Use docs in AI tools

Use this page to connect an AI editor or coding agent to current Adobe Commerce Storefront documentation. With this context, the tool can answer questions about storefront APIs, drop-in versions, and Edge Delivery Services without relying only on general model training.

What you get

Use docs context when you want your AI tool to generate answers based on the storefront documentation you are reading. It helps you:

• Get answers that reflect current storefront documentation instead of older model training.
• Point different AI tools at one shared documentation source.
• Scope a chat to a full export or a single topic export.

Context files

Context files are plain-text exports of this documentation, regenerated each time the site publishes so AI tools always have the latest content.

• Start with llms.txt, the index that links to every export file.
• Full exports contain the entire documentation site in one file.
• Topic exports under _llms-txt/ each cover one subject area. Use them when a tool should not load the entire site.

File	Purpose
llms.txt	Index with an overview and links to every export file.
llms-full.txt	Complete documentation in one file.
llms-small.txt	Same as the full export but without the release changelog, which is very long. Use this when a tool has a context size limit.
_llms-txt/*.txt	Topic exports, such as drop-ins reference, tutorials, and blocks. llms.txt lists every topic export URL.

Some of these files are large. Loading a whole file sends a lot of text into the model at once. When possible, paste a specific page URL from this site into your AI tool so it fetches the live page directly. Live pages include the latest edits, navigation, and diagrams that export files may not have yet. Use export files as a fallback when your tool cannot fetch a URL.

Publish timing

Context files update each time the site publishes. If a page is edited after the last publish, those changes won’t appear in context files until the site publishes again. Because the URLs in your AGENTS.md or CLAUDE.md always point to the same files, your AI tool fetches the latest published version automatically each time it reads the file.

Prerequisites

• Use an AI editor or coding agent that supports project context files, documentation web addresses, or pasted context, such as Cursor, Claude Code, or GitHub Copilot Chat.
• Open a storefront project in that editor. You might have started from the Adobe Commerce boilerplate or added Commerce blocks and drop-ins to your own site.
• For agent-based tools, use AGENTS.md, CLAUDE.md, or an equivalent context file at the project root where you can add the llms.txt web address.

Add context files

For agent-based tools, add the llms.txt URL to a project context file, such as AGENTS.md or CLAUDE.md. The agent can then fetch the index when storefront documentation is relevant. For other tools, paste a bundle web address or file content directly.

Cursor

Create or update AGENTS.md at your project root and add a section that points to the documentation index:

## Adobe Commerce Storefront Documentation

See https://experienceleague.adobe.com/developer/commerce/storefront/llms.txt for Adobe Commerce Storefront documentation.

Cursor agent mode reads AGENTS.md and fetches the index when needed. You can also add this reference to a file under .cursor/rules/ if you prefer a Cursor-specific location.

Claude Code

Create or update CLAUDE.md at your project root and add a line pointing to the documentation index:

See https://experienceleague.adobe.com/developer/commerce/storefront/llms.txt for Adobe Commerce Storefront documentation.

Claude Code fetches the index and linked bundles when the documentation is relevant. To confirm the setup, start a new chat and ask a question this storefront documentation answers, such as a question about a drop-in. If the reply cites or matches those topics, the tool can read the documentation.

Other AI tools

Other AI editors and agents often accept a documentation URL in settings or system prompts.

For tools that support custom context URLs or documentation sources, such as GitHub Copilot Chat or Windsurf, provide this URL below. Tools that implement the llms.txt spec can follow the index to the relevant bundles automatically.

https://experienceleague.adobe.com/developer/commerce/storefront/llms.txt

For tools that do not support URL-based context, paste the content of llms-small.txt or a relevant _llms-txt/*.txt topic bundle directly into the chat or system prompt.

Example prompt

After you add the documentation context, test the connection with a concrete question in chat. You can paste or rewrite the sample below.

Use the Storefront docs. I'm building a product detail page and I want to add a custom 'Add to Wishlist' button in the product details drop-in, below the existing Add to Cart button. How do I use slots to do this?

Check the result

A successful setup produces replies that cite storefront topics, drop-in APIs, or paths that match this documentation. Adapt drop-in names or UI labels if your project differs. Then verify the reply against the live pages.

Keep context focused

• Many paths, blocks, and drop-in examples in this documentation follow the folder layout of the Adobe Commerce boilerplate on GitHub. Keep your storefront project open so suggested paths match your workspace. If your repository layout differs, tell the agent in chat. For example, say when you have merged boilerplate code into an existing site so the agent does not assume default boilerplate folders.
• To scope one reply to a single page, paste the page web address into the same chat. Your persistent context file connection stays in place, and the pasted web address narrows only that exchange.