Trader Information
Back to topOverview
Back to topAI Discovery prepares your Magento store to be understood and cited by AI-powered search tools, chatbots, and large language models (LLMs). As shopping increasingly starts inside AI assistants rather than traditional search engines, stores that expose clean, structured, machine-readable information have a growing advantage in visibility and citation accuracy.
This extension automatically generates industry-standard llms.txt and llms-full.txt discovery files, and publishes JSON-LD structured data endpoints for your products, categories, and CMS pages — all without altering your existing storefront URLs, theme, or SEO setup.
It is built for merchants and agencies who want to future-proof their store's discoverability for AI-driven shopping experiences, including AI search assistants, answer engines, and LLM-based product research tools, without manually maintaining separate data feeds.
No design or template changes are required. The extension works entirely in the background through configuration, scheduled generation, and dedicated data endpoints.
Key Features
- Automatic llms.txt Generation: Generates a standards-compliant
llms.txtfile at the store root, summarizing your store's identity, categories, products, and content in a concise, LLM-friendly Markdown format. - Automatic llms-full.txt Generation: Generates a companion
llms-full.txtfile containing expanded, detailed entries for categories, products, and CMS pages — including descriptions, URLs, pricing, SKUs, and variant counts — for AI systems that require deeper context. - JSON Structured Catalog Endpoints: Automatically exposes JSON-LD (schema.org) structured data for products, categories, and CMS pages at a parallel
.jsonURL for every existing.htmlpage (for example,/product-name.jsonalongside/product-name.html), without replacing or redirecting any existing URL. - Rich Schema.org Product Markup: Simple, configurable, and bundle products are each converted into accurate schema.org types (
Product,ProductGroup,TypeAndQuantityNode), including pricing, availability, images, SKUs, and configurable variants with their distinguishing attributes. - Category and CMS Page Structured Data: Categories are published as
CollectionPageobjects listing their in-stock products as anItemList, while CMS pages are published as cleaned, plain-textWebPageentries — giving AI crawlers structured context beyond raw HTML. - Configurable Content Sections: Store owners can independently toggle which sections appear in each generated file: base store information, categories, products, and CMS pages, for both
llms.txtandllms-full.txt. - Store Information Injection: Automatically pulls store name, phone number, hours, address, country/region, postal code, and VAT number from core Magento Store Information settings, plus a custom additional description field, into the generated files.
- Flexible Generation Methods: Choose between automatic generation on a configurable cron schedule or on-demand generation via a dedicated CLI command — giving control over server load and update frequency.
- Dedicated CLI Command: Includes a console command to manually trigger generation of
llms.txtand/orllms-full.txton demand, independent of the cron schedule, ideal for deployment pipelines or manual refreshes. - AI Resources Cross-Linking: When enabled,
llms.txtautomatically links to the full-content file and to the individual JSON structured data endpoints for categories, products, and CMS pages, creating a discoverable network of machine-readable resources for AI crawlers.
Benefits
- Improve your store's visibility and accuracy of citation inside AI search assistants and LLM-based shopping tools.
- Keep AI-facing data automatically synchronized with your live catalog and content, with no manual feed maintenance.
- Adopt the emerging llms.txt/llms-full.txt standard without custom development.
- Add machine-readable structured data without touching theme templates or existing SEO-optimized URLs.
- Reduce the risk of AI systems returning outdated or inaccurate product information about your store.
- Gain full control over what information is disclosed to AI crawlers through granular, section-level configuration.
Configuration
All settings are managed from Stores > Configuration > Horizon > AI Discovery and can be applied per website or store view. A master toggle enables or disables the entire module. Separate sections independently control llms.txt, llms-full.txt, and the JSON Structured Catalog. For each of llms.txt and llms-full.txt, merchants can enable/disable generation, choose between manual (CLI) or automatic (cron) generation, set a custom cron expression, and toggle inclusion of base store information (plus a custom additional description), categories, products, and CMS pages. The JSON Structured Catalog can be enabled independently to expose .json structured data endpoints alongside existing catalog and content URLs.
Compatibility
- Installed via Composer as a standard Magento 2 module.
- Requires PHP 7.2 or later.
- Depends on the
horizon/module-basepackage. - Configuration supports store-view and website scope, enabling multi-store setups.
- Structured data generation respects per-store base URLs and currency settings.
Use Cases
- Merchants wanting their product catalog accurately represented in AI shopping assistants and chatbots.
- Stores optimizing for emerging "AI SEO" / Generative Engine Optimization (GEO) practices alongside traditional SEO.
- Agencies deploying a standardized, repeatable way to expose llms.txt across multiple client stores.
- B2B or B2C catalogs with configurable and bundle products that need accurate variant and pricing data exposed to AI crawlers.
- Content-rich stores wanting CMS pages included in AI-readable discovery files.
- Development teams wanting scriptable, CLI-driven generation as part of deployment or content-refresh workflows.
Technical Highlights
- Dedicated admin configuration section with store/website scope support
- Custom ACL resources for configuration access control
- Custom admin menu entry under a shared "Horizon" parent menu
- Two scheduled cron jobs with independently configurable expressions
- Custom CLI command (
horizon:ai-discovery:generate) for manual generation - Custom frontend router and controller serving JSON-LD structured data at
.jsonURLs - Schema.org-compliant JSON-LD formatters for products, categories, and CMS pages
- Multi-store/multi-website scoped configuration
Why Choose This Extension?
AI Discovery gives Magento merchants a straightforward, standards-based way to make their catalog and content legible to AI search tools and LLMs — combining automated llms.txt/llms-full.txt generation with schema.org JSON-LD endpoints, all managed through simple, scoped configuration and without disrupting existing storefront URLs or SEO.
Technical Specifications
Back to topSeller profile
Seller contact
Current Version
1.0.2
Adobe Commerce platform compatibility
Adobe Commerce (cloud): 2.4 (current)
Adobe Commerce (on-prem): 2.4 (current)
Magento Open Source: 2.4 (current)
Type
Stable Build
Updated
28 September, 2026
Categories
Extensions, Marketing, SEO/SEM, Marketing Automation
Supported Browsers
Chrome, Firefox, Opera, Safari, Edge, IE
Documentation
License Type
Open Software License 3.0 (OSL-3.0)
Policy
Quality Report
Back to topAll tests were conducted on the latest versions of Adobe Commerce that existed for the compatible release lines at the moment of the extension submission. Latest versions of all other software were used, as applicable.
Release Notes
Back to top1.0.2:
- Compatible with Adobe Commerce (cloud) : 2.4
- Compatible with Adobe Commerce (on-prem) : 2.4
- Compatible with Magento Open Source : 2.4
- Stability: Stable Build
-
Description:
- Fixed ACL configuration
- Added module manifest
1.0.1:
- Compatible with Adobe Commerce (cloud) : 2.4
- Compatible with Adobe Commerce (on-prem) : 2.4
- Compatible with Magento Open Source : 2.4
- Stability: Stable Build
-
Description:
Initial Release
Support
Back to topThe best place to start if you need help with a specific extension is to contact the developer. All Adobe Commerce developers have both a contact email and a support email listed.
Contact Vendor