inflearn logo
inflearn logo

All Knowledge for AI Agent Development [Early Bird]

Stop copy-pasting code! 🙅‍♂️ This is a "real" conceptual lecture that dives deep into everything from how agents work to their architecture and design philosophy. Beyond just learning how to build them, I will help you develop an eye for designing entire systems. Build a solid foundation here that remains unshakable amidst the technology trends of 2026! 🧠✨

강의소개.상단개요.수강생

난이도 입문

수강기한 무제한

prompt engineering
prompt engineering
LLM
LLM
LangChain
LangChain
RAG
RAG
AI Agent
AI Agent
prompt engineering
prompt engineering
LLM
LLM
LangChain
LangChain
RAG
RAG
AI Agent
AI Agent

강의상세_배울수있는것_타이틀

  • 'Architecture Insight' that pierces through the system! Beyond simply implementing functions, you can perfectly understand and design the 8 core layers of an agent (brain, memory, tools, safety, etc.).

  • The 'design capability' to control probability! Learn how to confine unpredictable LLMs within State Machines and Graphs to make them operate exactly as you intend.

  • A 'preview' of 2026 technical standards! You can master the latest technology trends and standards, such as MCP, GraphRAG, and Agentic Workflow—the hottest topics right now—and stay one step ahead of others.

  • 'Operational know-how' that goes beyond a demo! It's not just about building it and being done. Gain production-level operational knowledge on how to evaluate (Eval), trace (Tracing), and solve problems.

Early Bird Notice!

I am currently editing some parts where the speech is too fast during slide transitions!!

I'm also working on the remaining sections, so the upload is being delayed. Sorry! T_T!

It is scheduled to be uploaded on the evening of February 10th!


🚀 Course Introduction: Time to graduate from being a prompt-crafting artisan!

Are you still begging a chatbot (LLM) "please do this" using only prompt engineering? 🙏 Now it's time to build an 'AI Agent' that plans on its own, uses tools, and gets the job done.

Stop copy-pasting code! 🙅‍♂️ This course is an 'engineering' class where you learn to control the probabilistic nature of LLMs as you wish, and a 'design' class where you can get ahead on MCP, GraphRAG, Agentic Workflow, and LangChain, which will become the mainstream in 2026.

Take all the real technology hidden behind the flashy demos right here!


✨ Key Highlights of This Course

  • 🧱 8-Layer Anatomy: From the agent's 'brain' to its 'operation,' I'll pass on the 8-step secret to building a rock-solid system.

  • ⚙️ Taming AI: Dealing with unpredictable AI? I'll show you exactly how to keep it in check and make it follow instructions perfectly using State Machines (FSM) and graph technology.

  • 🔮 Stay Ahead: Get a head start on the trending MCP and GraphRAG concepts!

🎧 "Crystal clear even at 2x speed!"
For busy developers 🏃‍♂️, we used AI voice enhancement so the pronunciation remains perfectly clear without any distortion, even at double speed. Because your time is precious :)

Recommended for these people

Backend/Full-stack developers who have reached their limits

👨‍💻 "AI keeps getting stupid when I give it complex tasks..." 👉 Graduate from simple integration! I'll show you how to build a 'tenacious agent' that fixes its own errors and gets the job done no matter what.



AI engineers who want more than just RAG

🤖 "Aren't you bored of chatbots that just search documents and give answers all day?" 👉 Level up beyond simple search (RAG) to 'Multi-Agents' that use tools freely and collaborate with each other!



Tech PMs who need to lead technology trends

📅 "I wonder if it's actually impossible or if the technology just isn't there yet." 👉 I'll pinpoint the real limitations of AI and the standard technologies for 2026. Now you can plan projects while having fact-based conversations with developers.

💡 What will you gain after listening?

  • 🤷‍♂️ Instead of saying "There's nothing we can do because it's AI," you can coolly respond, "Let's solve it with caching and guardrails."

  • 🏗️ You can build a Cyclic architecture yourself using the currently trending LangGraph.

  • 🛠️ Not just a toy project, you will be building a robust service that is actually ready to be sold to paying customers.

📚 What you'll learn (4 key points)

Treating AI like a component (Brain & Action)

Don't put LLMs on a pedestal. They are just components! Master the tool usage and the infinite loop of Think → Act → Observe.


Planting Smart Memories (Context & Memory)

One search and done? No way. We will build a persistent RAG that re-searches until it finds the answer, along with a 'Memory System' that remembers the user.


The Magic of Controlling Probability (Control Flow)

How to trap randomly behaving AI within if-else statements and state machines! You will even learn multi-agent collaboration patterns that solve complex problems with ease.

Impenetrable Shield and Operations (Ops & Security)

From preventing hacking (prompt injection) to automated evaluation systems where AI grades AI, and even error tracking! Let's preemptively block the issues that explode in real-world practice.

Notes before taking the course

Learning Materials

  • It will be provided via a Notion link!

Prerequisites and Important Notes

  • Python Basics: If you can look at code and understand the general flow, you're OK!

  • Web Basics: You just need to know things like "what an API is" and "what JSON looks like."

  • Curiosity: The passion to think, "I want to try automating this with ChatGPT!" is more than enough. 🔥

강의소개.콘텐츠.추천문구

학습 대상은 누구일까요?

  • "I'm tired of just connecting APIs" 👉 For backend/full-stack developers who want to go beyond simple integration and design robust, complex systems themselves.

  • "I need the next step after RAG" 👉 For AI engineers who want to go beyond simple chatbots and create 'real agents' that handle complex tasks on their own.

  • "I want to know the technical boundaries" 👉 Tech PMs who want to plan feasible services by identifying the clear limitations and possibilities of AI.

선수 지식, 필요할까요?

  • Python Basics

  • Basic web knowledge: It is helpful to know what an API is and what JSON data looks like.

  • LLM Experience: As long as you have experience chatting with models like ChatGPT or Claude and have the curiosity to think, "I want to automate something with this," that's all you need!

강의소개.지공자소개

Nice to meet you!

I am Haeyeo, someone who explores the infinite possibilities of AI and computer science and wishes to share that journey with all of you.

During my undergraduate years, my passion for my major was so intense that I was nicknamed a 'Computer Science Addict.' I graduated at the top of my class with a major GPA of over 4.4. I then earned my Master's degree in AI from Seoul National University and further deepened my expertise through a doctoral program.

However, as I felt as much of a fascination for solving real-world problems with AI as I did for theoretical exploration, I took a break from my doctoral studies to gain valuable hands-on experience by working on AI-based LLM and video analysis projects at a startup.

Currently, I am working as an LLM project developer and PM at one of the top three conglomerates in Korea, contributing to creating positive changes that AI technology will bring to our lives. I will generously share with you the challenges I faced, the problem-solving processes I went through, and the vivid know-how I gained in the field. I will be your reliable guide on this journey into the exciting world of AI.

Inquiries and Proposals: haeyeo.open@gmail.com

더보기

커리큘럼

전체

10개 ∙ (강의상세_런타임_시간 강의상세_런타임_분)

강의 게시일: 
마지막 업데이트일: 

수강평

아직 충분한 평가를 받지 못한 강의입니다.
모두에게 도움이 되는 수강평의 주인공이 되어주세요!

비슷한 강의

같은 분야의 다른 강의를 만나보세요!

강의상세.할인문구

$39,600.00

40%

$51.70