> For the complete documentation index, see [llms.txt](https://docs.euno.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.euno.ai/using-euno/metadata-activation/metadata-tags/creating-metadata-tags-with-ai.md).

# Create and Update Metadata Tags with Euno AI

Use Euno AI to design, preview, create, and update metadata tags in natural language. Euno translates the business meaning of a tag into its type and EQL logic, then shows the exact plan before saving it.

## Create a Tag

Open **AI Assistant** and describe the tag you want. You can also start with `/tags` to explicitly use the metadata-tag workflow.

> `/tags Create a single-select certification tag for dashboards in the universal domain. Use certified, draft, and deprecated as the values. Preview it and request approval.`

Include the domain, target resources, values, thresholds, or rules when you know them. You can also specify the display name, description, group, visibility, and whether the tag is shared. Euno may ask questions when important details are unclear. If a tag with the same EQL name already exists, Euno reports it instead of creating a duplicate.

## Review and Approve

Before saving a create or update, Euno:

1. Inspects the tags and domains available to your active persona.
2. Validates the proposed configuration and previews its effect.
3. Shows an approval card with the proposed tag details and logic.
4. Waits for you to select **Approve** or **Reject**.

Select **Approve** to save the displayed plan. Select **Reject** to save nothing. You do not need to send a separate confirmation message after the approval card appears.

{% hint style="warning" %}
Review the domain, scope, conditions, values, and visibility before approving. To change the plan, reject it and describe the required change.
{% endhint %}

After a successful save, Euno provides a link to the tag. Active tag values are calculated in the background and may take time to appear on resources.

## Preview Without Saving

Ask for a preview only when you want to validate a plan without opening an approval request:

> `/tags Preview a boolean tag for Tableau dashboards whose name contains "finance". Do not save anything.`

## Update a Tag

Identify the existing tag and describe the change:

> `/tags Update the description and visibility of certification_status. Preview the change and request approval.`

The EQL name, domain, and tag type cannot be changed after creation. To move a tag to another domain, review its values and dependencies, then delete and recreate it. Create a replacement tag to use a different EQL name or type.

## Supported Tags and Previews

Euno AI supports the fixed and active types described in [Metadata Tags](/using-euno/metadata-activation/metadata-tags.md#types-of-metadata-tags), including fixed-tag default values where supported.

Preview details depend on the tag type. Counts and samples include only resources available to your active persona. AI Select previews do not run classification, and Liquid Template previews do not render the template.

Some lineage rules require a hidden boolean helper and a visible tag with readable labels. Euno can present both tags in one plan. Approving saves both; rejecting saves neither.

## Defaults and Permissions

* For newly created tags, the approving user becomes the owner.
* New tags are visible in the Data Model by default. Ask for a hidden tag when needed.
* Available domains and actions depend on your active persona's permissions.
* Account limits and tag validation still apply.

See [Domains](/setup-configuration/domains.md) for domain details. For MCP usage, see the [MCP Setup Guide](/ai/mcp-setup.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, and the optional `goal` query parameter:

```
GET https://docs.euno.ai/using-euno/metadata-activation/metadata-tags/creating-metadata-tags-with-ai.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.