Building Autonomous AI Agents

本课程是 Autonomous AI Agent Systems and Orchestration 专项课程的一部分

位教师：Edureka

访问权限由 Coursera Learning Team 提供

4个模块

深入了解一个主题并学习基础知识。

初级等级

推荐体验

7 小时完成

灵活的计划

自行安排学习进度

4个模块

深入了解一个主题并学习基础知识。

初级等级

推荐体验

7 小时完成

灵活的计划

自行安排学习进度

您将学到什么

Understand the core architecture and components of autonomous AI agents.
Build and orchestrate multi-agent systems using frameworks.
Integrate memory, reasoning, and tool-use capabilities into AI workflows.
Apply ethical, safety, and evaluation frameworks for trustworthy agent deployment.

您将获得的技能

要了解的详细信息

可分享的证书

添加到您的领英档案

作业

14 任务¹

AI 评分请参见免责声明

授课语言：英语（English）

了解顶级公司的员工如何掌握热门技能

了解关于 Coursera for Business 的更多信息

Petrobras, TATA, Danone, Capgemini, P&G 和 L'Oreal 的徽标

积累特定领域的专业知识

本课程是 Autonomous AI Agent Systems and Orchestration 专项课程专项课程的一部分

在注册此课程时，您还会同时注册此专项课程。

向行业专家学习新概念
获得对主题或工具的基础理解
通过实践项目培养工作相关技能
获得可共享的职业证书

该课程共有4个模块

Artificial intelligence is rapidly advancing from simple automation to systems that can reason, plan, and act on their own. Building Autonomous AI Agents is a hands-on, practice-driven course that walks you through the end-to-end process of designing, developing, and deploying intelligent agents capable of independent decision-making.

You’ll work with leading agent frameworks—including LangChain, Autogen, and AgentOps—and learn how to integrate models, tools, and APIs to build dynamic multi-agent ecosystems. Through guided demonstrations and structured labs, you’ll implement core agent components such as memory, tool use, planning modules, and goal-driven workflows, ultimately building a fully functional autonomous agent. The course also emphasizes safety, evaluation, and alignment practices to ensure that agents operate transparently, ethically, and reliably in real-world settings. By the end of this course, you will be able to: • Understand core agent architectures, memory types, and planning strategies. • Build agents using frameworks like LangChain, CrewAI, Autogen, and AgentOps. • Connect models, APIs, and external tools into cohesive multi-agent systems. • Implement goal-driven workflows with monitoring, evaluation, and safety controls. • Deploy production-ready autonomous agents capable of operating reliably in real environments. This course is ideal for AI developers, data scientists, software engineers, and technology professionals transitioning from basic prompt engineering to building fully autonomous systems. A foundational understanding of Python, APIs, and basic AI concepts is recommended, though all frameworks are introduced from scratch. Join us to master the tools and techniques that power the next generation of AI systems that can think, act, and collaborate with minimal human intervention.

This module introduces learners to the foundations of single AI agents using the ReAct framework. Learners will explore the core concepts of agentic reasoning, tool usage, and memory integration. Through hands-on exercises, they will set up a development environment, define and use tools with structured inputs, and implement the ReAct loop for reasoning and decision-making. By the end of this module, learners will be able to deploy a functional agent capable of performing tasks with structured reasoning and short-term memory.

涵盖的内容

15个视频6篇阅读材料4个作业

15个视频总计59分钟

Specialization Introduction 5分钟
Course Introduction 4分钟
Python Prerequisites for Agentic AI Development 5分钟
Setting Up Environment for AI Agents 4分钟
The Rise of Autonomous Agents and the SDR Case Study 4分钟
AI Agent Protocols 4分钟
Agent vs. LLM Why ReAct is the Next Generation of Prompting 4分钟
Hands-On: Setting Up the Agent Development Environment (Python & Libraries) 3分钟
Hands-On: Anatomy of a Tool (Part 1) Defining Functions & Docstrings 6分钟
Hands-On: Anatomy of a Tool (Part 2) Using Pydantic for Structured Input 4分钟
Hands-On: Building Your First Research Tool (Web Search Integration) 3分钟
The Core ReAct Loop: Thought, Action, Observation in Code 4分钟
Hands-On: Prompt Engineering for Reasoning How to Get Better Tool Use 3分钟
Hands-On: Implementing State Giving Your Agent Short-Term Memory 3分钟
Hands-On: Milestone Deploying the Researcher Agent (Tool & Memory Test) 3分钟

6篇阅读材料总计60分钟

Course Outline: Building Autonomous AI Agents 10分钟
Understanding the ReAct Reasoning Loop 10分钟
Foundations of Agentic AI 10分钟
Tool Development and Action 10分钟
ReAct Implementation & Memory 10分钟
Summary: The Agentic Foundation (ReAct & Tool Use) 10分钟

4个作业总计33分钟

Knowledge Check: The Agentic Foundation (ReAct & Tool Use) 15分钟
Practice Quiz: Foundations of Agentic AI 6分钟
Practice Quiz: Tool Development and Action 6分钟
Practice Quiz: ReAct Implementation & Memory 6分钟

This module focuses on enabling a single agent to access, process, and act on external knowledge. Learners will work with retrieval-augmented generation (RAG) pipelines, including data ingestion, text embedding, and vector database indexing. They will integrate tools and actuators to enable decision-making and apply grounding techniques to ensure the agent produces contextually accurate outputs. By the end of this module, learners will have built a “strategy-grounded” agent that can reason over knowledge sources and generate validated outputs.

涵盖的内容

10个视频4篇阅读材料4个作业

10个视频总计31分钟

RAG Theory 3分钟
Hands-On: Data Preparation Loading & Splitting the Internal Sales Playbook 3分钟
Hands-On: Text Embeddings How to Convert Documents to Vector Space 3分钟
Hands-On: Building the Vector Database & Indexing the Sales Playbook 3分钟
Hands-On: Creating the RAG Retrieval Tool (retrieve_playbook) 3分钟
Hands-On: Connecting to the CRM Defining the Actuator Tool (log_activity) 3分钟
Hands-On: LLM Decisioning When to Use the Web Tool vs. the RAG Tool 3分钟
The Multi-Step Chain: Sequencing Research, RAG, and Drafting 3分钟
Hands-On: Prompting for Grounding and Forcing the Agent to Cite the Playbook 3分钟
Hands-On: The Strategy-Grounded Draft Agent (Full Output Test) 3分钟

4篇阅读材料总计40分钟

RAG Architecture and Data Ingestion 10分钟
Tool Integration and Actuators 10分钟
Strategy-Grounded Drafting 10分钟
Summary: Context, Knowledge, and Grounding (RAG) 10分钟

4个作业总计33分钟

Knowledge Check: Context, Knowledge, and Grounding (RAG) 15分钟
Practice Quiz: RAG Architecture and Data Ingestion 6分钟
Practice Quiz: Tool Integration and Actuators 6分钟
Practice Quiz: Strategy-Grounded Drafting 6分钟

This module introduces learners to orchestrating, validating, and deploying single AI agents using LangGraph. Learners will design execution graphs, implement validation nodes, and integrate reflection loops for self-correction. They will also explore human-in-the-loop techniques and conditional logic for decision-making. Finally, learners will package their agent as a RESTful API, monitor its performance, and scale workflows for robust operation. By the end of this module, learners will have a fully operational, production-ready agent capable of autonomous task execution.

涵盖的内容

10个视频4篇阅读材料4个作业

10个视频总计37分钟

Graph Theory and Motivation 3分钟
Anatomy of a Graph: Nodes, Edges, and Defining Graph State 4分钟
Hands-On: Mapping the SDR Workflow Designing the Full Execution Graph 3分钟
Hands-On: Building the Validation Node Creating the LLM-as-a-Judge 3分钟
Hands-On: Implementing the Reflection Loop Routing for Self-Correction 4分钟
Hands-On: Conditional Edges and the Logic of Decision-Making in the Graph 5分钟
Hands-On: Integrating Manual Approval into the Workflow 4分钟
Hands-On: Finalizing the Actuator and Ensuring Atomic CRM Logging 3分钟
Hands-On: Packaging the Agent as a RESTful API with FastAPI 4分钟
Hands-On: Monitoring, Scaling, and Advanced Multi-Agent Systems 6分钟

4篇阅读材料总计40分钟

Building the State Machine 10分钟
Advanced Control and Self-Correction 10分钟
Productionizing the Agent 10分钟
Summary: Orchestration, Validation, and Deployment (LangGraph) 10分钟

4个作业总计33分钟

Knowledge Check: Orchestration, Validation, and Deployment (LangGraph) 15分钟
Practice Quiz: Building the State Machine 6分钟
Practice Quiz: Advanced Control and Self-Correction 6分钟
Practice Quiz: Productionizing the Agent 6分钟

This module provides learners with an opportunity to synthesize their knowledge and demonstrate mastery of single-agent AI workflows. Learners will review key concepts from agentic foundations, RAG pipelines, and LangGraph orchestration. They will complete graded assessments, including scenario-based exercises and end-of-course knowledge checks, to apply their understanding in practical contexts. By the end of this module, learners will be able to confidently design, implement, and evaluate a fully functional single AI agent capable of reasoning, tool use, and executing grounded tasks.