> 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.md).

# Application Examples

These cases show how to combine conversations, Agents, knowledge bases, notes, drawings, translation, channels, scheduled tasks, and multiple windows into workflows that can truly be delivered. The configurations in the cases are starting points; in real use, they still need to be adjusted according to data sensitivity, usage, and team rules.

<figure><img src="/files/97733abedf6794d6d01fb339d39345a4cb902475" alt="从人工跑通到沉淀方法、连接外部能力和自动运行的工作流成熟路径图"><figcaption><p>First run it through manually with real materials, then gradually add the knowledge base, skills, MCP, channels, and scheduled tasks.</p></figcaption></figure>

## Choose a case

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Multi-model research review</strong></td><td>Internal materials, external sources, and conflict checking</td><td><a href="/pages/73a63a1c503b0af516de753a69f29cb645b6d185">/pages/73a63a1c503b0af516de753a69f29cb645b6d185</a></td></tr><tr><td><strong>Long document review</strong></td><td>Check by chapter and generate a revised draft</td><td><a href="/pages/3bde95fd5111cf06d5bef6719a313f0b837c1256">/pages/3bde95fd5111cf06d5bef6719a313f0b837c1256</a></td></tr><tr><td><strong>Agent project file delivery</strong></td><td>Control the directory, permissions, and scope of deliverables</td><td><a href="/pages/da9e39fef32a523656ad31060028a995d3b3cfe9">/pages/da9e39fef32a523656ad31060028a995d3b3cfe9</a></td></tr><tr><td><strong>Brand illustration kit</strong></td><td>From visual direction to multi-size image generation</td><td><a href="/pages/e3508dffb0d014d64493c48c5cc7a75fbdf3fe73">/pages/e3508dffb0d014d64493c48c5cc7a75fbdf3fe73</a></td></tr><tr><td><strong>Private knowledge base Q&#x26;A</strong></td><td>Limit the scope of materials and refuse to guess</td><td><a href="/pages/d0390436a9bb64a9852831954a0d11f0ab22f76e">/pages/d0390436a9bb64a9852831954a0d11f0ab22f76e</a></td></tr><tr><td><strong>Generate a weekly report from notes</strong></td><td>From daily records to a verifiable weekly report</td><td><a href="/pages/2a695dca728b041c332bbcab869fa2c1c2731a23">/pages/2a695dca728b041c332bbcab869fa2c1c2731a23</a></td></tr><tr><td><strong>Multilingual material organization</strong></td><td>Terminology, OCR, documents, and consistency checks</td><td><a href="/pages/1f8074ea19ef75550e1cc9a99c77805971c69b2c">/pages/1f8074ea19ef75550e1cc9a99c77805971c69b2c</a></td></tr><tr><td><strong>Channels and scheduled daily reports</strong></td><td>Agent, channel, schedule, and run logs</td><td><a href="/pages/4a44f222b305bcf6cb5a82c6865e126634ffaa25">/pages/4a44f222b305bcf6cb5a82c6865e126634ffaa25</a></td></tr><tr><td><strong>Multi-window research workspace</strong></td><td>Keep materials, comparisons, and execution tasks at the same time</td><td><a href="/pages/39667cbaa83cbd6f4fba1517639d6fbd7c4bf5cb">/pages/39667cbaa83cbd6f4fba1517639d6fbd7c4bf5cb</a></td></tr></tbody></table>

## General setup sequence

<figure><img src="/files/aecf93d13d04d1712557ff1141528696395346ee" alt="Agent 工作区用于组合任务、文件、工具和交付结果"><figcaption><p>Cases are not a set of isolated settings, but a complete workflow from input, execution, review, to delivery.</p></figcaption></figure>

## Choose a case by task

| Your task                                                 | Recommended first                       | Core capabilities                     |
| --------------------------------------------------------- | --------------------------------------- | ------------------------------------- |
| Compare viewpoints and preserve the research process      | \[Multi-model research review]          | Conversation, branches, notes         |
| Review large amounts of material and output opinions      | \[Long document review]                 | Agent, working directory, files       |
| Deliver project documents and outputs                     | \[Agent project file delivery]          | Agent, state, files                   |
| Generate a set of images with a consistent style          | \[Brand illustration kit]               | Agent drawing, drawing templates      |
| Answer only based on internal materials                   | \[Private knowledge base Q\&A]          | Knowledge base, recall testing, Agent |
| Organize weekly reports from scattered notes              | \[Generate a weekly report from notes]  | Notes, Agent, files                   |
| Organize multilingual files                               | \[Multilingual material organization]   | Translation, Agent, working directory |
| Send fixed reports on a schedule                          | \[Channels and scheduled daily reports] | Agent, channel, scheduled tasks       |
| Observe materials and long-running tasks at the same time | \[Multi-window research workspace]      | Tabs, multiple windows, global search |

{% stepper %}
{% step %}

### 1. First define the deliverable

Explain which final file, table, image, or message you need, and how to determine it is complete.
{% endstep %}

{% step %}

### 2. Manually run it through in \[Work]

Verify whether the model, prompts, working directory, and materials are sufficient. Check approved actions one by one.
{% endstep %}

{% step %}

### 3. Only consolidate the stable parts

Turn repeated steps into skills, put long-term materials into the knowledge base, and keep temporary requirements in the task prompt.
{% endstep %}

{% step %}

### 4. Add external connections and automation at the end

After completing one manual acceptance check, then connect MCP, channels, or scheduled tasks, and keep a manual fallback path for failures.
{% endstep %}
{% endstepper %}


---

# 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.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.