# Files

The **Files** menu is the centralized repository where you store and organize documents that will be used as a knowledge base by your AI Agents. This is the core of the functionality, ensuring that the AI responds with internal and company-specific information.

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

#### Purpose

The documents uploaded here are processed exclusively by the **"File Reader" Connectors** and can only be accessed by Agents that have the appropriate permission.

* **Governance:** Folder organization allows you to apply access permissions and security restrictions, ensuring that Agents from one department do not access confidential documents from another.
* **Contextual Knowledge:** Enables Agents to answer complex questions about policies, contracts, manuals, and internal data based on your official documentation.

### Organization and Content

The Files screen displays the folder and document structure, similar to a file explorer:

<table><thead><tr><th width="177">Item Type</th><th>Description</th></tr></thead><tbody><tr><td>Folders</td><td>Used to logically organize content (Ex: Administrative Area, HR, G4). Folders are the main way to segregate access by permission.</td></tr><tr><td>Documents</td><td>Individual files (Ex: .doc, .pdf, .docx, .html, .java, .json…) that the AI will read and index.</td></tr></tbody></table>

### How to Manage Your Files

You have the following actions available on this screen:

* **Import Files:** Allows you to upload documents from your machine to the repository.
* **New Folder:** Creates a new folder to organize content and segment permissions.
* **Filters, Select All, Deselect All:** Tools for managing large volumes, facilitating batch actions such as deleting multiple files.

{% hint style="info" %}

### Essential Next Step

After uploading the documents, you must create a **"File Reader" Connector** and link it to the appropriate Agents. Without this link, the Agent will not be able to access or use the documents.
{% endhint %}


---

# 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.poweromni.ai/en/administration-and-configuration/artifacts/files.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.