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

# 歡迎來到 MaiAgent

MaiAgent 技術人員手冊入口：給 IT、開發者與系統整合夥伴的平台部署、身分整合（SSO／SCIM／OAuth）、API 串接與 Agent 技術原理，依產品線找整合方式。

MaiAgent 是企業級 AI Agent 平台，讓企業擁有自己的 AI 核心：以公司資產為基礎，安全治理為邊界。SaaS、雲端、地端與混合雲皆可部署，同一套平台、同一套 API。

這本技術人員手冊寫給 IT 人員、開發者與系統整合夥伴：平台部署、身分整合、API 串接與 Agent 的技術原理。功能操作請看 [使用者手冊](https://docs.maiagent.ai/)。

***

## 依產品線找整合方式 <a href="#integrate-by-product-line" id="integrate-by-product-line"></a>

MaiAgent 有三條產品線，整合的重點各不相同：

| 產品線                         | 你要做的事                          | 從這裡開始                                                                                                                                                                                                                                                        |
| --------------------------- | ------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **MaiAgent Work｜員工生產力**     | 讓組織成員在自家系統裡使用 MaiGPT           | [把 MaiGPT 加進您的系統](https://docs.maiagent.ai/tech/work/maigpt-system-integration-guide.md)                                                                                                                                                                     |
| **MaiAgent Serve｜客戶服務**     | 把 Agent 嵌進網站或產品給您的客戶用、串接既有客服系統 | [軟體廠商整合指南](https://docs.maiagent.ai/tech/serve/vendor-integration-guide.md)、[Web Chat 嵌入與 SDK](https://docs.maiagent.ai/tech/serve/web-chat-sdk.md)、[第三方客服系統串接](https://docs.maiagent.ai/tech/serve/customer-service-system-integration.md)                  |
| **MaiAgent Build｜Agent 建置** | 以 API 建置與呼叫 Agent、串接模型與企業系統    | [API 快速上手](https://docs.maiagent.ai/tech/api-integration/quickstart.md)、[MCP 與外部服務](https://docs.maiagent.ai/tech/mcp/mcp-model-context-protocol.md)、[AI Gateway：OpenAI 相容 API 串接](https://docs.maiagent.ai/tech/ai-gateway/ai-gateway-openai-compatible.md) |

三條線共用的基礎：

* [生成式 AI 快速入門](https://docs.maiagent.ai/tech/quickstart/llm.md)：LLM、RAG、Embedding、Reranker 等基礎概念
* [技術原理](https://docs.maiagent.ai/tech/advanced-genai-tech/system-prompt.md)：角色指令、Text to SQL、Function Calling、技能與安全防護的運作方式
* [身分與權限](https://docs.maiagent.ai/tech/identity-and-access/member-provisioning.md)：成員開通（SCIM／邀請／SSO）、SAML SSO 與知識存取權限
* [平台建置與部署](https://docs.maiagent.ai/tech/platform-development/gai-lan.md)：SaaS／私有雲／地端環境、部署架構與 GPU 算力規劃

***

## MaiAgent 資源與服務

| 資源                                                    | 內容                                                                                |
| ----------------------------------------------------- | --------------------------------------------------------------------------------- |
| [使用者手冊](https://docs.maiagent.ai/)                    | 後台與各產品功能的操作說明                                                                     |
| 技術人員手冊（本手冊）                                           | 部署、身分整合、API 串接與技術原理                                                               |
| [API 文件](https://docs.maiagent.ai/api)                | 完整 API 端點參考                                                                       |
| [Release Note](https://docs.maiagent.ai/release-note) | 每週產品更新                                                                            |
| 教育訓練與 AI 導入顧問                                         | 管理者與使用者課程、需求評估、場景建置與知識庫調校，請洽 <mark style="color:blue;"><sales@maiagent.ai></mark> |

***

## 開始使用 MaiAgent

前往 MaiAgent 註冊並聯繫 <mark style="color:blue;"><sales@maiagent.ai></mark>，將有專人深入了解你的需求，並為您開通試用服務。

{% embed url="<https://admin.maiagent.ai/>" %}

***

## 關於我們

思邁智能股份有限公司 | MaiAgent Co., Ltd.

統編：60688078

地址：106 臺北市大安區光復南路438號11樓

Email: <sales@maiagent.ai>

網址：<https://maiagent.ai/>


---

# 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.maiagent.ai/tech/readme.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.
