|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/building-ai-agents-agentic-ai-system-via-microsoft-autogen/
课程评论：没有评论
课程名称：使用 Microsoft AutoGen 构建 AI 代理与代理 AI 系统 课程概述： 欢迎参加“使用 AutoGen 构建 AI 代理和代理 AI 系统”课程，这是一个以项目为驱动的实践课程，旨在帮助您掌握智能软件的未来：代理 AI。随着大语言模型（LLM）的不断增强，下一步的演变是让它们通过 AI 代理协同工作，而本课程将成为实现这一目标的完整指南。 无论您是数据科学家、机器学习工程师、AI 研究者，还是产品开发者，本课程都将逐步引导您进入多代理 AI 系统的世界。您将学习如何设计、构建和部署能够自主规划、推理，以及通过彼此沟通和与外部工具交互执行复杂任务的 AI 代理。 学习内容包括： - 理解代理 AI 的基本原理及其与传统生成式 AI 应用的区别。 - 探索 AutoGen 的架构及其如何有效地协调多个基于 LLM 的代理进行协作。 - 构建和定制多种类型的代理（例如：UserProxyAgent、AssistantAgent、GroupChatAgent）。 - 实现多代理工作流程，以代码生成、任务分解和动态决策解决实际问题。 - 将 web API、数据库和 Python 函数等工具集成到您的代理生态系统中。 - 使用 AutoGen Studio 进行视觉开发和代理交互监测。 - 通过配置调整和角色专业化优化代理的成本、速度和性能。 - 部署代理系统以实现编码助手、研究机器人、多代理聊天应用及自动任务运行器等用例。 本课程以项目为核心，您不仅仅会学习理论，还将从零开始构建强大的代理 AI 应用。您将了解如何设计自主 AI 团队，模拟人类工作流程，分配职责，高效沟通，并适应动态任务。 此外，我们还将比较 AutoGen 与其他 orchestration 框架，如 LangChain 和 CrewAI，帮助您全面理解何时使用哪些工具。 适合人群： 本课程非常适合以下人士： - 希望转型为 LLM 驱动的代理开发的 ML 和 AI 专业人士。 - 有兴趣构建超越聊天机器人智能应用的开发者。 - 渴望利用代理协作推动 LLM 能力边界的生成式 AI 爱好者。 - 在开发 AI 优先应用的初创公司创始人和产品团队。 - 希望与前沿代理框架建立实践项目的学生和研究人员。 课程结束时，您将具备构建、扩展和部署可以推理、行动和协作的 AI 代理生态系统的信心和技能，这一切都得益于 AutoGen 和代理 AI 的最新进展。
Welcome to "Building AI Agents and Agentic AI Systems Using AutoGen", a hands-on, project-driven course designed to help you master the future of intelligent software: Agentic AI. As large language models (LLMs) become more powerful, the next evolution is enabling them to work collaboratively through AI agents-and this course is your complete guide to making it happen using Microsoft's AutoGen framework.Whether you're a data scientist, ML engineer, AI researcher, or product builder, this course will take you step-by-step into the world of multi-agent AI systems. You'll learn to design, build, and deploy AI agents that can autonomously plan, reason, and execute complex tasks by communicating with each other and interacting with external tools.What you'll learn:Understand the fundamentals of Agentic AI and how it differs from traditional GenAI applications.Explore the architecture of AutoGen and how it orchestrates multiple LLM-powered agents to collaborate effectively.Build and customize various types of agents (e.g., UserProxyAgent, AssistantAgent, GroupChatAgent).Implement multi-agent workflows that solve real-world problems with code generation, task breakdown, and dynamic decision making.Integrate tools like web APIs, databases, and Python functions into your agent ecosystem.Use AutoGen Studio for visual development and monitoring of agent interactions.Optimize agents for cost, speed, and performance using configuration tuning and role specialization.Deploy agentic systems for use cases like coding assistants, research bots, multi-agent chat applications, and automated task runners.This course is project-focused-you won't just learn the theory, you'll build powerful agentic AI applications from scratch. You'll understand how to design autonomous AI teams that mirror human workflows, assign responsibilities, communicate efficiently, and adapt to dynamic tasks.We'll also compare AutoGen with other orchestration frameworks like LangChain and CrewAI, giving you a well-rounded perspective of what tools to use and when.Who should take this course?This course is ideal for:ML and AI professionals wanting to transition into LLM-powered agentic development.Developers interested in building intelligent apps that go beyond chatbots.GenAI enthusiasts eager to push the limits of LLM capabilities using agent collaboration.Startup founders and product teams working on AI-first applications.Students and researchers looking to build hands-on projects with cutting-edge agentic frameworks.By the end of this course, you will have the confidence and skills to build, scale, and deploy AI agent ecosystems that can reason, act, and collaborate just like teams of humans-powered by the latest advancements in AutoGen and Agentic AI.
