> 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/advanced-genai-tech.md).

# 技術原理

- [角色指令](https://docs.maiagent.ai/tech/advanced-genai-tech/system-prompt.md): Agent 每次回覆前，平台會在您寫的角色指令後面自動附加哪些情境（時間、使用者名稱、位置、語系、聯絡人與成員屬性、知識庫與技能提示等），各由哪個設定控制，以及寫角色指令時該怎麼引用。寫法與範本見使用者手冊。
- [回覆評估與監測結果](https://docs.maiagent.ai/tech/advanced-genai-tech/evaluation.md): MaiAgent 回覆評估的技術說明：Agent 監控與自動評估各用哪些指標、需要哪些資料、分數方向與測試案例的通過判定。
- [Text to SQL](https://docs.maiagent.ai/tech/advanced-genai-tech/text-to-sql.md): Text to SQL 技術規格：支援的資料庫與連線字串格式、唯讀保護、網路與帳號需求、大型 schema 的處理方式與查詢結果上限。
- [Function Calling](https://docs.maiagent.ai/tech/advanced-genai-tech/function-calling.md): Function Calling（工具呼叫）的概念，以及 MaiAgent 的 Agent 怎麼取得工具定義、平台怎麼執行工具並把結果交回模型，還有迭代次數、逾時與結果長度等限制。
- [Skill 技能模組](https://docs.maiagent.ai/tech/advanced-genai-tech/skill.md): Skill 技能模組技術說明：把任務指令、工具與資源檔封裝成 Agent 按需展開的能力單元，SKILL.md 規格、觸發條件、技能包結構與 API 端點。
- [Canvas](https://docs.maiagent.ai/tech/advanced-genai-tech/canvas.md): Canvas（畫布）的概念，以及 MaiAgent 的 Agent 如何把產出交給畫布代理、支援哪些內容類型、在哪些對話平台顯示，與相關限制。
- [AI 安全防護機制](https://docs.maiagent.ai/tech/advanced-genai-tech/guardrails.md): MaiAgent 的 AI 安全防護機制：客戶可自行設定的 Hook 訊息攔截（個資遮罩、內容安全分類等），以及由 MaiAgent 代為設定的 ICAP 內容驗證與 AWS Bedrock Guardrails，各自的作用位置與限制。
- [OAuth 2.0 整合與 Token 自動刷新機制](https://docs.maiagent.ai/tech/advanced-genai-tech/oauth-integration.md): OAuth 2.0 整合與 Token 自動刷新：MaiAgent 連接 Google Workspace、Salesforce、GitHub 等第三方服務的授權架構、refresh token 管理與最佳實踐。
- [ICAP 內容驗證整合](https://docs.maiagent.ai/tech/advanced-genai-tech/icap-content-validation.md): ICAP 內容驗證整合：以 ICAP 協定把 Web Chat 上傳的檔案轉送外部服務做病毒掃描、內容過濾與 DLP，整合架構、協定實作、掃描記錄與部署設定。


---

# 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/advanced-genai-tech.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.