# Make your website easier for AI assistants to find and cite

Clear, accessible content and consistent facts help retrieval systems understand a site. This guide separates that work from the uncertain outcome of being selected as a source.

When a person asks ChatGPT, Perplexity, Claude, or Gemini a question, the assistant answers from sources it can read and trust. Being cited means being one of those sources, and no site controls that outcome directly. What a site controls is whether the assistant can reach its content, read it cheaply, confirm the facts, and find corroboration elsewhere. This guide covers that part.

## 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, which means a prerendered or static page. A markdown form served through content negotiation and an llms.txt that maps the site help the clients that read them, and no assistant is obliged to. Google states that Search, including its generative features, ignores llms.txt, so publish the file for the clients that use it rather than as a route into Google. 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 may already know, for example through a Wikidata item and consistent sameAs links across profiles. Neither one settles attribution by itself. What they remove is ambiguity about which entity a claim belongs to, which matters when the same name could point to more than one organization.

## 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 the count of them.

## 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 current, is how new content reaches that layer.

## Measure it

Whether a site is cited is observable, and it is the one part of this list that has to be measured rather than reasoned about. 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 against its own queries.

## Frequently asked

**How do you get a site cited by AI assistants?**

A site is cited when the assistant can reach its content, read it cheaply, confirm the facts, and find corroboration elsewhere. That means readable content in the first response, facts stated as data, independent corroboration, and being indexed where the assistant searches. None of it decides the outcome on its own, because the assistant still chooses.

**Why does corroboration matter for citation?**

An assistant is more likely to cite a claim it can confirm in more than one place. Open-source code, a public company record, trusted directory listings, and genuine third-party mentions raise confidence. The signal is consistency across sources, not volume.

**What makes a claim easy for an assistant to confirm?**

Facts stated as data rather than prose, and the same fact visible in more than one place. Open-source code, a public company record and genuine third-party mentions raise confidence, and consistency matters more than volume.

## Sources

- [Google Search Central, optimizing your website for generative AI features on Google Search](https://developers.google.com/search/docs/fundamentals/ai-optimization-guide)
- [OpenAI crawler and user-agent documentation](https://developers.openai.com/api/docs/bots)
- [Content Signals](https://contentsignals.org/)
- [llms.txt proposal](https://llmstxt.org/)

## Related

- [llms.txt explained](/guides/llms-txt)
- [SEO and agent-readiness: overlap and differences](/guides/seo-vs-agent-readiness)
- [Agent-readiness, AEO and GEO](/guides/agent-readiness-aeo-geo)