LLM Application Service Case Analysis (For Product Managers)

Moving beyond prompt engineering and context engineering, we are now entering the era of harness engineering. Harnesses can solve LLM-based challenges that are difficult to achieve with prompts and RAG alone.

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.

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.

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.

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.

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).

For beginner planners/PMs who are about to launch their first product, we will teach you the know-how of writing test cases and practical QA know-how.

There are many pretty landing pages. Landing pages that convert are different. This is a conversion-focused landing page design course designed based on CTR and CVR. It covers how to design clicks and conversions through logic and structure rather than just intuition.

Based on an accurate understanding of black consumers, appropriate countermeasures and strategies are acquired, enabling effective response to black consumers. Furthermore, it is designed to enhance the professionalism of service staff and improve job satisfaction.

This special lecture concurrently prepares for Microsoft AI-900 certification, featuring the latest content reflecting May 2025 exam scope, combining theory and practice, including AI overview, machine learning basics, computer vision, natural language processing, document intelligence, knowledge mining, and generative AI.

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

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.

How does the architecture change when an LLM is integrated into an existing backend? This is an introductory system design course that goes beyond simple LLM API calls to help you understand core AI service components such as Model Routers, LLM Gateways, and Vector DBs, and step-by-step design an operational AI service architecture including RAG and AI Agents. It is designed to help those who want to create their own LLM-based AI services quickly master the design workflow.

In this lecture, we will look at service planning and design methodologies for planning services in the IT/tech field, as well as various soft skills that service planners must have. Finally, we will analyze the service using the example of an AI voice recognition service, a UX service introductory lecture for beginners.

Through AI company reviews, we examine how AI technology will change our present and future through various cases. By examining the necessary elements for carrying out AI projects, we prepare for the upcoming AI Transformation.

In the age of information overload, 'communicating easily' is now the real competitive advantage over 'knowing a lot.' This course goes beyond simply polishing your writing—it develops your 'communication design ability' to identify the core message in a flood of information and deliver it at the right level for your audience. It consists of a compact curriculum of 7 lessons totaling 56 minutes. Say goodbye to boring lectures filled with theory! Through training centered on real-world examples (Before/After), you'll transform into an 'information delivery expert' who communicates best within your organization.

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.

If you know that UT (usability testing) and user interviews are good, but don't know how to do them, gain confidence with this course!

This is a practical lecture on operational tools & back office and data analysis planning, which are tasks handled by game planning, service planning, and business PM positions.

"History repeats itself, strategy evolves. Everything about business improvisation and strategy formulation learned through 300 decisive moments."

A precise analysis of 300 cases applying the 'Rule of Three' within the story, from the Oath of the Peach Garden to the unification of the Three Kingdoms, presented in a 600-page PDF. - Perfect Structuring: Provides overwhelming readability by standardizing every episode into the format of [Original Quote - Rule of Three Analysis - Business Application]. - Vast Archiving: A comprehensive compilation of 300 key milestones across 100 years of history, from the Yellow Turban Rebellion in 184 to the unification in 280, without any omissions. - Practical Utility: Non-exclusive data that goes beyond simple reading material, ready for immediate citation as strategic evidence for proposals, lecture materials, and organizational management.

"Beyond just attending a lecture, we give you the time to 'own' the strategy." The 'Rule of 3', a formula for victory hidden within thousands of figures and complex battles. Change your business landscape with this 483-page PDF textbook and workbook, a culmination of a 30-year strategy expert's systems thinking.

Have you ever created an IR Deck only to receive feedback that it "lacks persuasion"? In most cases, the problem lies not in the design, but in the structure of the message. Based on real-world experience in IR Deck design, I have outlined the criteria for designing a narrative flow from an investor's perspective. This class is designed to help you grow into a hands-on designer who can architect structure beyond just visuals.

This is our 'actual real-world workflow,' and we are releasing the 'onboarding video' used for planners and developers joining our company. It teaches you how to design service screens without a designer and create UX flows and prototypes even if you don't know Figma. Our company maximizes productivity by prototyping quickly during service planning to enable fast decision-making, finalize necessary features, and utilize them directly in front-end development. If the response is positive, I will upload more lectures on other "real-world workflows."

This introductory course for AI engineers is designed to provide a brief hands-on experience of the entire process, from data processing and model development to cloud, MLOps, and ethical considerations. It focuses on building practical skills by helping students understand the process of connecting models to actual services, rather than just creating them. The course includes hands-on exercises and examples so that even those learning AI for the first time can easily follow along.