> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/docs/en-us/advanced-basic/cases/multi-window-research.md).

# Multi-window Research Workbench

Researchers need to keep materials and model comparisons on one hand, while letting the Agent organize files and generate reports on the other. After splitting the research task into a separate window, the main window can continue looking up information without interrupting the Agent’s state.

## Recommended layout

* Main window: keep the materials conversation and global search;
* Separate window: open the research Agent task and pin it on top;
* Second tab: open the knowledge base or notes to check the original materials at any time.

<figure><img src="/files/6e480690b987061aa8346a25a82a2b1637d647d2" alt="对话中的多模型选择入口"><figcaption><p>The main window keeps multi-model comparison, while the separate window continues running the research Agent.</p></figcaption></figure>

## Workflow

{% stepper %}
{% step %}

### 1. Compare the research question in \[Conversation]

Use multi-model comparison to find consensus, conflicts, and items that still need verification; do not rush to generate the final report.
{% endstep %}

{% step %}

### 2. Prepare a directory for the research Agent

Separate the original materials from the output directory, bind the relevant knowledge base, and require external information to keep links.
{% endstep %}

{% step %}

### 3. Split the task into a separate window

Right-click the Agent tab and choose \[Open in new window]; use window pinning when needed. The main window continues looking up information without interrupting the Agent’s state.
{% endstep %}

{% step %}

### 4. Summarize and review

Check the report in \[Files] on the right side of the Agent, and open the original conversation in the main window to verify conflicts. In the end, keep only conclusions that can be traced back to the materials or sources.
{% endstep %}
{% endstepper %}

<figure><img src="/files/5917e805cd6f5a67d5983714f93235f949473024" alt="标签页菜单中的从新窗口打开操作"><figcaption><p>Split the Agent task into a separate window from the tab menu.</p></figcaption></figure>

<figure><img src="https://3562065924-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F0Ut5BptC3t8CtSU1UWpM%2Fuploads%2Fgit-blob-44f5c55e3e8d1d1d728067775cc8a07ccfb3f3cc%2Fcherry-v2-guide-case-multi-window-research.png?alt=media" alt="从主窗口拆出的独立 Cherry Studio 窗口中仍然显示完整的发布方案评审结果"><figcaption><p>① The separate window keeps the original question; ② the results and follow-up actions are fully preserved, and the main window can continue looking up information or organizing notes.</p></figcaption></figure>

## Recommended combination and completion criteria

| Window              | Suggested content                                                                                                                         |
| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
| Main window         | Materials conversation, global search, and notes                                                                                          |
| Separate window     | One running Agent task                                                                                                                    |
| Pinned tabs         | The project's most frequently used knowledge base or task                                                                                 |
| Completion criteria | Source materials, task status, and final notes can correspond to one another; after the task ends, the window has been restored or closed |

Suitable for research that requires continuous monitoring of long-running tasks; not recommended to open many windows at the same time just to 'look more professional.'

{% hint style="info" %}
Multi-window only changes the display position; it does not create a new account or an isolated space. The data and permissions for the same task remain the same.
{% endhint %}


---

# 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.cherryai.com.cn/docs/en-us/advanced-basic/cases/multi-window-research.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.