> 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/optimize-attributes-with-ai/understand-ai-enriched-attributes.md).

# Understand AI enriched attributes

{% hint style="info" %}
**Who can use this feature**

You need the **Core Plus** or **Core Pro** plan in your [Channable subscription](/account-billing/manage-your-subscription/channables-pricing-plans.md) to use this feature.
{% endhint %}

### What are AI enriched attributes?

**AI enriched attributes** help you generate missing product data in **Optimize**.

Channable uses your existing import data to extract or generate attributes such as color, weight, brand, material, or keywords. This means you can fill missing values without building manual rules for every case.

For example, a channel may require a separate color field. If the color only appears in the product title, you can create an AI enriched attribute that searches your title field and saves the result in its own project field.

<figure><img src="/files/cc22fd0c5937c549955bfd93e50edd1239bbdcd8" alt=""><figcaption></figcaption></figure>

### Key terms

* **Input data**: The fields in your import where the value may already exist, such as titles, URLs, or descriptions.
* **Attribute**: A specific product characteristic, such as color, weight, brand, or material.
* **AI enriched attribute**: The generated result, such as `red`, extracted from your existing import data.

### Where AI enriched attributes run

AI enriched attributes run after your import in **Setup**.

This means Channable first imports your product data. After that, you can run AI enrichment in **Optimize** to generate or refine attributes from that imported data.

<figure><img src="/files/11e8541e53cf5fb314427ce5048cb8c6c8a292c7" alt=""><figcaption></figcaption></figure>

Once the enrichment runs, the approved values are added to your import data. You can then use them across the rest of your project workflow, including your channels.

### Supported attributes

These attribute types are currently supported:

* Color
* Weight
* Quantity
* Brand
* Length
* Width
* Height
* Volume
* Material
* Keywords

{% hint style="info" %}
Each attribute is generated from your existing import data. You can also select an output language for translated results.
{% endhint %}

### How AI enriched attributes help

AI enriched attributes help you:

* Fill missing product data faster.
* Improve listing quality across channels.
* Generate keywords for better discoverability.
* Prepare data for international channels with translated output.

### Next steps

* [Create AI enriched attributes](/manage-improve-product-data/optimize-attributes-with-ai/how-to-create-ai-enriched-attributes.md)
* [Generate AI text for titles and descriptions](/manage-improve-product-data/optimize-attributes-with-ai/how-to-use-ai-generated-text.md)


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://helpcenter.channable.com/manage-improve-product-data/optimize-attributes-with-ai/understand-ai-enriched-attributes.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.