This live challenge is available to both individual customers and employer-sponsored training customers
.
Individual customers are not eligible for a refund. Corporate training customers, please check the application and refund procedures below.
- Participate in 1 day out of 2
- Submit 2 of the 4 missions required
- Completion requires meeting both requirements 1 and 2
- If the minimum is not met, submit 3 out of 4 missions
- Proceed when the minimum number of participants, 3, is reached
- If fewer than 3 participants, arrangements for carrying over participation or a refund will be made through consultation with the manager
- Two screenshots in total (directly tied to the completion criteria)
- 1 session · Within 30 minutes after starting
- 2 sessions · About 30 minutes before the end
- Camera must be ON when taking screenshots (with your face visible)
- Completion is not possible if your face is not visible
gov.partnership@inflab.com
Designing AI Agents that make decisions and take action independently
It doesn’t stop at calling an LLM.
You will build an Agent that combines RAG and Tools to get the job done.
Building an AI Agent,
do you ever have
these concerns?
take action on their own.
6 hours later, you’ll have an Agent that gets the job done
for you.
100% Live in real time
Build it together live with the knowledge sharer. Ask questions as soon as you get stuck and solve them right there.
Close mission support
Each session has a mission. You’ll pass with close support from the operations manager and feedback from the knowledge sharer.
A total of 6 hours, completed in 2 sessions
Two 3-hour sessions. From Agent fundamentals to workflow automation Agents, you’ll complete everything in one course.
Building a RAG System
Hands-on Project
Each lesson
produces a working Agent
A Workflow that completes tasks
from start to finish
Going beyond LLM calls to judgment, branching, and completion, you’ll design Agent workflows that finish tasks from a single instruction.
When to use RAG and
when not to use it
Learn design criteria for distinguishing situations that require search from those where reasoning is sufficient, achieving both accuracy and speed.
As the Agent's
action through the tool
Complete an Agent ready for immediate practical use with a ReAct structure that interprets results and determines the next action.
Introduction to the Knowledge Sharer
CEO of Dapada Co., Ltd., an AI and data education company
Adjunct Professor, Department of Computer Software, Induk University
Numerous lectures and training sessions on LLMs/Agents for large corporations, financial institutions, and public institutions
Operates courses in the LLM field on Inflearn
Book: 『Introduction to LangChain: From RAG Chatbots to Agents』
Book 『Python Deep Learning with TensorFlow』
Book 『Introduction to Python Deep Learning and Machine Learning』
Across a total of 4 modules
apply it to your work
Each module follows the structure: theory → hands-on practice → mission.
- Concepts and Principles of LLM-Based AI Agents
- LangChain Basics
- Key Prompt Engineering Techniques
- Create Your Own Expert Chatbot
- Understanding RAG Architecture
- Document preprocessing and Vector Database construction
- Developing a RAG-based Q&A Agent
- Building a Company Document Search System
- Tool/Function Calling Concepts and Implementation
- Hands-on practice implementing various Tools
- ReAct Agent Design
- Building a Smart Assistant Agent
- Advanced Agents Built with LangGraph
- State Management·Memory Strategy
- Create a Work Automation Agent
A live course created and operated by Inflearn,
where countless people learn
90% of the training costs refunded
If you’re a small or medium-sized business, you can take this course with government support.
the rest is covered by government support
Guaranteed minimum for companies with fewer than 500 employees
Settlement handled by Inflearn
The application must be submitted by the HR or training manager under the company’s name. It is available to companies eligible for priority support (employees currently enrolled in employment insurance), and applications may close early once the budget is exhausted.
Now delegate tasks to an Agent
Build an Agent structure that can make decisions and take action on its own.
Ask questions and solve problems as soon as you get stuck.