Master AI Agents: Hands-On Development with LangGraph, RAG, MCP, and Multi-Agent Systems

This course is a practical, hands-on guide for those who want to learn how to maximize development productivity in the AI era. Beyond simply learning how to use AI, we focus on how to utilize Claude Code in a real-world development environment and how to produce "proper results." Many developers use AI but still face issues such as: ❌ Inconsistent results ❌ Poor code quality ❌ Increasing project complexity To solve these problems, this course teaches you how to utilize AI as a "development partner" rather than just a tool through: ✔ Spec-based workflows ✔ Structured command systems ✔ Sub-agent and automation strategies Furthermore, you will gain the experience of completing and deploying a full application from start to finish by integrating with real-world services such as Firebase, Figma, GitHub, and Vercel.

Claude Code is rapidly growing as one of the most powerful AI coding agents available today. However, simply installing Claude Code is not enough to maximize productivity. To truly utilize Claude Code effectively, you must understand advanced features such as context management, memory systems, skills, subagents, and agent teams. In this course, we will learn step-by-step, starting from the installation and initial setup of Claude Code to advanced workflows used in real-world practice. Students will learn how to integrate Claude Code with VS Code and how to select and utilize various models. Furthermore, you will master how to perform complex development tasks efficiently using Context Engineering, Memory management, Skills, Subagents, and Agent Teams. After the course, you will be able to use Claude Code not just as a simple AI chatbot, but as an AI development partner that genuinely boosts development productivity. Based on real-world experience in AI development and software projects, the instructor explains how to apply Claude Code to practical work and helps students solve common issues such as context management problems, token waste, and inefficient prompt writing.

This is an introductory course designed for those learning Rust for the first time, structured to help you learn step-by-step from the basics. Many learners encountering Rust for the first time often find it difficult due to: - Unfamiliar syntax - The burden of memory concepts - Differences from existing languages (C/C++) To solve these problems, this course helps anyone understand Rust naturally through: 👉 Easy explanations 👉 Step-by-step curriculum 👉 Repetitive practical examples Rust is a modern systems programming language that offers both safety and performance, making it a very important technology in the future development landscape. Build a solid foundation of Rust's core basics through this course.

Even without coding experience, you can create a real-world work automation program yourself with Cursor AI. This course is a hands-on project in which you use Python and Cursor AI to automatically collect news comments (Crawling), save them as a CSV file, and analyze public opinion and sentiment, creating a complete project from start to finish. This is not a course where you simply type along with the code. It is designed to let you experience the entire real-world development process, including how to ask Cursor AI effective questions, setting up the development environment, writing automation programs, and troubleshooting errors. By following the course, you will learn step by step—from installing Python and configuring Cursor AI to the basics of work automation, scraping news comments, saving data as a CSV file, performing sentiment analysis, and fixing errors that arise in actual projects. Even if you are new to programming, you will naturally learn how to develop alongside AI, automate repetitive tasks, and build practical skills for using data.

This course is designed step-by-step, from the basics to practical application, so that even those new to Claude AI can easily follow along. In this course, you will start with the basic concepts of Claude AI and how to write prompts, and then learn various use cases such as document writing, summarization, translation, brainstorming, and file and image analysis. You will also practice how to create documents, charts, diagrams, and simple applications using Claude Artifacts, as well as creating infographics using Claude Design, modifying results, and saving them as PDFs. Finally, we provide productivity-enhancing know-how that can be used immediately in the workplace, including advanced prompt engineering techniques, automating repetitive tasks using the Projects feature, Excel functions, and coding support. From beginners with no AI experience to office workers, students, and content creators who want to increase work efficiency, the course explains everything through practical examples so that anyone can learn easily and apply it right away.

This is a practical, step-by-step course designed to help everyone from learners using Google Gemini for the first time to professionals who want to actively apply Gemini in their work. Rather than simply introducing features, the course focuses on real-world applications and explains how to address challenges learners may encounter when writing prompts, researching information, creating documents, producing content, and more. Participants will progressively learn Gemini’s basic features, Google Workspace integration, Gem customization, Google Labs, and NotebookLM, gaining the skills to use AI effectively in both their work and daily lives. In particular, the course is systematically structured—from basic concepts to practical applications—so that even learners who are new to AI can follow along easily. It also covers safe ways to use AI, including information verification and personal data protection.

This is a practical, hands-on course where you will learn the principles of AI Agents—going beyond simple chatbots that just answer questions to systems that can perceive situations, make judgments, and control actual systems. The curriculum is structured to provide a step-by-step understanding, starting from the differences between AI Agents and chatbots to the core Agent Loop structure: Sense-Think-Act, state management, planning, and feedback loops. Moving beyond theory, you will set up Windows and Linux development environments and gain hands-on experience with the basic structure of Kubernetes and kubectl commands. Following this, you will implement a process where an AI Agent detects server issues, analyzes the causes, and automatically resolves errors. Finally, by directly analyzing the Python code and internal logic of the Agent controlling Kubernetes, you will understand how AI Agents connect to and operate within real-world systems. From developers new to AI Agents to those who want to design Multi-Agents that control actual systems, this course allows you to learn both the principles and the practical implementation process of Agents.

This course is designed to help learners build solid AWS cloud engineering and architecture skills through hands-on projects and practical demonstrations. Students will learn how to build secure AWS environments, manage scalable computing infrastructure using EC2 and Auto Scaling, configure networking via VPC and Load Balancers, and implement cloud-native storage and database solutions using S3, Aurora, and MySQL. Throughout the course, I will guide students step-by-step using hands-on labs, architectural explanations, and real-world deployment scenarios commonly used in modern cloud environments. I focus on simplifying complex AWS concepts into easy-to-understand lessons while helping students avoid common mistakes made during cloud deployment, security configuration, and infrastructure scaling. By the end of this course, students will not only gain the confidence to design secure, scalable, and cost-effective solutions on AWS but will also be prepared for the AWS Solutions Architect Associate certification exam.

This course is designed for developers, DevOps engineers, cloud engineers, and IT professionals who want to master advanced Kubernetes concepts used in real-world production environments. Throughout the course, students will engage in hands-on projects and real-world deployment scenarios, learning how to build secure, scalable, and production-ready Kubernetes infrastructure. Rather than focusing solely on theory, this course emphasizes practical implementation, troubleshooting, and best practices utilized by modern DevOps teams. One of the biggest challenges students face when learning Kubernetes is understanding how all components interact within large-scale environments. Many learners struggle with topics such as RBAC permissions, persistent storage, namespaces, network policies, StatefulSets, Kustomize, and secure cloud deployments. This course addresses these issues step-by-step through clear explanations, guided labs, and examples that mirror actual production environments. Students will learn step-by-step how to organize Kubernetes resources, secure workloads, manage application configurations, deploy stateful applications like MongoDB, and automate multi-environment deployments using Kustomize. Additionally, the course covers how to deploy applications to Google Kubernetes Engine (GKE) and configure Ingress, TLS certificates, monitoring, and scaling strategies. By the end of this course, students will have the confidence to design, secure, deploy, and manage advanced Kubernetes environments used in professional DevOps and cloud engineering workflows.

This course is designed for developers, AI enthusiasts, and professionals who want to develop real-world AI applications using LangChain, OpenAI, Hugging Face, and Python. Rather than focusing solely on theory, this course takes a practical, project-oriented approach. Throughout the course, students will directly build a total of 15 high-quality AI applications, including chatbots, CSV analysis tools, resume screening systems, invoice extraction bots, support assistants, marketing tools, and text-to-SQL applications. I created this course to make complex AI concepts easy to understand and to ensure modern LLM development is accessible to everyone. Many learners struggle to understand how tools like LangChain, embeddings, memory systems, vector databases, and AI agents interact in real-world applications. This course guides you step-by-step through clear explanations, hands-on coding sessions, and actual implementation workflows. By the end of the course, students will confidently understand how to design, build, and deploy AI-powered applications using the latest generative AI technologies.

While studying Spring Security, you've probably wondered at least once: "I've built the login, but how do I handle authorization?" "How are authentication and authorization implemented in real-world practice?" This course is a practical, project-oriented lecture designed to solve those exact concerns. Instead of just explaining concepts, we implement them exactly as they are used in real services by: 👉 Building on an actual TodoApp project 👉 Integrating with a database 👉 Managing user permissions 👉 Handling validation In particular, I will provide easy, step-by-step explanations for the parts many students find difficult: Method-level authorization Access control within templates Validation using regular expressions Through this course, I will help you confidently say, 👉 "I can actually use Spring Security." 🚀

This course goes beyond simple grammar explanations and focuses on developing C++ programming skills that can be applied immediately in the field. Throughout my teaching, I have directly addressed common challenges faced by many learners—such as struggling to understand the STL or feeling confused by file handling and exception handling concepts. Based on this experience, I provide step-by-step explanations to ensure even complex concepts are understood easily and clearly. Furthermore, this course is not just about delivering theory; it is structured around: 👉 "Why this concept is necessary" 👉 "How it is used in actual code" 👉 "How it is applied in professional practice"

This course is designed to help even those new to MySQL understand it easily, starting from the basic concepts of DBMS and progressing step-by-step to the ability to write SQL that can be applied in real-world practice. To solve the problems learners frequently encounter (e.g., SQL syntax is difficult, not knowing how to write queries, or not understanding the flow of data processing), the course is structured with repetitive theory and practice, helping you naturally build your skills through a hands-on approach. In particular, the focus is not on simple memorization of syntax, but on understanding "why it is written this way" through the process of handling actual data.

This course is designed for those who want to go beyond simple AI chatting and actually get work done using AI agents. Many students are already using ChatGPT or Claude, yet they still struggle with repetitive tasks, scattered workflows, excessive research, and low productivity. The problem usually doesn't lie with the AI itself, but in knowing how to organize work systematically, give clear instructions, and build reliable workflows. In this course, we provide a step-by-step guide on the practical application of Claude Cowork. Rather than focusing solely on theory, we practice through practical examples such as project management, browser automation, meeting preparation, persistent memory systems, skills, plugins, and desktop control. This course explains everything in a simple and practical way so that even beginners can easily follow along. By the end of the course, students will understand how to utilize Claude Cowork as a true productivity assistant for research, planning, organization, automation, and daily tasks.

This course explains everything from the basics of MySQL to its practical application in a step-by-step manner, making it easy to understand even for those learning databases for the first time. Rather than just providing simple theoretical explanations, the course focuses on real-world problem scenarios and teaches you how to write SQL and handle data through hands-on practice. The curriculum is systematically structured to cover the entire process, from DBMS concepts to MySQL installation, basic SQL syntax, data manipulation, and the use of functions. In particular, the goal is to help you understand "why it is written this way" through repetitive practice and to develop the ability to write queries on your own.

This course is a practical, hands-on guide to automating repetitive tasks and maximizing work productivity using ChatGPT and Python. You will learn step-by-step how to use AI to automate daily repetitive tasks such as Excel work, report writing, sending emails, and data organization. Starting as a non-developer myself, I have taught AI automation to thousands of students, and I have compiled only the methods that can be used immediately in actual business environments. This course focuses not on complex theories, but on **"automation techniques you can use right today."** 👉 The goal is to turn ChatGPT into more than just a tool, but into **your own personal work assistant (Jarvis)**.

Building an 'Intelligent Collaboration' Expert Agent Team Using Spring AI Router Pattern + RAG + MCP Beyond a Single Agent to Architecture: The Standard for Router Patterns and Agent Isolation Design

Beyond the era of simply using AI, we are now in an era that requires people who can design AI. This course is a master roadmap that systematically organizes the entire design map of AI agents, from "Introduction → Structure → Design → Operation." Based on RAG, Tool Calling, Memory, and Multi-Agent structures, you will learn how to design and scale AI agents from an architect's perspective. If you want to grow into someone who designs AI systems rather than just someone who "uses" AI, this course will provide the direction.

This is a hands-on course where you'll build an AI-based autonomous driving car using Raspberry Pi and various sensors.

This is a practical, hands-on course where you will learn the principles of AI Agents—going beyond simple chatbots that just answer questions to systems that can perceive situations, make judgments, and control actual systems. The curriculum is structured to provide a step-by-step understanding, starting from the differences between AI Agents and chatbots to the core Agent Loop structure: Sense-Think-Act, state management, planning, and feedback loops. Moving beyond theory, you will set up Windows and Linux development environments and gain hands-on experience with the basic structure of Kubernetes and kubectl commands. Following this, you will implement a process where an AI Agent detects server issues, analyzes the causes, and automatically resolves errors. Finally, by directly analyzing the Python code and internal logic of the Agent controlling Kubernetes, you will understand how AI Agents connect to and operate within real-world systems. From developers new to AI Agents to those who want to design Multi-Agents that control actual systems, this course allows you to learn both the principles and the practical implementation process of Agents.

Go beyond a simple system prompt to build an AI character chatbot that remembers users and whose relationship with them evolves, using persona design and Structured Outputs. In this 30-minute hands-on session, you’ll learn how to safely call the OpenAI API based on the provided starter project, process emotions, trust levels, and memories in a verifiable format using JSON Schema and Zod, and use an AI coding agent within defined constraints.

LLM and Agent, the fundamental technologies behind AI like ChatGPT. LLM is currently the technology that has come closest to AGI. In this lecture, we will explore LLM and Agent technologies from a layperson's perspective.

We explore how to create an AI judge by combining knowledge graphs, reasoning systems, and various agent frameworks such as CrewAI, LangChain, and AutoGen, which enable the implementation of LLM-based multi-agent technology.

We design and implement AI agent systems that go beyond simple chatbots to perform tasks autonomously. From Sense-Think-Act loop-based architectures to LangGraph cyclic structures, RAGAS and LangSmith-based quantitative evaluation, and operational guardrails, you will complete your enterprise-grade agent engineering capabilities through hands-on practice of the entire process.

Explore how LLM applications are shifting the development paradigm. Understand why LLMs are becoming a sustainable core technology through comparisons with existing technologies, and learn about the essential skills and mindset shifts required for developers. Gain insights from expert instructors to grasp the essence and future direction of LLM application development.

We are launching a "Complete Reading Challenge" for the book "AI Agent Engineering," a practical guide to building proactive agent systems using LLMs. This book covers the core components of agents step-by-step, from tool selection to orchestration (designing planning and execution flows) and memory management. It also explores how to scale into multi-agent architectures where multiple agents collaborate by dividing roles. Furthermore, it expands your perspective from "how to build" to "how to operate" by covering essential production-level topics such as reliability, security, and governance. Do you want to design agent systems that go beyond simple automation to operate safely and transparently according to human intent? Join the book and the challenge to discover a concrete roadmap for turning your ideas into production-level systems!

1. A practice-oriented lecture designed to help you pass the AICE Associate, Korea's only nationally recognized AI certification. 2. Learn to the level of performing data analysis and AI modeling based on Python.

This course is not just about "how to implement" a Transformer, but about dissecting why this architecture was created, what role each module plays, and how the entire model works from the designer's perspective. We deeply analyze the internal computation principles of Self-Attention and Multi-Head Attention, and directly verify through formulas, papers, and implementation code what limitations Positional Encoding, Feed-Forward Networks, and Encoder·Decoder structures were introduced to solve. Starting from Attention, we assemble the entire Transformer structure ourselves, and actually perform training to experience firsthand how the model operates. This course is the most structured and practical roadmap for "anyone who wants to completely understand Transformers."

Beyond a chatbot that simply generates answers, you will directly implement an autonomous AI Agent that makes its own judgments, calls tools, and performs multi-step tasks. You will learn through step-by-step practice, covering everything from OpenAI Agents SDK's Tool Calling, Handoff, Guardrail, Session, and Tracing to connecting external tools and databases using MCP, as well as LangChain and Deep Agents' Planning, Subagents, Filesystem, and Memory. The ultimate goal is to equip you with the ability to design and implement tool-integrated AI Agents that can be applied to real-world tasks.

This course covers everything from core recommendation system algorithms to practical implementation. - Content-based filtering - Collaborative filtering and deep learning-based recommendation model implementation - Two-step recommender systems implementation - Hands-on practice using PyTorch/RecBole - Industry know-how and recommendation result visualization

This is an advanced course focused on designing and implementing Multi-LLM architectures and orchestration-centered Agent systems (Main/Sub, Tool, Task Runtime, Agent Registry) by strategically combining GPT, Gemini, and LLaMA (local) based on Spring AI and Spring Boot. Moving beyond simple LLM calls, the curriculum covers the implementation of scalable, stable, and continuously improving AI systems. This involves applying Agentic Workflow Patterns (Chain, Parallel, Routing, Orchestrator–Workers, Evaluator–Optimizer) and Multi-Agent structures, separating execution layers like RAG and external APIs/DBs via Tool/ToolRegistry, and utilizing DAG engines, YAML declarative workflows, and Validated DSL (validation immediately after loading). Furthermore, the course includes Circuit Breakers, Reactive Streams, Redis monitoring, parallel processing, and iterative evaluation loops. It expands from Thymeleaf (SSR) exercises to decoupled Front-end/Back-end architectures using React and REST, while integrating tool and agent runtimes via MCP (Model Context Protocol) to build AI architecture design capabilities at a production-ready level. The ultimate goal is to evolve beyond being a simple AI user who merely integrates APIs and writes prompts, becoming a developer capable of designing AI systems—explaining and balancing Multi-LLM, agents, workflows, declarations, and validation within a single execution architecture.

Develop various features using Spring WebFlux. This course will teach you WebFlux's essential concepts and practical implementation.

Do you know the basics but feel overwhelmed when it comes to applying them in practice? Drawing on real-world experience, we make complex LLM architectures easy to understand.

This course teaches you how to build AI agents from scratch to a production-ready level using OpenClaw. Beyond a simple introduction to features, you will master OpenAI, local LLMs, memory, sessions, Tools, and Skills in a single, cohesive workflow. Based on hands-on experience and know-how gained from developing AI and large-scale systems in Silicon Valley, the course explains architectures and operational methods applicable to real-world projects. By the end of the course, you will be able to design your own AI agents and implement automation by integrating them with various services. This is a practice-oriented course for those who want to go beyond just using AI and learn how to build and operate it themselves.

Learn the easiest way to handle AI with Spring AI. Let's learn Spring AI by building a RAG chatbot.

[Source Code Provided] No coding knowledge required. Build it instantly in your browser using Google's latest tool (IDX) without any installation! Stop studying coding syntax! This is an ultra-fast, hands-on course where you'll build an RAG chatbot that perfectly understands internal company documents through AI conversation (Vibe Coding) in the Google IDX environment and deploy it live to the web.