> 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/generate-with-ai/ai-enriched-attributes/how-to-create-and-use-ai-enriched-attributes.md).
# How to create and use AI generated attributes
Set up AI enriched attributes, filter items, and review generated values before saving them to your project fields.
{% 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 %}
{% hint style="info" icon="lightbulb" %}
#### **Tip**
Check out the [AI enriched attributes webinar](https://app.livestorm.co/p/604ee763-4b5f-4f9b-9e49-8c5be427ce09/live?s=7f2cc82e-2a40-4a95-87bf-480c17144c5d).
{% endhint %}
### :memo-circle-check: Before you start
**You'll need**
* A **Core Plus** or **Core Pro** plan in your [Channable subscription](/account-billing/manage-your-subscription/channables-pricing-plans.md)
* Imported product data in your project
* A unique ID for each item in **\[your project] > Setup > ID fields**
**Good to know**
* AI enriched attributes use your imported data to generate [supported attributes](/manage-improve-product-data/generate-with-ai/ai-enriched-attributes.md#what-type-of-attributes-can-i-generate).
* Save generated values to a new project field to avoid overwriting existing data.
***
### Create a new AI enriched attribute
{% stepper %}
{% step %}
#### Start the attribute setup
1. In your project, go to **Optimize**.
2. Click **+ New AI enriched attribute**.
3. In the popup, select **Attribute**.
4. At **Title**, add a name for your AI enriched attribute.
5. At **Which type of attribute do you want to fill in?**, select an attribute type, such as **Color** or **Age group**.
6. Click **Continue**.
{% endstep %}
{% step %}
#### Configure the attribute settings
1. At **Field to save the generated attribute**, select the project field where you want to save the generated attribute. We recommend [creating a new field](/get-started/getting-started/fields-in-channable/map-and-add-fields.md) to avoid overwriting existing data.
2. At **Output language**, select the output language for the generated attribute. The default option uses the input data language.
3. At **Project fields used to generate attributes**, choose which project fields the AI searches. You can include all fields, specific fields, or all fields except selected fields.
4. Click **Save**.
{% endstep %}
{% endstepper %}
{% hint style="info" %}
#### Note
You can change any of these settings at any time in the **Settings** step.
{% endhint %}
### Filter & preview
{% hint style="info" %}
#### Note
The **Filter** step is similar to [Rule conditions in Channable](/manage-improve-product-data/rules-bulk-edit-and-enrich/how-to-use-conditions-if-in-rules.md).
{% endhint %}
To speed up generation, use a filter to limit the items processed.
{% hint style="info" %}
#### Example
A channel requires a separate color field. A product title contains `Red cotton T-shirt`, but the color field is empty.
Create an AI enriched attribute that searches the `title` field. It extracts `red` and saves the result in a project field.
{% endhint %}
How to set up the filter:
{% stepper %}
{% step %}
#### Set up the filter
1. Set up a filter to target items that are missing an attribute.
2. Next to **IF**, select the dropdown and choose a field.
3. Choose a condition.
4. Click **Save**.
{% endstep %}
{% step %}
#### Review the preview
1. In the **Preview** section, review the randomly selected items.
2. If the items are correct, click **Results**.
{% endstep %}
{% endstepper %}
### Results
{% stepper %}
{% step %}
#### Generate attribute values
1. Click **Generate** to generate values for the selected attribute.
2. In the **Status** column, find generated values marked “Needs review”.
{% endstep %}
{% step %}
#### Review text attribute values
Use this process for attributes such as ‘age group’, ‘brand’, ‘color’, ‘gender’, ‘key words’, and ‘material’.
1. Review each generated value. Select **Approve** or **Reject**.
2. In the ‘Value’ column, hover over an attribute and click **Edit** to change it.
3. In the ‘Items’ column, click **View** to review individual items.
4. Next to the ‘Generated \[value]’ column, click **Approve all** or **Reject all** to review a group.
5. Click **Back** to return to **Results**.
{% endstep %}
{% step %}
#### Review measurement attribute values
Use this process for attributes such as ‘depth’, ‘diameter’, ‘height’, ’length’, ‘quantity’, ‘volume’, ‘weight’, and ‘width’.
1. Review individual values by clicking either **Approve** or **Reject**, or review all of the values by clicking **Approve all** or **Reject all**.
2. Click **Back** to return to **Results**.
{% endstep %}
{% endstepper %}
After approval, the value appears in the selected project field under **Items**.
{% hint style="info" %}
#### Note
Click the **Approve new items automatically** toggle to approve any new items that get added to your import without reviewing them in the future.
{% endhint %}
To ensure the results are correct, you can check the updated attributes in the specific items in **\[your project] > Items**. Approved values will be available in the field you saved them in (in **Settings**) and can be used anywhere in your Channable project.
{% hint style="warning" %}
#### Important
AI enriched attributes rely on the **unique ID per item** configured in **\[your project] > Setup > ID fields**. If multiple items share the same unique ID, the AI may generate the same attribute values for those items. To avoid this, ensure that each item has a unique ID and ensure the selected fields contain relevant data for the attribute you’re generating values for. [Learn more about unique ID](/get-started/getting-started/fields-in-channable/understanding-a-unique-id.md).
{% endhint %}
---
# 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/generate-with-ai/ai-enriched-attributes/how-to-create-and-use-ai-enriched-attributes.md?ask=&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.
