> For the complete documentation index, see [llms.txt](https://docs.uptiq.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.uptiq.ai/document-ai/get-started/workspace.md).

# Workspace

Workspace combines two areas, both reachable from the sidebar:

* **Home**: a dashboard of processing metrics and account activity
* **Gallery**: a tool for organizing documents into named collections.

This page covers Workspace behavior and access.

### Navigate Document AI

* **Process documents** — use Document Classification, Document Extraction, and Fraud Detection.
* **Generate documents** — use Document Generation.
* **Understand supported schemas** — use Document Types.
* **Look up terminology** — use [Glossary](/document-ai/getting-started/glossary.md) for shared Document AI terms, roles, statuses, and workflow language.

| Capability                    | Description                                                                                              |
| ----------------------------- | -------------------------------------------------------------------------------------------------------- |
| Home metrics                  | Credit Balance, In-flight, Failed, Avg time, Webhooks, and Docs processed                                |
| Credit balance                | Available balance, shown as the first metric tile on Home                                                |
| Date range                    | Scope Home to a reporting period, and refresh the figures on demand                                      |
| Active runs / Recent activity | Live view of in-progress runs and recent account activity, with **Start extraction** when there are none |
| Pipeline health               | Processed/Processing/Pending/Failed counts, extraction queue and webhook progress, processor status      |
| Collection creation           | Create a named collection with an optional description and one of 6 colors                               |
| Collection hierarchy          | Organize a collection into nested directories or books                                                   |
| Document tagging              | Tag extraction documents into a collection from the Extractions page                                     |
| Search                        | Search collections by name                                                                               |

#### Home

1. **Land on Home** — see credit balance, processing metrics, pipeline health, active runs, and recent activity for the account.
2. **Jump in** — use **New Document** in the sidebar to start a job, or **Start extraction** from Active runs. The sidebar's Capabilities and Platform groups reach every other area directly.

#### Gallery

1. **Create a collection** — from Gallery, click **New Collection**. Name it (required), and optionally add a description and pick a color.
2. **Organize** (optional) — open the collection and click **New directory or book** to add a nested Directory or Book, each with its own name, description, and color.
3. **Tag documents** — collections don't have an upload or attach control of their own; documents are tagged into a collection from the Extractions page.
4. **Browse** — view a collection's contents, filtered by **All descendants** or **Direct only**. Each collection card shows its document count and creation date.
5. **Edit a collection** — open it and click **Edit** to change its name, description, or color.
6. **Remove a collection** — open it and click **Delete**. This deletes immediately with no confirmation prompt.


---

# 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.uptiq.ai/document-ai/get-started/workspace.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.