Why an AI recommends some sites and never mentions others, and what makes a website worth citing.
When you ask ChatGPT or Perplexity for a recommendation, you get a finished answer with a few sources. But why exactly those sources? Why do some companies show up and others never? It is worth a look behind the scenes.
The process in two steps
Roughly, this is what happens:
- Fetch sources. The AI looks for relevant pages. From where varies: ChatGPT and Copilot use a lot from the Bing index, Perplexity crawls itself, Google AI Overviews reach into the Google index.
- Build the answer. From those sources the AI writes an answer and cites the pages it relied on.
Step one is the important one. Whoever is not in the index cannot show up in step two. It is that simple.
What makes a page worth citing
The AI prefers content it can use easily:
- Self-contained paragraphs that make sense even without the rest of the page.
- Factual and concrete. Clear statements instead of vague advertising.
- Current. Old, dead content gets pulled in less often.
- Matching the question. The page has to cover exactly what is being asked.
- A trustworthy domain and a clear entity: who you are, what you do.
Why some never show up
- They are in none of the indexes the AI draws from.
- The content sits in JavaScript or under so much clutter that the AI cannot read it cleanly.
- The page stays vague and answers no concrete question.
- Authority is missing, nobody points to it.
What you can do
Readable, clearly structured content. Concrete answers to real questions. An llms.txt and structured data. And very practically: register your site with Bing Webmaster Tools, because that is where ChatGPT gets many of its sources.
The whole picture is in SEO is not enough anymore: now GEO matters too. If you want to know whether AI systems can even use your page, take a look at my SEO and GEO analysis.
