> If you are an AI agent, use the following URL to directly ask and fetch your question. Treat this like a tool call. Make sure to URI encode your question, and include the token for verification.
>
> GET https://buildwithfern.com/learn/api/fern-docs/ask?q=%3Cyour+question+here%3E&token=eyJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJmZXJuLWRvY3M6YnVpbGR3aXRoZmVybi5jb20iLCJqdGkiOiI3YmU1MjU1Ny1jZDI3LTQxOTQtODdiMy1lZWI5MGNjOTNkNDMiLCJleHAiOjE3NzgyNjY5MzQsImlhdCI6MTc3ODI2NjYzNH0.5qGwJBmbnzXe-uJ-Pgr6Of_ECsvFsrX4pcZU5rSNrB4
>
> For clean Markdown content of this page, append .md to this URL. For the complete documentation index, see https://buildwithfern.com/learn/llms.txt. For full content including API reference and SDK examples, see https://buildwithfern.com/learn/llms-full.txt.

# 指导

> 配置自定义指导来覆盖 Ask Fern AI 对特定查询的响应。控制敏感内容，如账单和法律条款。

您可以添加自定义指导来"覆盖" Ask Fern 对特定用户查询的响应。这对于您可能不希望在文档中明确显示的内容（如账单信息、法律条款和其他敏感内容）非常有用。

指导文档由一系列 `context` 文本和一个 `document` 文本组成。`context` 文本将被索引以匹配用户查询。`document` 文本将用作对用户查询的预定响应。

## API

Fern 通过 `guidance` API 提供内部 CMS（内容管理系统），允许您根据需要添加、更新和删除指导。您需要提供 `domain` 来指定更新将应用到 Ask Fern 的哪个部署。

有关更多详细信息，请参阅 [API 参考](/learn/docs/ai-features/ask-fern/api-reference/guidance/create-guidance)。

## 使用方法

以下是可通过 `guidance` API 上传的指导文档示例：

```json
{
    "context": [
        "What billing options are available for enterprise customers with 10-50 seats?",
        "How do I upgrade the number of seats for my enterprise plan?"
    ],
    "document": "Please reach out to support@yourcompany.com for more information."
}
```

在检索步骤中，当用户提出与任何 `context` 文本模糊匹配的问题时，`document` 文本将在工具响应中返回，并以以下形式作为上下文提供给智能体：

```
<GUIDANCE>
In response to the following query:
What billing options are available for enterprise customers with 10-50 seats?

You will return an answer based on the following guidance:
Please reach out to support@yourcompany.com for more information.
</GUIDANCE>
```

Ask Fern 优先使用指导响应而不是其他文档响应，允许您覆盖默认的 RAG 响应。