llms.txt is a plain-text Markdown file placed at the root of a website (for example, https://yourstore.com/llms.txt) that points large language models and AI agents to the site's most important, machine-readable content. It acts as a curated map so agents don't have to guess or scrape blindly.

Is llms.txt the same as robots.txt?

No. robots.txt tells crawlers what they may or may not access. llms.txt does the opposite job: it proactively points AI agents toward the content you most want them to use, and links to clean, structured resources like feeds and documentation.

Do AI models actually use llms.txt?

Adoption is still emerging and not every model reads it yet. But it is low-cost to publish, increasingly recognized, and it complements proven signals like structured data and sitemaps. For ecommerce it offers a clean way to expose product feeds to agents that do consume it.

Guides / What is llms.txt

What Is llms.txt? A Guide for Ecommerce Stores

As shoppers increasingly ask AI assistants instead of search engines, a new file is showing up at the root of forward-looking websites: llms.txt. Here’s what it is, how it differs from robots.txt, and how an ecommerce store should use it.

The one-sentence definition

llms.txt is a plain-text file at your domain root that gives AI agents a curated map of your most important, machine-readable content. Think of it as a friendly index written for language models rather than humans.

Why it exists

Large language models and AI answer engines don’t browse the way people do. They have limited context, they often can’t run JavaScript, and scraping a sprawling, template-heavy storefront is noisy and unreliable. llms.txt solves this by pointing agents straight at clean sources — documentation, product feeds, key pages — so they spend their limited attention on the content that matters.

llms.txt vs. robots.txt vs. sitemap.xml

File	Audience	Job
`robots.txt`	Crawlers	What they may or may not access
`sitemap.xml`	Search engines	A list of every URL to index
`llms.txt`	AI agents / LLMs	A curated map of your best, structured content

They’re complementary. robots.txt sets permissions, sitemap.xml lists everything, and llms.txt highlights what’s most useful and where the machine-readable versions live.

What an ecommerce llms.txt should contain

The format is simple Markdown: an H1 with your site name, a short summary, then sections of links. For a store, the highest-value links are your catalog feeds and product endpoints:

# Your Store

> Public, read-only product catalog for AI agents and answer engines.
> Private customer and order data is never exposed.

## Product feeds
- [Full catalog (JSON)](https://yourstore.com/api/products.json)
- [Full catalog (XML)](https://yourstore.com/api/products.xml)

## Single product
- By SKU: https://yourstore.com/api/products/{sku}.json
- By slug: https://yourstore.com/api/products/by-slug/{slug}.json

## About
- [Shipping & returns](https://yourstore.com/shipping/)
- [Contact](https://yourstore.com/contact/)

Best practices

Link to structured data, not just pages. A JSON feed is worth more to an agent than ten HTML pages.
Keep it public and safe. Only reference catalog and informational resources — never anything behind authentication.
Keep it current. A stale map is worse than none; point to live endpoints that always reflect your catalog.
Don’t rely on it alone. Pair it with solid Product schema and a clean sitemap.

How this works in WooCommerce

WordPress and WooCommerce don’t generate an llms.txt for you. You can write one by hand, but the links inside it need to point at real, machine-readable catalog data — which WooCommerce also doesn’t expose publicly by default. Easy Woo API generates the llms.txt and the JSON/XML feeds and product endpoints it points to, so the map and the destinations stay in sync automatically.

Go deeper: read the full guide to WooCommerce AI search visibility for the complete AEO checklist.