A file called llms.txt started appearing on websites in late 2024, proposed as a standard for telling AI engines how to read and understand your content. Two years later, llms.txt has become one of the most asked-about AEO topics — and one of the most misunderstood. This article explains what llms.txt is, what it does, and whether your B2B site needs one.
What llms.txt is, exactly
llms.txt is a plain-text markdown file placed at the root of your website (at
yoursite.com/llms.txt) that gives AI engines a structured map of your site’s most important content. It was proposed in 2024 by Jeremy Howard of Answer.AI as a complement to robots.txt and sitemap.xml — but designed specifically for large language models rather than traditional crawlers.
A typical llms.txt contains: an H1 with your site or organization name, a blockquote with a one-line description, a paragraph of context, and one or more sections (typically
## Services,
## About,
## Resources) listing your key pages with brief descriptions. The format is intentionally readable by both humans and machines.
The proposed standard also defines an optional
llms-full.txt that contains more complete content — useful for sites that want to feed AI engines a richer extract beyond just the URL index.
Important distinction: llms.txt is
not a permission file. It doesn’t tell AI engines whether they can crawl your site — that’s the role of robots.txt and ai.txt. llms.txt is a content directive: “here’s what’s on this site and how it’s organized.”
Common questions
Do major AI engines actually read llms.txt?
The major engines — OpenAI, Anthropic, Perplexity, and Google — have publicly acknowledged llms.txt as a useful signal, though none have committed to specific weighting. As of 2026, the file is recognized but not yet a primary ranking input. Its strongest current value is as an
authority signal: sites with a valid llms.txt tend to have other AEO foundations in place, which engines correlate with citation-worthiness.
Is llms.txt required to be cited by AI engines?
No. Many sites currently cited heavily by AI engines do not have llms.txt files. The file accelerates discovery and helps engines understand your site’s structure, but absence of llms.txt does not disqualify a site from citation. Other factors — structured data, content quality, authority signals — matter more.
What’s the difference between llms.txt and ai.txt?
llms.txt is a
content index: it tells AI engines what’s on your site. ai.txt is a
permission directive: it tells AI engines whether they’re allowed to crawl, train on, or cite your content. The two files complement each other. A site doing serious AEO publishes both — llms.txt to invite the engines in with a map, ai.txt to explicitly allow them.
What’s the difference between llms.txt and sitemap.xml?
Sitemap.xml is a machine-readable list of every URL on your site, designed for traditional search crawlers. llms.txt is a curated, human-readable summary of your most important content, designed for AI engines that prioritize meaning over completeness. A sitemap might list 500 URLs; llms.txt might list 20 — the ones that matter for understanding what your business does and how it can be cited.
What should be in a B2B company’s llms.txt?
For a typical B2B firm, the file should include: organization name and one-line description, a paragraph of context (founding, focus, what you do), a Services section listing each core service with a 1–2 sentence description, an About section linking to company information, and optionally a Resources section linking to articles or guides. Each listed URL should have descriptive context — not just the URL itself.
Where do I put llms.txt?
At the root of your domain:
https://yoursite.com/llms.txt. It must be accessible by direct URL request, served as
text/plain. WordPress sites can deploy it via FTP/cPanel root upload, via plugins that support custom root files, or via rewrite rules. Verify after deployment by visiting the URL in a browser — you should see the raw text, not a 404.
How often should llms.txt be updated?
When your services, key pages, or organizational positioning changes meaningfully. For most B2B firms, that’s two to four times per year. New blog content categories or new service offerings should trigger an update. Stale llms.txt files (referencing services you no longer offer, for example) hurt more than help — they create factual inconsistency that AI engines detect.
How this applies to your business
Whether you “need” llms.txt depends on your AEO ambition. If you’re trying to maximize citation share across all four major AI engines, llms.txt is a low-cost, high-signal addition that takes an hour to draft and another hour to deploy. The downside risk is minimal; the upside is incremental but real.
If you’re not yet running an AEO program at all, llms.txt is not the place to start. Foundational JSON-LD schema, content restructuring around question-shaped queries, and author markup matter far more in early AEO work. llms.txt is the polish on a well-built foundation, not the foundation itself.
The practical recommendation: deploy llms.txt as part of a complete AEO foundation in the first 90 days of any AEO program. Treat it as table stakes for sites serious about being cited — even if its individual contribution to citation share is modest, its presence signals that the rest of your AEO work is likely competent too.
Iscope Digital deploys llms.txt as part of every
AI Engine Optimization engagement, along with the JSON-LD schema, ai.txt, and content restructuring that make the file useful in practice. For the related question of which schema types matter most for AI engines, see
JSON-LD schema for AI engines: which types matter most for B2B? 
