> For the complete documentation index, see [llms.txt](https://academy.shade.inc/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://academy.shade.inc/ai-tools/custom-and-automated-metadata.md). # Metadata and Custom Fields Metadata for your assets can be created in under the drive settings tab on the left sidebar under your drive. Metadata field creation is separated from your main workspace view to encourage intention behind creating a metadata attribute. Metadata attributes you add to a drive can either be populated manually or populated with AI. {% embed url="" %} {% embed url="" %} ## Creating First Metadata Attribute To create a metadata attribute: * Add a field name * Choose the metadata type: Text, Single-select, Tags, Decimal, Integer, Checkbox, Date, Rating, or Relation. A Relation field links an asset to other assets, people, or any custom object type in the drive. * Choose which types of assets to apply this attribute to (all by default) To create an automated (AI) metadata attribute: * Toggle the **Autofill with AI** field (not available for Date or Relation fields) * Enter a descriptive prompt. AI autofill currently supports images and videos only. * For single-select and multi-select fields, you can turn on **Generate new options with AI** to let the AI add options that don't exist yet Examples of good AI Prompts: “Identify all the jersey numbers that can be seen in the frames of this video” “Determine which one of the shot types best apply to the video or image” “Choose the tags that best apply to the image or video. If a tag is not available, create one. Tags should be 1-2 words long describing a specific object in the video” ## Creating Metadata from Views Metadata attributes can also be created within a list view. This is a spreadsheet-style overview of all the assets in your drive where you can add columns for each metadata attribute within your drive.
If your assets have Relation fields, the **Add column** menu also lists fields from the linked objects. Pick one to add a **Lookup** column that shows that linked field next to each asset. ## Editing Existing Metadata Update aspects of your existing metadata attributes, archive them, or fully delete them. Within the web or desktop app navigate to Settings > scroll down to your drives on the left > expand the options available for the desired drive > click **Metadata** For any custom metadata attribute you’ll notice the following options: ### Edit * **Field name -** the name of your metadata attribute * **Options** (if Tags or Single-select field type) * **Autofill with AI** (not available for Date or Relation fields) * **AI prompt** (if Autofill with AI is enabled) * **Generate new options with AI** (if Autofill with AI is enabled on a Tags or Single-select field type). * **Do you want to rerun and override all cells?** (if Autofill with AI is enabled) - reruns the AI for this field and replaces its existing values * **Description -** description about the field, its intended use, or purpose in your broader workflow * **Lock metadata editing -** when locked, only drive managers and up can edit values for the metadata field ### Archive Disables the field from being usable and visible within the drive, but doesn’t outright delete the field and all values. The field will remain within your drives metadata library and can be reactivated for later use if necessary. ### Delete Permanently deletes the metadata attribute and all values from the drive, and cannot be undone. ## Creating Your First View You can create a new view by pressing the + next to the “Views” tab. After you have named your view and chosen an icon, you will be brought to the view’s page. Start adding metadata attributes by pressing the + on a new column. You can either select an existing metadata attribute or create a new attribute. --- # 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://academy.shade.inc/ai-tools/custom-and-automated-metadata.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.