> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/build-and-improve/intelligence/files.md).

# Files

Files are Project working material available to the Agent and other configured capabilities. Use Files for documents, spreadsheets, PDFs, images and other artefacts that need to be read, compared, transformed or used as evidence during operational work.

Project members can read Files. Operators, Builders and Owners can upload files and manage folders and items, making Files the most operator-accessible Intelligence surface.

## The Files surface

The Project Files view behaves like a working folder. You can search within the current folder, switch between grid and list views, and organise material into folders. Operators and above can create folders and upload new files.

![A populated Project Files view showing folders, files, search, view controls, New Folder and Upload.](https://3370306531-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlgSglJDQZxDZdn20CUcl%2Fuploads%2FiknAH10qMDMRXef9zOQq%2Ffiles-populated-grid-technivorm.png?alt=media)

The **Filter** control is about provenance rather than file type. Depending on the Project's contents, you can narrow files by source, uploader or originating session, and identify files that are **Remembered** or are saved Agent **Artefacts**. When a provenance filter is active, search can cover matching files across the Project rather than only the current folder.

![The Files provenance filter with Source, Uploaded by, Remembered and Artefacts options.](https://3370306531-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlgSglJDQZxDZdn20CUcl%2Fuploads%2FyHo7FXHJstlKKmRqFAnm%2Ffiles-filter-provenance-technivorm.png?alt=media)

For an individual file, the current actions are **Download**, **Rename**, **Move to**, **Add to Favourites** and **Delete**. The Files page does not currently open or preview file contents. Previewing a generated artefact belongs to the Agent session experience, not this inventory surface.

![The current per-file actions menu showing Download, Rename, Move to, Add to Favourites and Delete.](https://3370306531-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FlgSglJDQZxDZdn20CUcl%2Fuploads%2F9rwk0XIVfN0HrRvTnSm6%2Ffiles-item-actions-menu-technivorm.png?alt=media)

Folders are useful for organisation, but folder placement does not itself tell the Agent how authoritative a file is.

## Files can play different roles

A file may be:

* **input** to a piece of work;
* **evidence** supporting a decision;
* **reference material** used repeatedly;
* **output** generated during Agent or Workflow work and saved into the Project.

Agent-generated output that is promoted into Project Files can be identified as an artefact. A **Remembered** file is one that has been ingested into Memory; it is not a manual trust or approval flag.

Make the role of important files clear in the surrounding Skill, Workflow or Project setup where it matters.

## Choose a more durable home when appropriate

A file is not automatically authoritative just because it exists in the Project.

For long-lived governed reference material, consider **Knowledge Bases**. For structured data that needs to be maintained and reused, consider **Tables**. For exact live records, keep the source system authoritative.

Session working files are separate from this Project inventory. For session-specific uploads, generated-file preview and save-to-Project behaviour, use the Agent file and session documentation.


---

# 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.lleverage.ai/build-and-improve/intelligence/files.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.
