Understanding Core LLM Theory Through Its Architecture -The Operating Principles of ChatGPT, RAG, and Agents at a Glance-

You use ChatGPT, but haven’t you found it difficult to explain why it produces answers like these? “I know terms like RAG, agents, and fine-tuning… but it’s difficult to explain them precisely.” “When I hear LLM-related terminology, I’m at a loss for words.” “Explanations of concepts in AI meetings are always vague.” This course was created specifically for people like you. This is a theory course designed to help you understand LLMs not as ‘tools,’ but as ‘structures.’ Rather than teaching you how to use ChatGPT or Gemini, it gives you a framework for explaining why they work the way they do.

(4.5) 24 reviews

194 learners

Level Beginner

Course period Unlimited

ChatGPT
ChatGPT
prompt engineering
prompt engineering
LLM
LLM
RAG
RAG
AI Agent
AI Agent
ChatGPT
ChatGPT
prompt engineering
prompt engineering
LLM
LLM
RAG
RAG
AI Agent
AI Agent

Reviews from Early Learners

4.5

5.0

HJ

100% enrolled

This is really great material for grasping the overall concepts! How can I receive the lecture materials?

5.0

Goldie

63% enrolled

It is good for building a solid foundation.

5.0

leckar1231

100% enrolled

It would be even better if lecture materials were provided and Q&A responses were addressed. The content is truly great for grasping the overall concepts!

What you will gain after the course

  • Structural thinking to understand the process by which an LLM generates answers

  • Criteria for not confusing key concepts such as prompts, RAG, and agents

  • An understanding that allows you to accurately follow discussions related to AI

  • Realistic judgment informed by the limitations and parameters of LLMs


Master the principles behind how LLMs work
A comprehensive theory course to make them your own

Gain a deep understanding of LLMs, the key technology driving the AI era.


Have you ever wondered how ChatGPT or Gemini work, even though you use them?
This course explains everything step by step, starting with the basic concepts of LLMs.

It helps you understand the core technologies of prompts, RAG, and agents without difficulty.

How LLMs work

Theory Lessons to Make It Your Own

Although you use ChatGPT and Gemini,

Have you ever wondered why it gives the answers it does?

This course covers everything from the basic structure of LLMs to their core concepts.

Explained with a focus on understanding, without complex formulas.

Not only Transformer and Self-Attention, but also

Prompts, RAG, and Agents

You can naturally connect and understand how they work inside an LLM.

Not how to use tools, but

This course helps you develop criteria for evaluating AI.


This course helps you understand the thought structure of LLMs,

To make use of the latest technologies, such as prompts, RAG, and agents

It is a course that lays the foundation.

What makes this course different?

This course does not simply cover how to use tools or various tricks.

LLMs

  • how it understands context and

  • Why hallucinations occur and

  • why prompts, RAG, fine-tuning, and Agents emerged.

We explain the theory behind the key concepts step by step, focusing on structure without formulas.

It is structured so that you can connect and understand core concepts such as Transformers, Self-Attention, tokens, and embeddings
through an intuitive flow, rather than as a list of papers.


Especially recommended for the following people:

  • If you use ChatGPT but are always confused about LLM concepts

  • Planners and PMs who don’t understand what’s being discussed in meetings when RAG and Agents come up

  • Practitioners considering AI adoption or utilization strategies

  • Those who aren't developers but want to truly understand LLMs

  • Learners looking for an “Introduction to LLM Theory” course

This is not that kind of course.

  • ❌ A course explaining ChatGPT features

  • ❌ A course focused on how to use specific AI tools

  • ❌ A hands-on course focused on automation and work efficiency

This is a theory-focused course that helps you understand the structure and operating principles of LLMs.

By taking this course

From someone who simply uses AI
to someone who can understand and design AI


Structure-focused learning to
understand the core principles of LLMs


Section 1 - Understanding the Basics of Generative AI and LLMs

Explore the basic principles of generative AI and LLMs. Understand how LLMs statistically learn the meaning and context of language from vast amounts of text data to generate natural sentences.

Section 2 - Analysis of LLM Trends and Industry Developments

We examine the latest development trends in LLM technology and analyze future strategic directions for LLMs amid the global AI competitive landscape. This will help provide a perspective on the present and future of LLM technology.

Section 3 - Fundamentals of How LLMs Work

Learn the fundamental operating principles of LLMs. Understand key concepts such as tokens, embeddings, vector spaces, and context windows, and learn about the main output control parameters.

Section 4 - Prompt Engineering Techniques

Learn the basic concepts and advanced techniques of prompt engineering to maximize LLM performance. Develop the ability to write effective prompts by mastering various patterns, including Zero-shot, Few-shot, and Chain-of-Thought (CoT).

Section 5 - Overcoming LLM Limitations with RAG

Learn the RAG (Retrieval-Augmented Generation) architecture to overcome limitations of LLMs, such as hallucinations and a lack of up-to-date information. Understand embeddings and vector databases, the core components of RAG, and grasp the overall workflow.

Section 6 - Strategies for Improving RAG Performance

Learn the metrics and methodologies for evaluating the accuracy of RAG systems, and explore practical techniques for improving performance. Through this, you will investigate ways to enhance the efficiency and reliability of RAG systems.

Section 7 - Fine-Tuning and Parameter-Efficient Tuning Strategies

Learn the basic concepts and application strategies of fine-tuning LLMs for specific tasks or domains. You will also learn efficient model tuning methods through lightweight tuning techniques such as PEFT (Parameter-Efficient Fine-Tuning).

Section 8 - Understanding and Using LLM Agents

Understand the concept and structure of Agents, and explore various types of LLM Agents. Learn through concrete examples how Agents can be utilized in actual work and services.

Section 9 - The Latest Theories of MCP and A2A

We compare and analyze the concepts, operating principles, structures, and applications of MCP (Multi-agent Cooperative Planning) and A2A (Agent-to-Agent), the latest theories in multi-agent systems. Through this, you will understand advanced agent system design.

From Theory to Practice


Point 1. Understand the core principles of LLMs without formulas

Do you use ChatGPT but wonder how it works? This course clearly explains how LLMs operate, focusing on their structure without using formulas. You’ll understand the fundamental reasons behind hallucinations, as well as why prompts, RAG, fine-tuning, and agents are necessary.


Point 2. You can easily understand how LLMs work.

Rather than simply learning how to use tools, the focus is on understanding the thought structure through which LLMs operate.

Through this, you will gain a theoretical framework for understanding and explaining, without confusion, the concepts that appear in AI-related meetings and planning documents. In addition, by understanding the structural limitations of LLMs, such as hallucinations, recency, and context limitations,

You will be able to determine what you can and cannot expect.

Point 3. A theoretical framework for understanding RAG, fine-tuning, and agents

The theoretical foundations of the RAG architecture, which emerged to address the structural limitations of LLMs, including its key components and overall workflow. It also structurally explains what problems fine-tuning and lightweight tuning methods (PEFT, LoRA) were designed to solve, and when they are appropriate choices. Agents are likewise covered not in terms of “how to build them,” but with a focus on why they are needed, their internal structure, and how they differ from simple automation.


Point 4. Developing a perspective for understanding AI

The goal is to move beyond simply using AI and develop a structural understanding of it.

From core LLM concepts such as tokens, embeddings, and context windows to the latest multi-agent theories, including MCP and A2A.

It organizes the material around why this kind of structure emerged.


I use ChatGPT, but I don’t understand why it works this way.
This course was created specifically for people like you.


✔️ Beginners who want to understand the basic principles of LLMs

  • Those who want to structurally understand why LLMs hallucinate (Hallucination)

  • Those who want to know why prompts, RAG, fine-tuning, and agents are needed and how they work

  • Those who want to fundamentally understand how AI works beyond simply learning how to use tools

✔️ Planners and practitioners who want to accurately explain LLM concepts in AI-related meetings or planning documents

  • Those who want to clearly explain the core principles of LLMs (tokens, embeddings, and context windows)

  • Those who want to understand the latest LLM technology trends, including RAG, fine-tuning, and agents

  • Those who want to explore practical ways to use LLMs by considering their limitations when planning and developing AI services and strategies

✔️ Developers and data analysts who want to effectively apply LLMs to their work

  • Those who want to structurally understand LLM reasoning and answer-generation processes and apply them to development

  • Those who want to establish criteria for determining which approach (prompting, RAG, fine-tuning, or agents) is best suited to solving a problem

  • Those who want to overcome LLM limitations (hallucinations, up-to-dateness, and context) and design strategies for applying them to real-world services


Stop using AI as a 'black box.
Become an expert who understands how LLMs work.

Important note before enrolling

  • This course
    focuses on understanding the architecture and operating principles of LLMs (large language models).
    It is a theory-focused course.

    • The exercises are supplementary tools to aid understanding of the concepts.

    • It does not aim to teach how to use specific AI tools or automate practical tasks.

Prerequisite Knowledge and Important Notes

  • A basic understanding of key concepts such as LLMs, Transformers, and Self-Attention is recommended.

  • Familiarity with related terms such as tokens, context windows, and embeddings will help with learning.

  • Curiosity about how AI LLMs work and a willingness to learn are important.



Recommended for
these people

Who is this course right for?

  • Core Principles of LLMs, Transformers, and Self-Attention

  • A summary of essential concepts such as tokens, context windows, and embeddings

  • Core Prompt Engineering Techniques (Zero-shot, Few-shot, CoT)

  • Overall structure of RAG and methods for improving accuracy

  • Differences Between Fine-Tuning and RAG and Criteria for Choosing Them

  • Architecture and Real-World Use Cases of AI Agents

  • The latest trends in multi-agent theory, such as MCP and A2A

Need to know before starting?

  • People who use ChatGPT but are always confused about the concept of LLMs

  • A planner/PM who doesn’t understand what’s being discussed in meetings when RAG or agents come up

  • Business practitioners considering AI adoption or utilization strategies

  • For those who aren’t developers but want to properly understand AI LLMs

  • A learner looking for an “Introduction to LLM Fundamentals” course

Hello
This is HappyAI

5,418

Learners

317

Reviews

52

Answers

4.5

Rating

12

Courses

Lee JinKyu | Lee JinKyu

AI·LLM·Big Data Analysis Expert / CEO of Happy AI

👉Detailed career history can be found at the link below.
https://bit.ly/jinkyu-profile

Hello.
I am Lee Jin-kyu (Ph.D. in AI Engineering), CEO of Happy AI, who has been consistently working with AI and big data analysis in R&D, education, and project fields.

I have analyzed various unstructured data such as
surveys, documents, reviews, news, policies, and academic data
based on Natural Language Processing (NLP) and text mining,
and recently, I have been delivering practical AI application methods tailored to organizations and work environments using Generative AI and Large Language Models (LLM).

I have collaborated with numerous public institutions, corporations, and educational organizations, including Samsung Electronics, Seoul National University, Offices of Education, Gyeonggi Research Institute, Korea Forest Service,
the Korea National Park Service, and Seoul City, and have conducted
more than 200 research and analysis projects across various domains such as healthcare, commerce, ecology, law, economics, and culture.

 


🎒 Inquiries for Lectures and Outsourcing

Kmong Prime Expert (Top 2%)


📘 Bio (Summary)

  • 2024.07 ~ Present
    CEO of Happy AI, a Generative AI and Big Data Analytics Company

  • Ph.D. in Engineering (Artificial Intelligence)
    Dongguk University Graduate School of AI

     

    Major: Large Language Models (LLM)

     

    (2022.03 ~ 2026.02)

     

  • 2023 ~ 2025
    Public News AI Columnist
    (Generative AI Bias, RAG, LLM Utilization Issues)

  • 2021 ~ 2023
    AI/Big Data Specialist Company Stellavision Developer

  • 2018 ~ 2021
    Government-funded Research Institute Natural Language Processing & Big Data Analysis Researcher


🔹 Areas of Expertise (Lecture & Project Focused)

  • Generative AI and LLM Utilization

    • Private LLM, RAG, Agent

    • Basics of LoRA·QLoRA Fine-tuning

  • AI-based Big Data Analysis

    • Survey, review, media, policy, and academic data

  • Natural Language Processing (NLP) & Text Mining

    • Topic analysis, sentiment analysis, keyword network

  • Public and Corporate AI Task Automation

    • Document Summarization, Classification, and Analysis

       


🎒 Courses & Activities (Selected)

2025

  • LLM/sLLM Application Development
    (Fine-tuning, RAG, and Agent-based) – KT

2024

  • LangChain·RAG-based LLM Programming – Samsung SDS

  • LLM Theory and RAG Chatbot Development Practice – Seoul Digital Foundation

  • Introduction to Big Data Analysis Based on ChatGPT – LetUin Edu

  • AI Fundamentals & Prompt Engineering – Korea Vocational Development Institute

  • LDA & Sentiment Analysis with ChatGPT – Inflearn

  • Python-based Text Analysis – Seoul National University of Science and Technology

  • Creating LLM Chatbots Using LangChain – Inflearn

2023

  • Python Basics using ChatGPT – Kyonggi University

  • Big Data Expert Course Special Lecture – Dankook University

  • Basics of Big Data Analysis – Let U In Edu


💻 Projects (Summary)

  • Building a Private LLM-based RAG Chatbot (Korea Electric Power Corporation)

  • LLM-based Big Data Analysis for Forest Restoration (National Institute of Forest Science)

  • Private LLM Text Mining Solution for Internal Networks (Government Agency)

  • Development of LLM models based on Instruction Tuning and RLHF

  • Healthcare, Law, Policy, and Education Data Analysis

  • AI Analysis of Survey, Review, and Media Data

Over 200 projects completed, including public institutions, corporations, and research institutes


📖 Publication (Selected)

  • Improving Commonsense Bias Classification by Mitigating the Influence of Demographic Terms (2024)

  • Improving Generation of Sentiment Commonsense by Bias Mitigation
    – International Conference on Big Data and Smart Computing (2023)

  • Analysis of LLM Technology Perception Based on News Article Big Data (2024)

  • Numerous NLP-based text mining studies
    (Forestry, Environment, Society, and Healthcare sectors)


🔹 Others

  • Python-based data analysis and visualization

  • Data analysis using LLM

  • Improving work productivity using ChatGPT, LangChain, and Agents

More

Curriculum

All

27 lectures ∙ (1hr 31min)

Published: 
Last updated: 

Reviews

All

24 reviews

4.5

24 reviews

  • goldie7님의 프로필 이미지
    goldie7

    Reviews 12

    Average Rating 5.0

    5

    63% enrolled

    It is good for building a solid foundation.

    • leckar12311219님의 프로필 이미지
      leckar12311219

      Reviews 23

      Average Rating 5.0

      5

      100% enrolled

      It would be even better if lecture materials were provided and Q&A responses were addressed. The content is truly great for grasping the overall concepts!

      • leejinkyu0612
        Instructor

        Thank you for the positive review. Please contact leejinkyu0612@naver.com to receive the lecture materials.

    • ymkoo님의 프로필 이미지
      ymkoo

      Reviews 10

      Average Rating 5.0

      5

      33% enrolled

      It is easy to understand, and the clear explanations are very helpful for studying.

      • 20007013611님의 프로필 이미지
        20007013611

        Reviews 1

        Average Rating 5.0

        5

        100% enrolled

        It was a great introductory session for listening to the latest key AI concepts.

        • present29263701님의 프로필 이미지
          present29263701

          Reviews 1

          Average Rating 5.0

          Edited

          5

          100% enrolled

          This is really great material for grasping the overall concepts! How can I receive the lecture materials?

          HappyAI's other courses

          Check out other courses by the instructor!

          Similar courses

          Explore other courses in the same field!