# Collections ### A Collection is a filtered group of documents that helps you scope how your AI agents access information. Collections allow you to organize your data into logical groups. For example, you might have separate collections for "Product Documentation," "Engineering Design Docs," or "Community Support History." ### How Collections Work In Katara, collections act as a bridge between your organization and your content: * **Organization Scope**: Every collection belongs to a specific [Organization](/about/organizations/manage-your-organization.md). * **AI Context**: When you configure an agent, you can specify which collections it should use as its source of truth. * **Filtering**: Collections help you filter your corpus so your agent doesn't get overwhelmed by irrelevant data. ### Collection Management Collections are often created and populated automatically by [Loader Agents](/about/agents/loaders.md). When you set up a loader, it typically creates a collection to store the documents it imports. * **Owner**: The user who created the collection or the loader that manages it. * **Editors**: Users who can update the collection settings or refresh the data. * **Viewers**: Users who can see the collection metadata. Access to individual documents still depends on each document's own [visibility](/about/corpuses/what-is-a-corpus/visibility.md), [sharing](/about/corpuses/what-is-a-corpus/sharing.md), and [sensitivity classification](/about/corpuses/what-is-a-corpus/sensitivity-classification.md). By default, Organization Admins and Owners have full control over all collections within the organization. --- # Agent Instructions: 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.katara.ai/about/corpuses/what-is-a-corpus/collections.md?ask= ``` 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.