Mastering the Microsoft Agent Framework: Building Enterprise AI Agents with .Net
暫譯: 精通 Microsoft Agent Framework：使用 .NET 建構企業級 AI Agent

Name: Mastering the Microsoft Agent Framework: Building Enterprise AI Agents with .Net
Price: 2023 TWD
Availability: OnlineOnly
Author: Piridi, Sarat
ISBN: 9798868828874

Piridi, Sarat

出版商: Apress
出版日期: 2026-09-27
售價: $2,130
貴賓價: 9.5 折 $2,023
語言: 英文
頁數: 270
裝訂: Quality Paper - also called trade paper
ISBN: 9798868828874
ISBN-13: 9798868828874
相關分類: Large language model、.NET、Microsoft Azure

海外代購書籍(需單獨結帳)

商品描述

Design and build enterprise AI agents using the Microsoft Agent Framework with .NET and C#.

The Microsoft Agent Framework is Microsoft's foundation for building AI agents on .NET. It unifies the ideas that started in Semantic Kernel and AutoGen and adds what a production system actually needs. This book teaches it from the ground up, one working agent per chapter, from your first conversational agent to agents that call each other and run in the cloud.

You start simple: deploy a model, connect your first agent, and understand how models, providers, and credentials fit together. Then you add the capabilities that make an agent genuinely useful. You give it tools so it can call your code. You give it memory so it remembers, both within a conversation and after a restart. You ground it in your own documents so it answers from real sources, with citations. And you put a human in the loop, so risky actions happen only after someone approves them.

From there, the book goes further. You connect your agent to outside tools and data through the Model Context Protocol, and package reusable capabilities as skills. You learn to coordinate several agents at once: running them in sequence, in parallel, handing off between them, or letting them collaborate in a group. Then you make agents production-ready, adding guardrails, tracing what they do with OpenTelemetry and Azure Application Insights, and measuring their quality with evaluation. Finally, you connect agents to each other and host them on Azure, and close with a chapter of hard-won best practices for building agents that last.

Everything in the book runs. Every code listing is a real program that builds and executes, and a companion GitHub repository gives you the complete source for every chapter. The book pins one framework version throughout, so the code works exactly as written instead of drifting out of date. Each chapter follows the same practical rhythm: here's the problem, here's the code, here's it running, and here's what to watch for in production.

What You Will Learn:

Deploy a model and give your agent tools to call your own code Add memory, ground answers in your documents with retrieval, and require human approval for risky steps Extend agents with the Model Context Protocol and reusable skills Coordinate multiple agents: sequential, concurrent, handoff, group chat, and Magentic orchestration Add guardrails and trace agents with OpenTelemetry and Azure Application Insights Evaluate agent quality, connect agents to each other, and host agents in the cloud with Azure

Who This Book Is For:

.NET developers who want to build real AI agents with C#. You should be comfortable with C# and have used a cloud service before. No machine learning background is needed, you deploy and call models, you don't train them.

商品描述(中文翻譯)

使用 Microsoft Agent Framework 搭配 .NET 和 C# 設計並建置企業級 AI agent。

Microsoft Agent Framework 是 Microsoft 在 .NET 上建置 AI agent 的基礎。它整合了 Semantic Kernel 和 AutoGen 所開創的概念，並加入實際生產環境所需的功能。本書從基礎開始教學，每章都會完成一個可運作的 agent，帶你從第一個對話式 agent 開始，一路學到能彼此呼叫並在雲端執行的 agent。

你會先從簡單的內容開始：部署模型、連接第一個 agent，並了解模型、提供者（provider）與認證資訊如何搭配運作。接著，你會逐步加入讓 agent 真正實用的功能。你可以賦予 agent 工具，讓它呼叫自己的程式碼；加入記憶功能，讓它在對話期間以及重新啟動後都能記住資訊；以自己的文件建立基礎，讓它根據真實來源回答問題並附上引用；此外，也可以將人工介入納入流程，確保高風險操作只有在獲得人員核准後才會執行。

接下來，本書將進一步探討更進階的內容。你會透過 Model Context Protocol 將 agent 連接至外部工具與資料，並將可重複使用的功能封裝成 skills。你也會學習如何同時協調多個 agent：讓它們依序或平行執行、彼此交接，或在群組中共同協作。之後，你會讓 agent 具備生產環境所需的條件，包括加入防護機制（guardrails）、使用 OpenTelemetry 和 Azure Application Insights 追蹤 agent 的行為，以及透過評估機制衡量其品質。最後，你會學習如何讓 agent 彼此連接、在 Azure 上代管 agent，並透過最後一章整理多年實務經驗，掌握建置持久可靠 agent 的最佳實務。

本書中的所有內容都可以實際執行。每個程式碼範例都是能夠建置與執行的完整程式，而隨書提供的 GitHub repository 則包含每一章的完整原始碼。本書全程固定使用同一個 framework 版本，確保程式碼能如實執行，不會因版本變動而逐漸過時。每章都遵循相同的實務節奏：這是要解決的問題、這是程式碼、這是執行結果，以及在生產環境中需要注意的事項。

你將學會：

• 部署模型，並提供工具讓 agent 呼叫自己的程式碼
• 加入記憶功能，透過檢索（retrieval）以自己的文件作為回答依據，並要求高風險步驟必須經過人工核准
• 使用 Model Context Protocol 和可重複使用的 skills 擴充 agent
• 協調多個 agent：循序執行、並行執行、交接（handoff）、群組聊天（group chat）與 Magentic orchestration
• 加入防護機制，並使用 OpenTelemetry 和 Azure Application Insights 追蹤 agent
• 評估 agent 品質、讓 agent 彼此連接，並使用 Azure 在雲端代管 agent

本書適合哪些讀者：

想使用 C# 建置實際 AI agent 的 .NET 開發人員。你應該熟悉 C#，並且曾經使用過雲端服務。不需要具備機器學習背景；你會部署並呼叫模型，而不是訓練模型。

作者簡介

Sarat Piridi is a Microsoft-certified Solution Architect and AI Transformation Leader with more than 14 years of experience in enterprise automation and intelligent systems. He holds multiple Microsoft credentials, including the Microsoft Certified: AI Transformation Leader and Microsoft Certified: Agentic AI Business Solutions Architect, along with Power Platform and Azure expert certifications.

He is the author of GovOps with Microsoft Power Platform and Copilot: Automating Governance and has published multiple research papers and white papers on agentic AI, hyper automation, and enterprise-scale digital transformation. Sarat actively contributes to the global tech community as a speaker, reviewer, and advisor, focusing on modernizing public-sector and enterprise systems using AI and Microsoft technologies.

作者簡介(中文翻譯)

Sarat Piridi 是一名具備 Microsoft 認證的解決方案架構師（Solution Architect）與 AI 轉型領導者，擁有超過 14 年的企業自動化與智慧系統經驗。他持有多項 Microsoft 認證，包括 Microsoft Certified: AI Transformation Leader 和 Microsoft Certified: Agentic AI Business Solutions Architect，以及 Power Platform 和 Azure 專家級認證。

他著有《GovOps with Microsoft Power Platform and Copilot: Automating Governance》，並發表多篇探討 Agentic AI、超自動化（hyper automation）與企業規模數位轉型的研究論文及白皮書。Sarat 積極以講者、審稿人與顧問身分參與全球技術社群，專注於運用 AI 與 Microsoft 技術，推動公共部門及企業系統現代化。