Hands-on! Building Intermediate AI Agent Services with LangChain and LangGraph: From RAG to Multi-Agents

From PC control to high-level research and app development A guide to building your own 'AI Work Assistant' ready for immediate real-world deployment

Learn the core principles and practical implementation of Classic RAG, Graph RAG, and Agentic RAG. Design a dynamic routing system that optimizes token efficiency and latency, and build a long-term memory system that combines GraphRAG’s relational network reasoning with Agentic RAG’s self-evaluation loop. This course develops advanced RAG architecture design skills that can be applied directly in real-world settings.

We are now in the era of Generative AI! Go beyond simply using the latest technology—grasp the core principles and acquire the knowledge and experience to integrate Generative AI into your daily life!

If you only know LangChain, it's just a chatbot; but if you know LangGraph and Multi-Agent patterns, it becomes a service. An active AI instructor will share the know-how to build operational AI Agent workflows from start to finish—going beyond simple prompt calls to handling tools, maintaining memory, and incorporating human-in-the-loop verification—using 17 practice notebooks and 4 multi-agent patterns (Subagents, Handoffs, Router, and Skills).

Part I LangChain Practice in code how to load a PDF as page-by-page Documents, chunk it, convert the chunks into vectors using embeddings, and index them in a vector store Convert questions into vectors and perform similarity searches (including scores, vectors, and MMR), then wrap the search in a Retriever (Runnable) and connect it to RAG Review practical criteria for assessing search quality, security and governance (including prompt injection), and common mistakes Part II Implement in R the Random Forest algorithm, which overcomes the limitations of decision trees, and accurately interpret model results A complete workflow ready for practical use, including hyperparameter tuning, cross-validation, and ROC curve analysis Part III Building an Automated Classification and Response System for Complaints and Inquiries - Practical Prompt Chains and Multi-Agent Systems

Master Claude Code from the basics to a professional level. Learn core features (CLAUDE.md · subagents · MCP · Hooks, etc.), develop and deploy a real-world service, and wrap up with foundational appendices and advanced-use lessons for non-majors.

This is an introductory course for those using Claude Code for the first time. You won’t do the coding yourself—Claude writes both the code and the configuration files. Starting with creating a psychological test in the browser, you’ll build a household budget using card transaction records, create an escape room game, and make a travel itinerary that connects to external services like Google Calendar and Notion. Since you learn each feature as it becomes necessary, you’ll also understand why that feature is needed.

AI writes on Slack and Notion for me? Work smarter with MCP, which goes beyond the limits of existing AI!

Instead of using more agents, experience firsthand how to entrust them with greater confidence. With Codex CLI, build your own harness so you can delegate work without worry!

Start by installing the Claude desktop app and getting familiar with its interface. Then learn what’s changed with the all-in-one Claude and understand the difference between an AI you ask questions and an AI that does the work. PART 1 In “Giving Clear Instructions,” learn how to delegate work to Claude through a single chat window—from writing work requests and assigning files and research to getting finished documents, slides, and spreadsheets. PART 2 In “Connecting Claude to Your Work,” use memory and projects to teach Claude your rules, and connect it to your real work environment—including data analysis, email, Drive, Calendar, folders on your computer, and web-based work. PART 3 In “Handing Off the Whole Task,” delegate major tasks all at once and use skills, scheduled tasks, and work dashboards to automate recurring work—creating a workflow where people only need to approve the results. Each session centers on the instructor using Claude to handle work they’re actively doing, and includes examples of applying the same methods in corporate and school settings.

Based on the experience of wondering how facial recognition works in offline environments on-site, this course will guide you through building the basic structure of a facial recognition-based access and attendance management system using React + Electron and Python's FastAPI-based DeepFace. Rather than focusing on perfection, we focus on understanding the operating principles and laying the foundation for you to expand into your own personal projects.

This is a tutorial-style Claude Code development course that beginners and those new to development can easily follow. Based on experience teaching planners, designers, and non-developers in offline classes, the course covers everything in one continuous flow—from beginner examples not covered in books to intermediate development examples. Using Claude Code, you will experience the step-by-step development process, starting with Hello World and progressing to a lucky draw, a device-optimized café menu management web page integrating Claude Design with Excel data, and a SaaS web application that can be connected to a database and deployed to cloud services. Tutorials are provided at each stage—theory, practice, and projects. Through hands-on exercises across 6 levels, you will learn AI-collaborative development methodologies and experience the entire development cycle, including cloud deployment and operations.

If you want to create your own AI service without coding, this course is the perfect solution. Using the Dify no-code platform, you can create high-quality AI apps with just your ideas. Instead of complex theory, it's structured around hands-on projects, allowing both AI beginners and working professionals to develop practical skills.

We're building an AI-powered video conferencing application with real-time AI agents, meeting summary features, and post-call functionality.

Create eight games with Codex—no coding experience required—and take them all the way to web launch and store submission. Follow the recommended four-week course at your own pace.

Learn how to efficiently manage multiple AI coding agents, including Claude Code, Codex, and pi, from a single screen. Starting with tmux concepts, you’ll practice using Herdr’s sessions, panes, plugins, and CLI to build an agent workflow that keeps your work running even when your SSH connection is interrupted. Complete the essential development environment for the Agent era in just one day.

The online course “AI Teammates Do It All” is a hands-on program that teaches you how to use AI not merely as an automation tool, but as an “AI teammate” that works alongside you on practical tasks. The course is structured around common real-world workflows, including market research, proposal writing, strategy report creation, brand content visualization, project promotion and operations, and follow-up management. Participants assign various AI tools—including ChatGPT, Perplexity, Copilot, Canva, Gamma, MiriCanvas, and Vrew—as planning partners, strategic research partners, design partners, and operations support partners, and complete actual work deliverables with them. Across 30 sessions, you will learn step by step, from the basic mindset for working with AI to practical prompt writing, market research, proposal and report writing, brand content creation, and project operations. By following the course, you can develop the AI collaboration skills to work on your own like an entire team.

Create a program using the GPT API, and even generate images and videos!

Do you know the basics but feel overwhelmed when it comes to applying them in practice? Drawing on real-world experience, we make complex LLM architectures easy to understand.

Build a Kiwoom Securities API-based automated stock trading system from scratch using the core features of Claude Code (MCP, Agents, Skills). It's perfectly fine for beginners. Get started with Claude Code right now!