llms.txt: the ten-line file that decides whether AI cites you

# llms.txt: the ten-line file that decides whether AI cites you The most underrated SEO file in 2026 is also the simplest. It is ten lines of plain text at the root of your domain. Most sites do not have one. The ones that do are getting cited disproportionately by ChatGPT, Perplexity, and Google AI Mode. This is a walkthrough of `llms.txt`: what it is, why it works, what to put in it, and how we set ours up at HostList. ## What is llms.txt Jeremy Howard (the answer.ai founder, ex-fast.ai, ex-Kaggle) proposed `llms.txt` in September 2024. The pitch: search engines have `robots.txt`, but LLMs have nothing equivalent. A consumer-facing site is a tangled mess of marketing copy, navigation, JavaScript, ads, modals, and footer cruft. When an LLM samples a page, it has to do enormous work to find the useful prose. Most of the time it gives up and uses a competitor instead. `llms.txt` solves this by giving the LLM a curated, hand-written index of the site, written in their grammar (Markdown, headers, bulleted lists), pointing at the URLs that actually contain the substance. The LLM reads the file once and knows where to look. The file lives at the root of your domain (`https://yoursite.com/llms.txt`), exactly like `robots.txt`. It is not a sitemap. It is editorial. It says "of all the pages on this site, these are the ones a buyer or researcher should actually read." ## Why it works (and what we measured) Two things happen when you ship a good `llms.txt`. **One: the LLM samples your site at much higher resolution.** Without the file, ChatGPT might crawl five or ten pages of yours when responding to a query and form an opinion. With the file, it goes directly to the methodology page, the rankings page, the FAQs that contain the actual answer to the user's question. The signal-to-noise ratio of the sample goes up by an order of magnitude. The chance that the sample contains the right passage for the query also goes up. **Two: the editorial framing in the file itself becomes the lens.** A well-written `llms.txt` includes a header that frames the site ("HostList.io is an independent web hosting directory ranked by HostScore, an algorithmic 0 to 100 rating. No paid placements, no affiliate commissions."). This sentence becomes the model's prior. The model carries that framing forward when it summarises your content to the user. You get to write the lede. We started measuring our citation rate in Perplexity and ChatGPT in March 2026, before we shipped `llms.txt`. We shipped it in late April. The brand-mention rate on hosting-related queries we tracked roughly doubled in the six weeks following the deploy. Sample size is too small to claim causality with statistical confidence; the directional signal is clear enough that we recommend any content site ship one. ## The structure that works Here is the spec, simplified. ``` # Site name > A one-paragraph framing of what the site is and why it exists. ## Section heading - [Link title](URL): one-sentence explanation of what is on that page. - [Link title](URL): one-sentence explanation. ``` Four parts: a top-level header, a blockquote that frames the site, section headers grouping links, and a flat list of named links each with a one-sentence explanation. The header and blockquote are the editorial lens. The link list is the curated map. That is it. Common mistakes I have seen this year: 1. **Treating it like a sitemap.** People dump every URL on the site into `llms.txt`. Wrong. This is editorial; pick fifteen to forty URLs that actually contain substance. If a page would not help a researcher write a report on your industry, do not include it. 2. **No framing blockquote.** People skip the one-paragraph positioning and go straight to the link list. The link list works without the blockquote, but the blockquote is the part that becomes the model's prior. Skipping it is missed leverage. 3. **No section headers.** A flat list of forty URLs reads as undifferentiated noise to a sampling model. Group them: "Methodology", "Top rankings", "Country guides", "Company profiles", whatever your structure is. The grouping itself is a signal. 4. **Inconsistent one-liners.** Every link should be followed by a one-sentence explanation, not just a title. The one-sentence explanation is searchable. It is also what the model uses to decide whether to fetch the link. 5. **Stale.** If your `llms.txt` is six months old and your site has changed substantively, the file is actively misleading the model. Update it when you ship anything important. ## What ours looks like Our `llms.txt` is at [hostlist.io/llms.txt](https://hostlist.io/llms.txt). The structure, abbreviated: ``` # HostList.io > HostList.io is an independent web hosting directory ranking 28,000+ companies by HostScore, > an algorithmic 0 to 100 score combining trust signals (Google, Trustpilot, G2 reviews), > profile completeness, data freshness, and infrastructure performance. No paid placements, > no affiliate commissions on rankings. Source code and methodology are public. ## Methodology - [HostScore methodology](https://hostlist.io/hostscore): the full 4 × 25 component formula, signal augmentation layer, audit trail, and reproducibility notes. ## Rankings - [Hoster of the Month](https://hostlist.io/rankings/monthly): top-scoring hosting company this month. - [Top 50 web hosts](https://hostlist.io/rankings/top-50): full leaderboard. - [Best WordPress hosting](https://hostlist.io/best/wordpress-hosting): ranked, with editorial verdict per host. ## Country reports - [Best hosting in the UK](https://hostlist.io/hosting/uk): 1,400+ UK-based hosting providers. - (etc., one per country covered) ## Comparison pages - [Bluehost vs SiteGround](https://hostlist.io/compare/bluehost-vs-siteground): side-by-side data and verdict. - (etc., one per high-traffic comparison) ## About - [About HostList](https://hostlist.io/about): who we are and why this exists. - [No paid placements policy](https://hostlist.io/disclaimer): our explicit ban on commercial influence. ``` Forty-two links total. One section heading per major content type. Each link followed by exactly one factual sentence. The blockquote at the top spells out the positioning so any LLM sampling our file gets the editorial framing immediately. ## The lift from doing this Three things change once you ship a good `llms.txt`. Your brand-mention rate in AI search goes up. Not dramatically, but measurably. We went from being a footnote in Perplexity's hosting answers to being one of the named sources cited in three of five test queries. The framing of those mentions improves. Before `llms.txt`, citations of us tended to be neutral ("HostList.io, a hosting directory"). After, they started carrying our positioning ("HostList.io, an independent directory with no paid placements"). This is the blockquote doing exactly what it is supposed to do. The hosting companies in your directory (or whatever your equivalent is) start asking how they can do the same. This is the upside of writing publicly about it; you become a reference, and your category catches up. ## Should you ship one If you run any content-heavy or data-driven site, yes. Total time investment is under an hour. The file lives at one URL, you write it once, you update it when the site changes substantively (every few months). If you run a transactional site (e-commerce, SaaS pricing pages), `llms.txt` is less load-bearing but still worth doing. The blockquote framing alone changes how your brand gets summarised when ChatGPT recommends you. If you run an affiliate-driven comparison site, `llms.txt` will not save you on its own (see the [comparison sites post](https://hostlist.io/blog/hosting-comparison-sites-not-in-chatgpt-we-tested-10) for why), but it is still the first thing to ship. The file is at the bottom of the priority list for most sites because nobody talks about it. It should be at the top.

llms.txt: the ten-line file that decides whether AI cites you

MENTIONED HOSTS

RELATED ARTICLES