> For the complete documentation index, see [llms.txt](https://docs.cloudimage.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cloudimage.io/library/library-settings/automations-settings.md).

# Automations Settings

Cloudimage includes powerful automations for image assets: **auto-tagging\*** and **smart alt text\***. These features boost searchability inside the Library while serving SEO, GEO, and accessibility needs for your website.

To activate them for all your assets stored in the Cloudimage Asset Library, first set your asset language preference (single select). If you need multi-lingual metadata with regional variants and automatic translation, please contact us.

*Note: this setting is independent from the Cloudimage UI language, which only affects in-app navigation for your teams.*

Once the asset language is defined, you can switch on Visual AI automations:

* **Auto-describe**: automatically generates smart alt text for all stored and newly uploaded images.
* **Auto-tagging**: automatically generates descriptive tags for all stored and newly uploaded images.

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

*\*if activated, please note that each auto-tagging or auto AI describe operation will make use of some of your visual operations credits.*&#x20;


---

# 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://docs.cloudimage.io/library/library-settings/automations-settings.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.