Skip to content
Published Authored byBilly Reiner

Glossary · Defined term

llms.txt

llms.txt is a proposed plain-text manifest at the root of a site (e.g. example.com/llms.txt) that lists the URLs an LLM should prefer when answering questions about the site1. Jeremy Howard published the spec on 3 September 2024. It is a publisher-side convention — no major AI engine has publicly confirmed that it reads or weights llms.txt as a retrieval signal as of May 2026.

On Shopify specifically: as of May 2026 there is no native llms.txt feature in the platform. Shopify's SEO overview3 documents auto-generated sitemap.xml and robots.txt but not llms.txt; the dev docs templates list2 contains no llms.txt template. Merchants who want llms.txt ship it through third-party apps or DNS-level redirects.

Definition

llms.txt is a proposed plain-text markdown manifest at the root of a site (e.g. example.com/llms.txt) that lists the URLs an LLM should prefer when answering questions about the site. Proposed by Jeremy Howard in September 2024. As of May 2026 Shopify ships no native llms.txt feature.

The spec is permissive: one required H1 (the site name), an optional blockquote one-line summary, an optional prose section, and one or more H2 sections each listing markdown-formatted links to URLs the publisher wants the LLM to prefer. A companion file at /llms-full.txt can contain a fuller content dump (often a concatenated markdown export of every key page) for use cases that want context, not just URLs.

What the file looks like

A minimal llms.txt is roughly five lines. A complete one is between 30 and 200 lines depending on site size. The structural skeleton: H1 site name, blockquote one-liner, optional context paragraph, then H2 sections like 'Products', 'Policies', 'Articles' with bulleted markdown links to the URLs an LLM should prefer.

An example skeleton for a Shopify store: # Acme Outdoor on line one, then a blank line, then > Acme Outdoor sells minimalist hiking gear for distance hikers., then a paragraph of plain-text context, then ## Products followed by a bulleted list of links to the key product pages, then ## Policies with links to shipping, returns, and FAQ pages. Each link is markdown-formatted with an inline summary. The whole file is human-readable; that is the point.

Where the proposal comes from

Jeremy Howard (cofounder of fast.ai, now at Answer.AI) proposed llms.txt on 3 September 2024 in a blog post and at llmstxt.org. The motivation: LLMs spend most of their context window reading content not intended for them — sidebars, footers, cookie banners — and a publisher-curated manifest of canonical URLs would let an LLM answer site-specific questions more accurately and more cheaply.

The spec is intentionally lightweight1. It does not require structured data; it does not require schema validation; it has no consumer-side enforcement. The trade-off is that adoption is voluntary on both ends — publishers must ship the file, and LLM operators must choose to read it. The intentional design parallel is robots.txt: a polite publisher-side convention, not an enforced protocol.

Adoption status in 2026

Publisher adoption: substantial in developer-tools and AI-infrastructure (Anthropic, Cloudflare, Perplexity, Hugging Face, Vercel, Supabase). Publisher adoption in mainstream ecommerce: thin. Consumer adoption (AI engines reading third-party llms.txt at answer time): unconfirmed for ChatGPT, Perplexity, Claude, Gemini, AI Overviews.

The honest position for a Shopify owner: shipping llms.txt costs almost nothing once you know the workaround, and the downside is zero. The upside is uncertain but plausibly real, particularly for Perplexity (which has shipped publisher-facing tooling that suggests it cares about publisher-side signals more than ChatGPT does). We recommend shipping it; we do not promise it changes anything.

llms.txt on Shopify specifically

Shopify does not ship a native llms.txt feature in May 2026. The dev docs templates list contains robots.txt.liquid but no llms.txt.liquid; the SEO overview page enumerates sitemap.xml and robots.txt but not llms.txt. Merchants who want llms.txt use one of two workarounds: a third-party Shopify app that writes the file, or a DNS-level redirect on the apex domain.

The third-party-app pattern: install a Shopify app that takes content input from the merchant and serves the file at /llms.txt via a Shopify-routed proxy. The DNS pattern: configure your DNS provider or Cloudflare worker to serve /llms.txt from a separate static origin (S3, GitHub Pages, Cloudflare R2) while keeping the rest of the domain routed through Shopify. The full install lives in Pillar 2 — Cluster 2E llms.txt on Shopify.

llms.txt sits inside the AI-search infrastructure cluster.

  • AEO: llms.txt is one publisher-side AEO tactic.
  • GEO: AEO's umbrella discipline.
  • robots.txt.liquid: the sibling Shopify file. robots is consumer-side bot policy; llms is publisher-side LLM hints.
  • Cluster 2E: the full install treatment for Shopify.

Keep reading