When a person asks ChatGPT, Perplexity, Claude, or Gemini a question, the assistant answers from sources it can read and trust. Getting cited means being one of those sources. A site is cited when the assistant can reach its content, read it cheaply, confirm the facts, and find corroboration elsewhere. This guide covers what that takes.
Be readable, not just rendered
An assistant that does not run JavaScript sees an empty shell where a client-rendered page should be. The first requirement is that the content arrives in the response: a prerendered or static page, a markdown form served through content negotiation, and an llms.txt that maps the site. A page an assistant cannot read is a page it cannot cite.
State your facts as data
Prose can be summarized wrongly. JSON-LD states the facts of a page, such as the organization, the service, and the price, as data an assistant reads without inference. Structured data also ties a page to an entity an assistant already knows, which is why a Wikidata item and consistent sameAs links raise the odds that the assistant attributes the content to the right source.
Be corroborated
An assistant is more likely to cite a claim it can confirm in more than one place. A site that only references itself is weaker than one that independent sources also describe. Open-source code, a public company record, listings in directories an assistant trusts, and genuine third-party mentions all raise confidence. The signal is consistency across sources, not volume.
Be indexed where the assistant searches
Several assistants retrieve through a search index before they answer. If a site is not indexed where the assistant looks, it cannot be cited regardless of quality. Submitting URLs through the index protocols a site supports, and keeping the sitemap and llms.txt current, is how new content reaches that layer.
Measure it
Whether a site is cited is observable. Ask the assistants the questions a buyer would ask and record which sources they name. Repeat on a schedule. The sources that appear, and the ones that do not, tell you where the work is. turva.dev runs this check monthly against its own queries.
For an audit of how legible and citable a site is to assistants, contact info@turva.dev.
Related
- Agent-readiness, AEO and GEO: how they relate
- SEO and agent-readiness are not the same
- llms.txt explained
Originally published at https://turva.dev/guides/get-cited-by-ai-assistants
Top comments (3)
do you think the structure of the data matters more than the actual keywords for these bots now? ngl it feels like a totally different game than old school seo
wondering if structured data helps more than just plain text for these bots, or if they basically just scrape everything anyway
Structure matters more than keywords now, and the reason does not map back onto SEO. Keyword density was a signal for a human skimming a ranked list. An agent is not ranking you, it is pulling one fact out to act on, so what helps is whether that fact comes out unambiguous. On the second question, yes, they scrape everything, and that is the problem structured data fixes rather than a reason to skip it. When a bot ingests raw HTML it burns most of its context on nav and boilerplate, and the failure mode is subtle: it reads you fine and picks the wrong value. Scanning mid-size sites this summer, the raw HTML often runs ten times the tokens of the actual content and sometimes far more. A markdown version and JSON-LD add nothing new for a human. They cut the tokens and remove the guess for the machine. So the reader changed, and what you do about it changed less than it feels.