Key takeaways
- llms.txt is an optional note for agents. It is not a ranking lever, and Google Search does not use it as a ranking signal.
- Treat it as a README: it must match the public site, its links must resolve, and it must never outrank the HTML.
- The work that matters is honest public pages — the site, the copy, and SEO — not a file that invents a better version of the business.
Someone hears that agents read a file at the root, drops a Markdown note on a site that still cannot explain itself, and calls it GEO.
The homepage is still a slogan. The service pages still disagree. The file is the cheapest thing to write, so it gets written first. That is backwards. llms.txt is a short note for agents. It is not a ranking lever. Google Search does not use it to rank pages. A well-made one matches the public site. A badly made one invents a cleaner company than the HTML will admit.
A note at the root, if you want one
In September 2024, Jeremy Howard published a proposal at llmstxt.org: put a Markdown file at `/llms.txt` so a language model that is trying to use your site can read a curated orientation instead of guessing from a homepage full of chrome.
The idea is modest. An agent that fetches a marketing page also fetches the cookie banner, the nav, the footer, the newsletter modal, and three competing headlines. A short file can say: this is the project, these are the pages that matter, start here.
The proposed filename is `llms.txt`, with the *s*. The extra letter is not a product. It is the file the proposal named.
The proposed shape is a README, not a schema:
- One H1 with the site or project name. That is the only required section.
- An optional blockquote with a short summary.
- Optional prose — paragraphs and lists, not more headings — that explains how to read the rest.
- Zero or more H2 sections. Each section is a list of Markdown links — a name, a URL, optionally a colon and a note.
- An H2 titled `Optional` has a conventional meaning: skip these URLs if context is tight.
A companion file at `/llms-full.txt` appears in the same proposal: a longer dump for systems that want the pages concatenated, not just the map. Most sites do not need it. A map that lies is worse than no map.
The file is served as plain text. A person can open it in a browser and read it. That is the point. If a human cannot tell what the site is from the file, an agent will not either.
Generate the file from the canonical inventory
Do not draft llms.txt in isolation. Start with a table:
| Page | Canonical URL | Public purpose | Owner | Last reviewed | Include? |
|---|---|---|---|---|---|
| Homepage | Absolute URL | Organisation orientation | Brand owner | Date | Yes |
| Service page | Absolute URL | Specific offer | Service owner | Date | Yes |
| Article | Absolute URL | Durable reference | Editorial owner | Date | Selectively |
| Campaign page | Absolute URL | Temporary promotion | Campaign owner | Date | Usually no |
| Preview or internal tool | Non-public | Internal work | Internal owner | Date | Never |
Build the file from rows marked for inclusion. Use absolute canonical URLs, short factual annotations, and an Optional section for lower-priority material if following the proposal’s convention. Validate every link in CI. Remove retired pages when redirects or archives change their meaning.
The proposal describes one H1, an optional blockquote summary, optional explanatory prose, and H2 sections containing Markdown links. It also proposes llms-full.txt for larger compiled content, but most commercial sites do not need to duplicate the whole site into another maintained document.
Google has stated that Search does not use llms.txt as a ranking signal. That makes maintenance discipline more important, not less: the file should exist only when there is a plausible consumer and an owner willing to keep it truthful.
Never place private paths, draft offers, API secrets, client previews, or claims absent from the public pages in the file. Orientation is not privileged access.
The public pages are llms.txt proposal and Google Search Central — Optimising for generative AI.
robots.txt, sitemap, and this file
llms.txt is easy to oversell because it looks like `robots.txt` and sits in the same mental slot as a sitemap. It is neither.
| File | Job |
|---|---|
| `robots.txt` | Permission. What a crawler may request. |
| `sitemap.xml` | Discovery. Which URLs you want a search engine to know about. |
| `llms.txt` | Orientation. A curated note for agents that choose to read it. |
Permission is not orientation. Discovery is not ranking. A note is not a lever.
The file is also not a Google ranking signal. Search ignores it. Presence neither helps nor harms Google visibility. It is not a guarantee that ChatGPT, Claude, Perplexity, or any other system will cite you. It is not a replacement for crawlable HTML, titles, internal links, or useful copy. It is not a place to publish prices, offers, or proof that the public pages do not carry. It is not a required GEO tactic.
If a vendor sells "AI crawler documentation" as if the file were a backlink or a featured snippet, they are selling a filename. The filename does not rank.
Write it like a public README
Match the public site. The summary should be a compression of the homepage, not a second brand. If the site says you design and build brands, websites, and products, the file should say that. If the site does not claim a metric, the file does not invent one.
Links must resolve. Every URL in the list should be a real, current page. Dead links, redirects to the homepage, preview URLs, and "coming soon" paths do not belong. An agent that follows a broken link learns that the map is untrustworthy. A person who opens the same file learns it faster.
Never outrank the HTML. The HTML is the source. The file is a pointer. If the two disagree, the page wins — or should. Structured data has the same rule: it may clarify a visible fact; it may not introduce a claim the visitor cannot read. llms.txt is the same discipline in Markdown.
Keep it current. A README that lists last year's offers is worse than silence. When you retire a URL, remove it. When you publish a page you want an agent to prefer, add it. When the company description changes on the homepage, change the blockquote the same week.
Do not put secrets in it. The file is public. Private previews, internal tools, draft pages, and staff-only routes have no place in a document that any client can fetch.
Those rules are how you avoid teaching a model a fictional company.
Our /llms.txt as a format, not a ranking claim
CLICK.BLUE publishes llms.txt. Use it as a format example, not as a ranking claim. We do not say the file makes the site rank. We do not say it gets the company cited. We say: if an agent looks for a note, this is the note, and it agrees with the site.
The file follows the proposed order. It opens with `# CLICK.BLUE` and a blockquote that restates the homepage fact: a creative and technical network founded in 2014 that designs and builds brands, websites, digital products, campaigns, software, AI agents, automation, and ongoing systems. The same sentence carries the public record — 12+ years in operation, 50+ businesses supported, 100+ websites launched. Those numbers appear on the site. They are not invented for the file.
Then the file does the README job: canonical facts a model should not have to reconstruct, a short key for how to read the site, and H2 sections of links — essential pages, services, offers, then optional URLs. After the first H2, every non-blank line is a Markdown link with an absolute `https://www.click.blue` URL and a one-line note that restates the destination page. The file is a map of the public site. It is not the site.
Google Search ignores the filename
Google Search does not use llms.txt to rank pages or to appear in its generative features. It is fine to create and maintain the file for other systems that read it. Doing so will not help or harm Google visibility.
That does not make the file forbidden. It makes it the wrong place to spend the week if the homepage is still a slogan. Google may crawl many kinds of files. Discovery is not special treatment. A crawled text file is not a ranking document.
If you maintain llms.txt, maintain it for the agents that might read it. Do not report it as an SEO deliverable that moved rankings. If rankings move, they moved because pages, links, demand, and time moved — the ordinary search work, not a filename.
Do the pages before the Markdown
An agent that only reads llms.txt can be misled. An agent that reads the file and then fetches a page can check. A person who lands from search will only see the page. If the file promises a service the page does not describe, or a proof the page does not show, you have published two companies. The cheaper one to write is the file. The one that gets judged is the HTML.
So the order of work is not "write llms.txt, then decorate a site around it." The order is:
1. Decide what the business actually sells. 2. Put that on public pages a stranger can finish. 3. Make those pages crawlable, fast enough, and internally linked. 4. If you want a note for agents, summarize the pages you already shipped.
Skip step four if you have not finished step two. A precise file about a vague site is still a vague site.
The same rule applies to answer engines. A model may quote a short, supported sentence from visible HTML. It may ignore you. Schema and llms.txt may repeat that sentence. They cannot mint a citation.
Write an llms.txt when the public pages already agree with each other, you can list the essential URLs without padding, every link resolves, and you will update the file when the site changes. Skip it when the homepage is still mush, the offers are still being invented, or someone is asking you to "add GEO" by dropping a file on a site that cannot yet explain itself. In that case the next step is not Markdown at the root. It is the pages.
If you already know the offer and need the site to say it, that is a full website and the SEO that follows. If you want to write the file yourself, read the proposal, open our llms.txt, and copy the discipline — not the claims. Match your pages. Do not copy ours.
A filename will not rank you. Honest public pages might be found. The estimator at get started turns the current setup into a scoped proposal — the site and the search work, not a file for sale.
