest of the set.

6 min read AI search optimization

How an assistant decides what to say about your site, and which of those steps a team can actually influence.

7 min read What GEO can and cannot do

What generative engine optimisation means, what it borrowed from SEO, and which parts of it are sold as certainty but aren't.

5 min read How AI crawlers read a website

Rendering, fetch budgets, robots.txt, and why a JavaScript-drawn price is invisible to almost every engine reading you.

8 min read Generative engine optimization (GEO)

What it means, how an AI engine chooses its sources, the strategies with evidence behind them, and what GEO tools actually do.

7 min read Answer engine optimization (AEO)

What it means, three before-and-after examples, the practices that matter — and the step that comes before any of them.

5 min read Can ChatGPT read my website?

How it reads a site, why it does not run JavaScript, the five things that stop it, and how to check in a minute.

5 min read llms.txt: what it is, and what it does not do

What goes in the file, a working example, best practices — and whether any AI search engine actually reads it.

5 min read utm_source=chatgpt.com, and tracking AI traffic in GA4

What the tag on your URLs means, why ChatGPT adds it, and how to see every AI engine in Google Analytics.

6 min read Should you block AI crawlers?

Training bots, search bots and live fetch are three different decisions — and the one blocked by accident costs the most.

5 min read GEO vs AEO vs AIO vs LLMO

The full form and meaning of each, where the terms came from, and the four steps underneath all of them.

Or just look at it One page, served both ways.

What survives each trip, with the token count for both.

About Citable Who is behind this page, and what we stand on.

When an AI agent — ChatGPT, Claude, Perplexity or any of the 81 that Citable recognises — opens a page, Citable removes the theme, scripts, navigation and layout and serves only the content: the same facts, at the same URL, on the site's own domain. People and Google still get the full designed page.

Who opens the page What they are given

A person in a browser The full designed page, untouched.

Googlebot, Bingbot and other search engines The full designed page, untouched.

An AI agent — GPTBot, ChatGPT-User, ClaudeBot, PerplexityBot and the rest The content only: no UI, no scripts, the same facts at the same URL.

Measured, not estimated. A real product page of 386.8 KB is served to AI agents as 4.6 KB — 98.8% smaller, with the same facts. Every figure on this site comes from a fetch anybody can repeat.

One list. The 81 AI agents named on these pages are the list the product itself runs on. A page here cannot describe a crawler Citable does not serve.

Search is never touched. Googlebot and Bingbot always get your real page. The clean copy is for AI agents only — at the same address, with the same facts.

Checked, not trusted. A user agent is a claim, and anyone can send one. Where an operator publishes its addresses, every read is checked against them and recorded as verified or not.

Nothing about your visitors. Citable sees which crawler read which page. It does not see who your customers are, and their details never reach us.

Honest about limits. Nobody can promise a citation or a ranking, and we do not. What we show is what an AI agent was given, and whether it sent somebody back.

How it works · The measurements · What it touches and stores · Why Citable · Pricing · Questions, answered plainly · Talk to us

Free · about 20 seconds · no signup Find out whether AI has ever read your site.

Type your address. We fetch a page exactly as GPTBot does, count the tokens, and score fifteen things an answer engine needs. If the log then stays empty for a month, that is worth knowing too.

No contract · cancel any time · Googlebot untouched