> For the complete documentation index, see [llms.txt](https://helpcenter.channable.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://helpcenter.channable.com/manage-improve-product-data/categorize-products/ai-product-categorization.md).

# AI categorization

Learn how AI categorization assigns products to channel categories and how the experiences differ by channel.

{% hint style="info" %}

#### Who can use this feature

AI product categorization is available from the **Core** **Standard** subscription.
{% endhint %}

#### Jump straight in

{% content-ref url="/spaces/u8whzIfip72Kvn3M1bsc/pages/fXIGImKNxqu4h1kMQIa6" %}
[How to set up AI product categorization](/manage-improve-product-data/categorize-products/ai-product-categorization/how-to-set-up-ai-product-categorization.md)
{% endcontent-ref %}

***

{% columns %}
{% column %}

### AI categorization

**AI product categorization** matches products to likely categories in your channel's category tree.

AI product categorization helps you:

* Categorize products with less manual mapping.
* Use product data to improve category matches.
* Review and correct mappings in the **Categories** step.
  {% endcolumn %}

{% column %}

<figure><img src="https://501928696-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fu8whzIfip72Kvn3M1bsc%2Fuploads%2Fw0ce9HohcBPqIQ8tTnZG%2Fcmiyluq0v7jjy07w6hqooo96d1-ezgif.com-svg-to-png-converter.png?alt=media&amp;token=0cc1e5d8-0d53-4fea-ad36-12ecf2f69f7c" alt="AI product categorization maps imported product data to a channel category tree."><figcaption></figcaption></figure>
{% endcolumn %}
{% endcolumns %}

### How Channable assigns categories

Channable uses your product data to find the most likely category. It shows the results in the channel's **Categories** step.

You can review results, correct individual products, and create category rules. Manual category rules take precedence over AI-assigned categories.

{% hint style="info" %}

#### Example

A `product_category` field contains `Men's clothing > Jeans`. AI categorization uses that value to find the closest channel category.

With Improved AI categorization, add title, description, brand, or product type when the category field lacks detail.
{% endhint %}

### Improved AI categorization

Starting October 13, 2026, new Channable users see [Improved AI categorization](/manage-improve-product-data/categorize-products/ai-product-categorization/how-to-set-up-ai-product-categorization.md#improved-ai-categorization) for [supported channels](#supported-channels-or-improved-ai-categorization). If you are a new user, you can still switch back to [Standard AI categorization](#standard-ai-categorization).

We will then roll out Improved AI categorization to existing users, who can also opt out. Later, Improved AI categorization will become the standard experience for all users.

<details>

<summary>Channels that support improved AI categorization</summary>

{% hint style="info" %}
We will add channels to this list as Improved AI categorization support becomes available.
{% endhint %}

* Google
* Meta
* Amazon
* Bol

</details>

#### About the improved experience

[Improved AI categorization](/manage-improve-product-data/categorize-products/ai-product-categorization/how-to-set-up-ai-product-categorization.md) gives you more control while you work:

* Choose multiple product fields to give AI more context.
* Optionally reuse category mappings from another channel.
* Track categorized and uncategorized items as categorization runs.
* Correct single items or groups of items directly in the categorization overview.

If too few items are categorized, add more product fields and rerun categorization.

### Standard AI categorization

<details>

<summary>Channels that support standard AI categorization</summary>

* Google
* Meta
* Amazon
* Bol
* All channels that use Google Shopping categories
* eBay
* Fashionchick
* Fruugo
* Nextail
* Fonq
* Cdiscount
* Kleding.nl
* Kieskeurig
* Shopalike
* Marktplaats
* Tweedehands.
* Billiger
* Go Banana
* Spartoo
* Stylelight
* Vergelijk
* Winkelstraat.

</details>

#### About the standard experience

[Standard AI categorization](/manage-improve-product-data/categorize-products/ai-product-categorization/how-to-set-up-ai-product-categorization.md#standard-ai-categorization) gives you a familiar, rule-based workflow:

* Choose one product field for automatic categorization.
* Review categorized, manually categorized, excluded, and uncategorized products in separate views.
* Check **Uncategorized items** when AI cannot assign a confident match.

Use category rules to make specific corrections or manage existing mappings.

### Related resources

<details>

<summary>Languages supported for category searches</summary>

* Arabic
* Chinese
* Danish
* Dutch
* English
* French
* German
* Italian
* Japanese
* Polish
* Portuguese
* Russian
* Spanish
* Swedish
* Thai
* Turkish

</details>

{% content-ref url="/spaces/u8whzIfip72Kvn3M1bsc/pages/4ea1283d099caf462be550d2e279a246c7b77bbe" %}
[Categorization methods](/manage-improve-product-data/categorize-products/categorization-methods.md)
{% endcontent-ref %}

{% content-ref url="/spaces/u8whzIfip72Kvn3M1bsc/pages/fXIGImKNxqu4h1kMQIa6" %}
[How to set up AI product categorization](/manage-improve-product-data/categorize-products/ai-product-categorization/how-to-set-up-ai-product-categorization.md)
{% endcontent-ref %}

{% content-ref url="/spaces/u8whzIfip72Kvn3M1bsc/pages/909f27a16b099b34ceeeeb3d7e3b5671e0dacfb9" %}
[Manual categorization](/manage-improve-product-data/categorize-products/manual-categorization.md)
{% endcontent-ref %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://helpcenter.channable.com/manage-improve-product-data/categorize-products/ai-product-categorization.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.