Mastering Harness Engineering

This lecture is designed to be easily understood even if you have no prior knowledge of Secure Coding. After covering fundamental secure coding concepts, it focuses on web service security. This course was originally conducted as a special lecture hosted by OO University. It provides over 160 source codes with extensive comments, pinpointing core topics and techniques that can be applied immediately in the field.

Without a single formula or line of code, this penetrates the essence of basic statistics necessary for AI development and application.

It enables junior developers to understand the entire development process, from planning to coding, deployment, and verification, by using AI as a development tool.

It covers a wide range of topics, from prompt engineering theory and practical techniques to the latest application cases and security/ethical issues, providing practical assistance to LLM-based service developers, data scientists, and AI planners alike.

It helps train the "constructive thinking" needed to frame problems.

We present ways to improve RAG performance based on Cognitive Load Theory. To overcome the limitations of existing RAG enhancement techniques, we synthesize various methods by applying the conceptual framework of cognitive load.

You can learn the "service design" concepts and methods required when planning applications or web services based on LLM, a type of generative artificial intelligence (Generative AI).

"I only changed a name, but the code has transformed." I have summarized the core of readable code, 'naming that reads well,' from principles to examples. Easy-to-read names are the beginning of collaboration.

You can quickly understand the basic concepts and fundamental syntax of the C language.

We present various clean coding techniques.

We introduce basic prompt patterns for coding and advanced API prompt patterns for leveraging artificial intelligence.

It explains in detail the various language models developed in the process, starting from the beginnings of natural language processing technology to the latest LLM models.

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 will look at how to collect and analyze user requirements for planning an LLM service.

Explore the limitations of LLMs, the latest technologies to overcome them, and projected future technologies.

We will explore the types of applications and web services that can be built using LLMs.

Explains the reasons why LLM is necessary, the technical background, and basic concepts for LLM planners and LLM application planning managers.

You can enhance your development capabilities by deeply exploring the fundamental principles of large language models like ChatGPT and Claude. You will be able to learn a variety of information and development techniques that are not commonly encountered.

The lecture explains why the harness is more important than the model through the Claude Code architecture. It covers how to design the Claude Code task system using six structures: Context Harness, Permission Harness, Verification Harness, Tool Harness, Subagent & Worktree Harness, and Debugging Harness. Afterward, it connects these concepts to CLAUDE.md, session management, large codebase control, worktree parallel operations, error log analysis, and tracking environment variables and configuration scope issues, establishing the standards for continuously using Claude Code in practical backend and DevOps workflows.

Complete everything from design to TDD and CI with Claude Code. Taking a single feature from one line of spec all the way to main merge.