Related products that fill themselves, and a way to check they help
Most related product blocks are empty or out of date because someone has to fill them product by product. Rules can do the filling; a simple test tells you whether it was worth it.
AI Merchandising & Category Optimizer for Magento 2
Arrange Magento category products using sales, stock, margin and conversion signals. Review the proposed order, pin campaign products, preview the storefront and apply or revert the change. Numerical scoring works without external AI.
- Magento 2.4.6 – 2.4.9
- PHP 8.2 – 8.5
- Hyvä and Luma
- Version 2.0.5
$399
One-off payment, with 12 months of updates.
- 30-Day Money-Back GuaranteeBuy with confidence
- Developer supportHelp from the team behind the code
- 12 months of updatesKeep the versions you receive
What is included
- Install with Composer, or download a zip from your account
- Licence for one production domain, staging and development copies included
No subscription or automatic renewal. Keep using the versions included in your update period. Update and licence details
Key features
- Score per product from sales, revenue, margin, conversion, stock and newness
- "Why here?" explanation for every product
- Findings such as low conversion, hidden gems and buried best sellers
Composer package commercegears/module-ai-merchandising
The category order that worked at launch may now hide a strong seller behind unavailable products. AI Merchandising & Category Optimizer makes that review practical: collect the evidence, propose a new order, inspect the storefront and publish the arrangement your team chooses.
A commercial view of each product
Analyse a category over 30, 60, 90 or 180 days using supported sales, revenue, refunds, salable stock, margin, views, conversion, cart and wishlist signals. Relevant child activity contributes to the parent. Missing costs and views are flagged rather than treated as evidence of poor performance.
The configurable numerical score works locally without an external AI request. Rules can move unavailable products down, give new products exposure and preserve pins. Findings help identify a hidden bestseller, a high-refund item or a heavily viewed product that deserves a content or price review.
Review the order before applying it
The proposal shows current and proposed positions with Why here? explanations. Drag or move products, pin a campaign item and preview the first pages. A temporary signed link shows the proposal on your real Luma or Hyvä category page without caching the preview.
Approve & Apply writes normal Magento category positions and records the previous arrangement. History provides reversion for the latest live application. If category membership changed after analysis, a new analysis is required. Anchor-category application can add direct product assignments; reversion handles those additions.
Build a regular merchandising routine
Run single-category analysis, queue larger selections or enable nightly analysis for selected categories. Fresh proposals wait for review unless you explicitly enable auto-apply. The optional AI layer reviews a configured product summary and writes additional explanations; responses are validated and failures fall back to the numerical order.
Requirements and fit
Magento Open Source or Adobe Commerce 2.4.7–2.4.9, PHP 8.2–8.5, CommerceGears Core and AI Core. Product-view collection is needed for conversion signals; product costs are needed for meaningful margins. Luma and Hyvä storefront preview are supported.
Positions are global across store views, and the result is not personalised per shopper. Very large categories can make the proposal slow to render. The potential-uplift indicator is not a revenue forecast. Use a representative category and compare actual trading journeys after a reviewed change.
Read the AI Merchandising guide or open the admin demo to inspect the proposal, preview and history workflow.
See the workflow
Try the admin demo. Storefront examples are available on the Luma demo and Hyvä demo. Demonstration or offline-test data shows the workflow; evaluate AI matching and forecasts with your own representative catalogue.
Performance signals
- Units, revenue, orders and refund share over selected periods
- Salable stock, including supported MSI stock data
- Cost-based margin with unknown costs identified
- Product views, conversion, wishlist and cart activity
- Supported child-product activity aggregated to the parent
Scoring and findings
- Configurable weights for selling, margin, conversion, stock and newness
- Unavailable products moved down when the rule is enabled
- New-product boost and pinned positions
- Findings for low conversion, high refunds and hidden strong sellers
- Why here? explanations alongside each proposed position
Merchant review
- Current and proposed category order side by side
- Drag, move and pin products before saving the proposal
- Preview the first two pages and a temporary signed storefront link
- Apply normal Magento category positions
- History and reversion of the latest live application
Scheduled review
- Analyse one category or queue a larger selection
- Nightly analysis for chosen categories
- Proposals wait for review by default
- Optional auto-apply is off by default
Optional AI and control
- Core scoring available without an AI provider request
- Optional AI review of a configured top-product summary
- Separate choice for sharing margin information
- Validated responses fall back to numerical scoring when needed
- Shared AI Core budgets, usage and per-module access controls
Questions before you install
Does it change the category as soon as I analyse it?
No. Analysis creates a proposal. The storefront changes when an authorised user applies it; optional auto-apply is off by default.
Does it need an external AI service?
The scoring and review workflow work without AI. The optional explanation/review layer uses your configured provider key and budget through CommerceGears AI Core.
Can each store view have a different product order?
No. Magento category positions are global. The analysis scope can vary, but applying writes positions shared by store views.
Can I restore the old arrangement?
History lets you revert the latest live application to its previous positions. Revert newer applications first. Added direct assignments for anchor categories are also handled.
Is the potential uplift a sales forecast?
No. It is a placement-weighted score indicator. It does not predict or guarantee additional revenue.
-
Strong products where shoppers look
Best sellers below the first page, products without sales or out of stock on the first page and products with low conversion are found and moved, with the reason for every position.
-
You approve, you can undo
Nothing changes on the storefront until you click Approve & Apply. The previous positions are saved, and History restores them exactly with Revert.
-
No AI needed
The order comes from a transparent score with weights you set. Switch on the optional AI layer to have a model review the top products; any problem falls back to the score order.
All features
What is included
Analysis
- Period of 30, 60, 90 or 180 days per store view
- Units sold, revenue, orders, refund share and salable stock
- Margin from the Cost attribute, product views, wishlist and cart adds
- Configurable and grouped children count for the parent
- Score weights you set in the configuration
Rules
- Out-of-stock products last
- Boost for new products
- Pinned products stay where you pinned them
- Products are never removed from the category
Review and apply
- Drag and drop, up and down arrows, pin
- Badges, metrics and a potential uplift indicator
- Signed storefront preview links, valid for one hour and never cached
- Apply to that category only, with History and Revert
- Auto-apply for nightly analyses (off by default)
AI layer (optional)
- AI model reviews the top products and writes short notes
- Anonymised category summary, no customer data
- Costs and margins only shared when you allow it
- AI cost of each run, and an estimate before an AI run
- Budgets managed in CommerceGears AI Core
Related Products
- AI Semantic Search Help shoppers find products by describing what they need. Combine semantic and keyword search, show quick p…
- AI Visual Search & Shop the Look Magento shop by look and AI visual search: shoppers search from a photo, find visually similar products and…
- Layered Navigation Filters that shoppers actually use: several options per filter with correct counts, swatches, a price slide…
- AI Demand Forecast Forecast product demand from sales and stockout history, review stock risks and export purchase suggestions…
Live demo
Try it before you install it
A full Magento store with the module installed, on Luma and on Hyvä. The admin demo signs you in with one click.
Compatibility
Requirements and compatibility
| Magento | 2.4.6 – 2.4.9 |
|---|---|
| Platforms | Magento Open Source and Adobe Commerce (one price) |
| Storefront themes | Luma Blank Hyvä |
| PHP | 8.2 – 8.5 |
| Latest version | 2.0.5 |
| composer.json requires | php ~8.2.0||~8.3.0||~8.4.0||~8.5.0 ext-json * magento/framework ~103.0.6 commercegears/module-core ^2.0 free, installed by Composer with this module commercegears/module-ai-core ^2.0 free, installed by Composer with this module magento/module-backend * magento/module-catalog * magento/module-catalog-inventory * magento/module-config * magento/module-directory * magento/module-indexer * magento/module-sales * magento/module-store * magento/module-ui * magento/module-url-rewrite * magento/module-user * |
Installation
Up and running in minutes
After you buy, create a Composer key in your account. Then, in the root of your Magento project:
-
01Add the repository and your key (once per project)
composer config repositories.commercegears composer https://repo.commercegears.com composer config --auth http-basic.repo.commercegears.com PUBLIC_KEY PRIVATE_KEY
-
02Install the module
composer require commercegears/module-ai-merchandising -
03Enable it
bin/magento setup:upgrade bin/magento setup:di:compile bin/magento setup:static-content:deploy bin/magento cache:flush
The last three are only needed in production mode.
Prefer a zip? Every version you are entitled to can be downloaded from My modules. More about Composer access
User guide
Setting up AI Merchandising & Category Optimizer
The user guide has its own page: how to install AI Merchandising & Category Optimizer, what each option does and how to use it in your store. Written for version 2.0.5; a copy ships with the module.
In the guide
Changelog
Release notes
2.0.5
Latest
- Fix: with "Use AI" set to No, no analysis uses AI any more, also not from the analyse form or the command line.
2.0.4
- Fix: category page links with an invalid or expired preview code are now served from the page cache.
- Fix: categories queued for analysis are no longer analysed twice when cron runs overlap.
2.0.3
- Improvement: compatible with Magento 2.4.6 (PHP 8.2).
2.0.2
- Improvement: user guide screenshots added.
2.0.1
- Improvement: product page details and live demo links
2.0.0
- Improvement: renamed to CommerceGears (new Composer package, admin menu and settings paths)
FAQ
Questions, answered
Something else on your mind? The developers who wrote the module answer before and after you buy.
Ask a question →Already installed it? Open a support ticket
Do I need an AI provider key?
No. The module works fully without AI, with a score from your own sales data and the weights you set. The AI layer is optional: set up a key in CommerceGears > AI Providers & Costs and switch on Use AI in the AI Merchandising settings.
Will it change my category pages on its own?
No. An analysis only creates a proposal. Nothing changes on the storefront until you click Approve & Apply. Nightly analyses also wait for your review, unless you switch on Auto-apply (off by default).
Can I undo an applied order?
Yes. The previous positions are saved with every apply. History lists every apply with Revert, which restores the previous order exactly. Only the newest live order of a category can be reverted, so revert newer ones first.
What data is sent to the AI provider?
An anonymised summary of the category and its top products. No customer data is sent, and costs and margins only when Share Margins with AI is switched on.
Why do conversion figures show no values?
Magento must collect product views: Stores > Configuration > General > Reports > General Options > Enable Reports = Yes and Product View = Yes.
What if my products have no cost?
Fill in the Cost attribute (Advanced Pricing) for margins. Products without a cost show "margin unknown" and count as the category average.
Can each store view have its own order?
No. Category positions are the same for all store views in Magento, so an applied order is used by every store view.
Which Magento and PHP versions are supported?
Magento Open Source and Adobe Commerce 2.4.6 to 2.4.9 with PHP 8.2 to 8.5 (Magento 2.4.6: PHP 8.2), Luma and Hyvä. Multi-Source Inventory is optional.
Support
Help from the developers who wrote it
From the blog
Guides and articles
-
-
Magento AI Semantic Search: help shoppers find products in their own words
Customers describe what they need, not always what your catalogue calls it. See 12 example searches and how semantic search works alongside Magento's existing results.
-
Magento AI Merchandising: organise category pages around how your range sells
Bring selling, availability and margin into the category order. Review a proposed arrangement, protect campaign positions and keep a route back to the previous order.
-
Magento AI Demand Forecast: plan reorders, stock risk and price decisions
See what may run out, what to buy and which slow movers deserve review. Forecasts run locally; optional AI explains the numbers rather than replacing them.
-
Your best seller may look quiet because you keep running out
No sales can mean no demand, or no stock. Alert requests help separate the two, provided you treat them as interest rather than guaranteed orders.