← All guides

Guides

How AI assistants choose which sources to cite

By the Promvia team

Published

In short

AI assistants with live search retrieve candidate pages, then quote the passages that best answer the question with the least work: direct answers near the top, concrete statistics, quotable sentences, named sources, and recent dates. For competitive questions they lean heavily on third-party sources — reviews, comparisons, communities — over vendor sites. There is no secret ranking to game; there is a consistent preference for evidence-shaped content on trusted domains.

The two-stage reality: retrieve, then quote

AI assistants with browsing (Perplexity, ChatGPT search, Gemini) work in two stages. First a retrieval step finds candidate pages — this looks a lot like classic search, which is why SEO authority still matters. Then a synthesis step decides which passages actually make it into the answer. You can win retrieval and still lose synthesis: your page was read, but nothing in it was worth quoting.

Most GEO advice fails by only addressing stage one. The passage-level game — being the sentence an AI assistant wants to lift — is where sites that consistently get cited differ from sites that merely rank.

What the evidence says AI assistants prefer

  • Answer-shaped passages: a heading that matches the question with a direct 2–3 sentence answer under it.
  • Provenance signals: named sources, specific numbers, and recent years IN the text — AI assistants prefer quoting claims that carry their own evidence.
  • Freshness: visibly dated, recently updated pages beat undated ones for time-sensitive questions.
  • Machine-readable identity: structured data (Organization, FAQ) doesn't guarantee citations but removes ambiguity about who's making the claim.
  • Domain trust: for "best X" questions, AI assistants disproportionately cite aggregators, editorial comparisons, and community threads — consensus sources — rather than the vendors being compared.

What this means for your strategy

  • Audit passages, not just pages: for each question you want to win, does a single liftable paragraph exist anywhere on your site? If not, write it.
  • Give your claims receipts: numbers with sources and dates. "Rated 4.8/5 across 214 reviews (G2, 2026)" is quotable; "customers love us" is not.
  • Work the consensus layer: identify the exact domains AI assistants cite for your category and earn honest presence there. This is slower than on-site fixes, and it is where most of the cited evidence sits.
  • Sample repeatedly: answers vary run to run, so judge trends across scheduled checks, not single spot-checks.

Promvia's citation tracking records which domains each AI assistant cites for your tracked questions — turning "where do assistants look?" from guesswork into a ranked list you can act on.

Frequently asked questions

Do AI assistants cite the same sources every time?

No — answers and citations vary between runs, AI assistants, and phrasings. That variance is why single checks mislead and scheduled sampling across AI assistants is the honest measurement.

Does being in the training data matter more than being crawlable now?

For AI assistants with live search, current crawlability and current sources dominate. Training-data presence matters most for offline answers, and you influence it the same slow way: by being widely and credibly mentioned.

Can I pay to be cited?

Not in organic answers today. Sponsored placements are appearing in some AI assistants, but they're labeled — the synthesis itself draws on organic sources.

Does AI mention you?

Put buyer questions about your business to ChatGPT and Perplexity live, and see whether you are named and who is cited instead. Free, no signup.

See what AI says about you → Or start free →

Keep reading

How to get your brand cited by ChatGPT (and the other AI assistants) → What is GEO? Getting named in AI answers → GEO vs SEO: what changes, what doesn't →