Learning Building Real-World AI Agents

[voska89]

Building Real-World AI Agents
Published 5/2026
Created by Alper Daldal
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz, 2 Ch
Level: All Levels | Genre: eLearning | Language: English | Duration: 60 Lectures ( 4h 18m ) | Size: 1.32 GB

Explore AI agents and create your own using LangGraph or CrewAI.
What you'll learn
You will learn concepts such as large language models, generative AI, and prompts, which are essential for understanding the AI Agent architecture.
You will discover what AI Agents are and how they differ from Generative AI and Agentic AI.
You will study the fundamental components that make up an AI Agent, such as personality, memory, tools, reasoning, and planning.
You will discover powerful agentic patterns like ReAct, CoT, ReWOO, ToT, and reflection, and use them to design and build AI Agents.
You will study multi-agent architectures, analyze examples such as Supervisor and Swarm, and build your own multi-agent systems using these patterns.
You will discover how to bring humans into the AI Agent loop and solidify your learning with real code examples.
You will explore Agentic RAG and learn how to use it in your own AI Agents through practical code examples.
You will discover how AI Agents communicate through protocols like MCP, A2A, and ACP.
You will explore widely used AI Agent frameworks such as LangGraph and its core foundation, LangChain.
By learning concepts such as states, nodes, and edges in LangGraph, you will be able to build your own workflows.
You will learn different ways to use memory in LangGraph through practical code examples.
You will learn how to use both built-in and custom tools within the LangGraph framework.
You will explore examples of agent collaboration using LangGraph and learn to build similar systems yourself.
You will discover CrewAI, a powerful framework for developing AI Agents.
You will explore the key building blocks of CrewAI-teams, tasks, and agents-and learn how to use them in your own projects.
You will study the YAML-based configuration used to define tasks and agents in CrewAI and learn to create your own YAML files.
You will discover how to design and run flows in CrewAI while collaborating with a crew.
You will be able to develop AI Agents in CrewAI that can write and execute code.
You will learn how to improve your AI Agent's performance using CrewAI's testing and training features.
Requirements
Possession of basic programming and algorithm development or comprehension skills
While Python knowledge is not required, it may assist in understanding the provided code examples
Description
This course contains the use of artificial intelligence. (Since this course may be followed by people from all around the world, I considered that my accent might not be equally easy for everyone to understand. Therefore, to ensure clarity and accessibility, I chose to use text-to-speech AI tools for the course narration.)
With the rapid advancement of large language models, artificial intelligence has entered a new era, and generative AI has become part of everyday life. The next step in this evolution is AI agents-autonomous systems that interact with their environment, make decisions, and perform tasks on behalf of users. In many ways, these agents can take on roles similar to human employees within organizations.
So, can we build our own AI agents to meet specific needs? Can we create solutions for companies looking to leverage this technology? This course is designed to help you do exactly that-by equipping you with both the theoretical knowledge and hands-on skills needed to develop AI agents.
This course is divided into two main parts. In the first part, we will build the foundational knowledge required to understand AI agents. We will start with large language models-the core "brain" behind these systems.
From there, we will explore what AI agents are, clarifying how they differ from generative AI and Agentic AI. We will then take a closer look at their internal structure and the key components that define them.
You will also learn about widely used design patterns for developing AI agents. In addition, we will introduce Retrieval-Augmented Generation (RAG) and its evolution into Agentic RAG. To complete this section, we will examine agent communication protocols, focusing on how agents interact with one another and with external tools.
The second part of the course is fully hands-on and practice-oriented. You will apply the AI agent design patterns learned in the first section to real-world scenarios.
We start by introducing two of the most popular frameworks for building AI agents: LangGraph and CrewAI. Then, you will develop 24 different AI agent applications using these frameworks. Along the way, you will explore key features such as tool integration, memory, Agentic RAG, and multi-agent systems.
These applications will showcase how AI agents can reshape the way we work by handling tasks like content creation and validation, online research, agent collaboration, file processing, code generation and execution, knowledge retrieval, conversational interfaces, and issue management.
By the end of the course, you will not only understand AI agents conceptually but also have the practical expertise to build them for diverse real-world needs.
Who this course is for
This course will be an inspiring resource for those who want to make a difference in their fields by learning AI Agent concepts.
Programmers who aim to design and build their own AI Agents.
Professionals across different roles aiming to develop new projects, products, or business opportunities through AI Agents.
Homepage

https://www.udemy.com/course/building-real-world-ai-agents

RapidGator
https://rg.to/file/6b19c3b5c79521356998b914efe8b571/hxziv.Building.RealWorld.AI.Agents.part1.rar.html
https://rg.to/file/b978868b8f9c921341d4b2bd28b15977/hxziv.Building.RealWorld.AI.Agents.part2.rar.html
[b]AlfaFile[/b]
https://alfafile.net/file/A4Kbd/hxziv.Building.RealWorld.AI.Agents.part1.rar
https://alfafile.net/file/A4KbF/hxziv.Building.RealWorld.AI.Agents.part2.rar

No Password - Links are Interchangeable