Claude Code in Practice — From Installation to Harness

How to Finish, Not Just How to Get Things Done. This course is for those who have tried having AI do things for them but feel overwhelmed about where to start with their own projects. You’ll learn a workflow where you define the intent first, leave implementation and verification to AI, and use the result yourself before making a judgment. You’ll complete a deployment together once using a feedme clone and once independently with your own idea, learning your own way of working.

Document (SDD) → Code Automation. Make the system work instead of typing prompts. Build your own AI development agent with Skills, Sub-agents, and Commands, and complete monetization services through 5 real-world projects.

In the era of generative AI, it is difficult to solve practical problems simply by writing prompts. In real-world services, you need to be able to design AI systems that can make decisions autonomously, call tools, retrieve data, and collaborate across multiple agents. This course is a hands-on program for everyone from developers designing AI agents for the first time to engineers seeking to build systems that can be operated in production. You will learn step by step, from designing agent architectures with LangGraph to State Management, Tool Calling, API and MCP integration, natural-language database control, RAG implementation, semantic search, Few-shot Learning, Reflection, and Fine-tuning. You will also learn how to build multi-agent collaboration structures, use the Supervisor pattern and Actor-Critic strategies, implement asynchronous communication, create automated evaluation systems, and establish Quality Gates through real-world projects. Finally, you will learn the MLOps and AI Agent operations strategies required in real production environments, including monitoring based on Metrics, Logs, and Tracing; Shadow Deployment; Canary Deployment; Drift Detection; RCA automation; and A/B testing. By the end of the course, you will be able to directly design, develop, and operate high-performance AI systems that can be applied to real-world services using the latest AI agent technologies.

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.

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.

Simple tutorials alone make it difficult to apply in practice. I will clearly pass on my professional know-how, covering complex state management and multi-agent design methods.

Instead of writing longer prompts, I create rule files, logs, permissions, hooks, and validation routines one by one whenever something goes wrong in a real project. With a news alert bot that I actually built and deployed to a server in five days, 211 screenshots and 87 instructions exactly as originally written.

Can I execute the AI’s decisions as is? Learn how to run Laya directly to verify its decisions, then connect them to code rules to divide the process between automation and human review.

This is a tutorial-style Claude Code development course that beginners and those new to development can easily follow. Based on experience teaching planners, designers, and non-developers in offline classes, the course covers everything in one continuous flow—from beginner examples not covered in books to intermediate development examples. Using Claude Code, you will experience the step-by-step development process, starting with Hello World and progressing to a lucky draw, a device-optimized café menu management web page integrating Claude Design with Excel data, and a SaaS web application that can be connected to a database and deployed to cloud services. Tutorials are provided at each stage—theory, practice, and projects. Through hands-on exercises across 6 levels, you will learn AI-collaborative development methodologies and experience the entire development cycle, including cloud deployment and operations.

Learn how to efficiently manage multiple AI coding agents, including Claude Code, Codex, and pi, from a single screen. Starting with tmux concepts, you’ll practice using Herdr’s sessions, panes, plugins, and CLI to build an agent workflow that keeps your work running even when your SSH connection is interrupted. Complete the essential development environment for the Agent era in just one day.

Design by me, code by AI: Learn object-oriented design with Unity 6 and C#, Copilot / Claude prompting, and AI code verification to complete a 60-second survival 3D game. Become a game developer who knows how to work with AI.

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.

AI is only as good as you are. Learn vibe coding properly in three steps: how to use AI → essential foundational knowledge → project development. For those who want to learn vibe coding the right way, we deliver the core concepts that remain unchanged regardless of which AI you use, broken down into bite-sized pieces.

AI agents can feel vague, right? We’ll share practical problem-solving know-how from real-world experience, covering everything from prompts and loops to graph engineering systems.

Can you create a service with your ideas even if you don't know how to code? With AI, it is possible! In this course, you will experience the entire process of turning an idea into a real web service using "Vibe Coding" tools used in the industry, such as Gemini, Lovable, Antigravity, Cursor, and Claude Code. You won't just learn how to use the tools; you will master a new way of service development in the AI era—from planning and deploying to integrating payments. Point 1. Master 5 Core Vibe Coding Tools - Hands-on practice with core features and applications of Gemini, Lovable, Antigravity, Cursor, and Claude Code - Understanding the Vibe Coding development method of collaborating with AI Point 2. Building a Real Service Without Coding - Hands-on process of planning and implementing a book recommendation web service - Understanding the entire service creation flow: Idea → Development → Deployment Point 3. Practical Skills for Service Launch and Operation - Understanding domain purchase, server setup, and the deployment process - Learning core operational technologies such as payment module integration and SEO settings

Learn how to ask ChatGPT for the results you want and verify the sources and outcomes of the materials. This is a 70-session course that begins with hands-on practice in documents, data, and writing, then progressively expands to the OpenAI API, RAG, agents, evaluation, and operations.

Learn what JEV is in simple terms first. Then follow the process of checking the results in the TypeSafe AI Playground and creating a Mac app that recommends emojis matching a sentence by making verbal requests to Claude Code. From signing up and connecting your API key to making your code public on GitHub, learn together through five videos and learning materials that include screen captures and prompts you can copy.

We invite you to become a ‘Top-Tier Enterprise AI Systems Architect’ Do not remain a micro-level technician (Prompt Writer) who merely assembles libraries created by others or polishes prompt sentences. From mathematical first principles to runtime control-loop kernels and autonomous recovery infrastructure — through 40 years of practical engineering insight that has driven industrial operations in South Korea, I will firmly guide you to become a top-level ‘Enterprise AI Systems Architect’ who protects your company’s business and digital sovereignty. Now, begin the great journey of transforming uncontrollable AI into a perfect industrial core. “Why does an AI that ran perfectly in a demo start spouting strange nonsense or bring the pipeline to a halt as soon as it is deployed to production?” “Why do AI projects that so many companies launch with great enthusiasm ultimately fail to escape the ‘PoC (Proof of Concept) swamp’ and get abandoned?” These are the most desperate questions that countless developers and systems architects I have met in the field have asked me. Hello. I am Hongjip Kim, who spent more than 40 years in the powertrain R&D division of the South Korean automotive industry (including 17 years as an executive in Hyundai Motor Group R&D), led the export of engine and drivetrain technologies worth 130 billion won, and commanded operations as the CEO/CTO of a listed mid-sized manufacturing company. From the perspective of an engineer who has spent decades in mechanical engineering and precision-control environments, a ‘risk of fatal uncertainty’ lurks behind today’s frenzy to adopt generative AI. In mission-critical industrial environments where even a mere 0.1% error or mistake can directly result in the destruction of physical equipment worth hundreds of millions of won and an enterprise-wide shutdown, integrating a probabilistic chatbot that simply relies on probability to generate plausible text directly into a service is like carrying a ticking time bomb into a fire. This course was designed to impart the “practical engineering methodology for training uncontrollable probabilistic AI into the most robust industrial control core, one that allows not even 0.000% of syntax errors.” 1. The 3 Major Fatal Bottlenecks You Face in the Field (Problem) Many engineers attempt to challenge production environments using an approach limited to one-off prompt tuning (Vibe Prompting), only to become frustrated when they encounter the following 3 structural defects: Finite Context and ‘Lost in the Middle’: As conversations or multistep executions grow longer, critical system instructions are pushed aside and the context window is exhausted, causing the system to lose its memory and amplifying hallucinations. Nondeterministic Outputs and Cascading Pipeline Collapse: Tiny probabilistic fluctuations, such as one missing closing bracket in JSON or an incorrect type, can paralyze legacy ERP/CRM API calls and destroy data integrity. Untrusted Code Execution and Infrastructure Security Bankruptcy: When scripts autonomously generated by an agent run in a non-isolated host OS environment, they create risks such as kernel escapes and sensitive-data leakage. As such, AI malfunctions in industrial environments are not merely quantitative accuracy problems; they become a massive financial disaster in the form of asymmetric business loss (Asymmetric Business Loss). 2. ‘How’ to Solve These Problems Perfectly (Solution) This course differs fundamentally from commercial courses that teach only how to use fragmented off-the-shelf tools. By combining 40 years of hands-on field expertise with computer systems engineering, it delivers 3 hardcore architectures for vertically integrated, system-level control of probabilistic AI: ① Move Beyond Prompting to ‘LLM-OS & Context Orchestration’ Following Andrej Karpathy’s paradigm, redefine the LLM not as a conversational respondent but as the central computational core (CPU) of a computer. Systematically organize the context window as ultra-low-latency volatile RAM, the internal vector DB as Disk, and external APIs as an I/O bus. Through MemGPT hierarchical virtual-memory paging, preserve critical state without saturation even during infinite conversations, while scaling a dynamic agent network through MCP-based Liquid Swarm MAS, minimizing token costs. ② ‘Deterministic Harness Engineering’ That Constrains Probabilistic Hallucinations to 0.000% Leave the language model’s creative flexibility open only during the Reasoning phase, while firmly confining the physical output layer that interacts with external systems using mathematical Boolean algebra and compilers. Apply EBNF / XGrammar-based CUDA logit masking to forcibly block the generation probability of invalid tokens at P = 0.000%. Form a physical security isolation ring so that code generated by agents runs only once inside a Firecracker MicroVM micro-virtualization sandbox with 5ms snapshot restoration capability. ③ ‘High-Reliability MLOps·LLMOps Autonomous Recovery Infrastructure’ Without Wasting GPU Resources Build vLLM PagedAttention and S-LoRA hot-swapping to suppress idle VRAM waste to below 4%. When a multi-agent API fails, restore data consistency 100% through SagaLLM reverse compensation transactions. Through an OpenTelemetry/Langfuse distributed observability network, defend system availability by executing an unmanned automatic canary rollback whenever a decline in the RAGAS faithfulness score (Data Drift) is detected. 3. Practical Value That Drives Spiral Growth (Pedagogy & ROI) This course is systematically designed according to the 5 levels of Bloom's Taxonomy. Starting from simple theoretical recall (Remember), learners directly code and validate a 5-stage debugging pipeline (analyzing deceptive baseline trap source code ➔ deconstructing adversarial engineering ➔ establishing a Robust integrity pipeline ➔ calculating the TEI ROI formula ➔ SOTIF/ISO 42001 governance). Going beyond the intuitive satisfaction of simply “working well,” I will apply the Forrester TEI (Total Economic Impact) financial model to visualize, from an executive perspective, how much the AI system you build reduces your company’s rework cost (Rework Cost), avoids failure risks worth hundreds of millions of won, and proves an ROI of more than 200%.

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.

This course is a 37-lesson, approximately 14-hour program that covers OpenAI’s AI coding agent, Codex, from start to finish. AI coding tools are now commonplace. However, most users remain at the level of accepting autocomplete suggestions or asking questions in a chat window. Agentic tools like Codex can do much more than that. They can read an entire project, modify multiple files simultaneously, run tests, and find and fix errors on their own. The problem is that they require an equivalent level of control. If you do not know what to allow and what to block, or how to teach the tool your project’s rules, you will end up cleaning up the code it creates afterward. This course focuses on how to establish that control. In the beginner section, you will learn installation and your first conversations, file editing and session management, and slash commands, while building a foundation in prompt writing. Through hands-on practice, you will internalize three principles: making clear requests, breaking down tasks, and verifying the results. The intermediate section is where the main content begins. You will configure behavior with config.toml, teach project rules with AGENTS.md, and manage memories with Memories. You will design safety boundaries yourself by combining the sandbox with four types of approval policies. The course then covers thread separation and parallel work, planning mode, connecting MCP servers, and creating custom skills based on SKILL.md. Finally, after covering web searches and Git automation, VS Code and Cursor integration, and hands-on FastAPI practice, you will examine Codex’s internal protocol, the SQ/EQ queue model. Understanding how the tool works changes how you respond when problems arise. The entire course follows the process of building a single service called TaskFlow. Rather than learning each feature in isolation, you will experience, in sequence, when and why each one is needed in a real project.