> For the complete documentation index, see [llms.txt](https://docs.3techagency.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.3techagency.com/documentation/work-safely/the-workspace.md).

# The workspace

The seven destinations, their sub-pages, and how Conversations, Playbooks and Task Runs connect.

Everything lives under **WP AI Manager** in the WordPress admin menu. A tab row across the top links seven destinations. On a narrow screen the tab row scrolls, with arrows at each end. Admin notices always appear below the tab row.

| Destination        | What is on it                                                                                                                                                  |
| ------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Home**           | **Needs you** (setup items, reviews, failed runs), **Recent changes** with Undo, **Recent chats and task runs**                                                |
| **AI Chat**        | Conversations, starters, result cards, approvals, the What the AI knows drawer                                                                                 |
| **Playbooks**      | **Library**, **Tasks and runs**, **Skills**, **Prompts**                                                                                                       |
| **Site Knowledge** | **Brand Kit**, **Brand presets**, **Content defaults**, **Context**, **Memory**                                                                                |
| **History**        | Change history with Undo, and **Backups**                                                                                                                      |
| **Integrations**   | **Integrations** status cards, **Advanced tools**, **Page builders**, **Redirects**                                                                            |
| **Settings**       | **Settings** tabs (AI Models, Access, Privacy, Advanced, Onboarding, License), **External MCP**, **MCP log**, **Sandbox**, **Modules**, **Help and changelog** |

The help menu in the top bar links to Ticket Support, Documentation, Community and Tutorials.

## Home

* **Needs you** lists what is blocking you: setup checklist items, Task runs waiting for review ("A scheduled task needs your review"), failed runs and license notices.
* **Recent changes** shows the newest five changes in plain words ("Rewrote the Services page intro", "Page edited: Homepage") with a domain label, age and source (**via Chat** or **via Task**, linking back). **Undo** appears only when the change can still be undone, asks for confirmation, and uses the same rollback as History.
* **Recent chats and task runs** merges your newest conversations and runs by time, with statuses in words such as **Needs your review** or **Finished**.

## The three working objects

| Object           | What it is                                                                                                               | Where you find it                |
| ---------------- | ------------------------------------------------------------------------------------------------------------------------ | -------------------------------- |
| **Conversation** | A Chat thread with its messages, tool events and approvals. Private to its owner.                                        | AI Chat sidebar, Home            |
| **Playbook**     | A reusable job: instructions, inputs, required integrations and the modes it supports.                                   | Playbooks > Library              |
| **Task Run**     | One execution of a Task recipe: status, processed items, proposals, logs and a link to its Conversation for agent Tasks. | Playbooks > Tasks and runs, Home |

Playbook modes connect them:

* **Ask** opens Chat with the playbook's instructions.
* **Guided** collects and validates inputs, then opens Chat.
* **Automate** opens the Task's review screen. You still choose **Run now**, or set a schedule.

Not every playbook has every mode. A greyed-out Automate button says why (for example "Needs SEO") on hover and to screen readers.

## What counts as a result

A model reply is guidance, not proof. Trust:

* successful **tool-result cards** and their preview links
* **Task Run** outcomes and processed counts
* **History** entries

A proposal is not applied until **Apply selected** succeeds. After applying, the proposal list reloads because positions can change; wait for it before selecting more.

Start with [AI Chat](/documentation/workflows/ai-chat.md) or [Playbooks](/documentation/workflows/playbooks.md).


---

# 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://docs.3techagency.com/documentation/work-safely/the-workspace.md?ask=<question>&goal=<user_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.