6 AI Agent Team Incident Reports and 5 Checklists

Simple tutorials alone make it difficult to apply in practice. I will clearly pass on my professional know-how, covering complex state management and multi-agent design methods.

As AI rapidly permeates daily life and industries, attack techniques targeting these systems are evolving alongside them. This course is a practical, hands-on program designed to help you understand the latest security threats surrounding Generative AI and LLMs, automate security tasks using AI, and experience LLM jailbreak attacks and defenses firsthand.

Instead of writing longer prompts, I create rule files, logs, permissions, hooks, and validation routines one by one whenever something goes wrong in a real project. With a news alert bot that I actually built and deployed to a server in five days, 211 screenshots and 87 instructions exactly as originally written.

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.

If you follow OpenClaw Parts 1 and 2, you eventually end up making a single agent do everything. As you do this, there comes a moment when prompts get tangled, memory gets mixed up, folders get messy, and you feel stuck, not knowing how to organize things anymore. This lecture is the "Introduction to Multi-Agents (Part 2.5)," designed to help you move one step further from that point. While maintaining a single bot, we will separate roles into two agents—planner and editor—and connect each agent to different workspaces and Telegram forum topics. You will personally build a structure where "different agents respond depending on which room you speak in." By following the hands-on practice, you will have the following in your environment: - A configuration file defining two agents: `content_planner` and `content_editor`, - A content folder structure where planning and drafting are separated, - A Telegram group chat where different agents are attached to specific forum topics, - And one actual draft of an Inflearn course introduction created through the collaboration of the two agents. In short, this is a practical class that helps you design the first step of upgrading your Telegram bot from a "single AI assistant" into a "small AI team with divided roles."

"Turn your Java code into the hands and feet of AI! Practical Agent Development with Kakao PlayMCP and Spring AI" Traditional LLMs are limited to answering based only on their trained data, which can lead to issues with recency and accuracy. In this course, you will learn **MCP (Model Context Protocol)**—the next-generation standard protocol for connecting AI with external tools. Using Spring AI, you will build a server that communicates with various platforms like Kakao PlayMCP through a single implementation. Master the entire process from theory to real-world deployment and platform registration through the 'Proverbs & Psalms Counseling Center (JAMSI)' project, and grow into a true AI agent developer who can empower AI to handle tools independently.

Let's create a service that improves itself even while you sleep! Learn step-by-step how to build a 24-hour vibe coding system using loop engineering with Codex.

Can I execute an AI agent’s decisions as they are? Run the open-source Decision AI model Laya yourself and check its decisions and confidence levels. Learn how to connect code rules with Human-in-the-Loop review to design which decisions should be executed automatically and which require human confirmation. This is a 1-hour 48-minute hands-on course for developers who want to control and validate AI decisions in real-world services, rather than stopping at simply calling an LLM.

This is an introductory course on a mobile AI assistant workflow with vision capabilities: when you send a photo of a receipt via Telegram on your smartphone, OpenClaw and Gemini 2.5 Flash automatically analyze it and organize the data into your PC workspace.

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.

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.

Test the agent’s authorization boundaries for tool calls and RAG search and document access. Using the actual model and training mock tools and documents, observe the approval gates and search permission filters, then complete the Mission 5·6 diagnostic worksheet.

"How is a 1-trillion parameter model trained?" Discover the scaling strategy of Kimi K2.5, revealed directly on stage by Moonshot AI at GTC 2026, in Korean on Inflearn. 2x token efficiency · 1 million token context · 1,000 agent swarm The next step for open-source LLMs is here. * This lecture is released for free through an official collaboration between Moonshot AI, the creator of Kimi, and Inflearn.

It's okay if you don't know a single line of code. We are now in the era of 'Vibe Coding,' where you develop by 'conversing' with AI.

Design by me, code by AI: Learn object-oriented design with Unity 6 and C#, Copilot / Claude prompting, and AI code verification to complete a 60-second survival 3D game. Become a game developer who knows how to work with AI.

How much can you entrust to an AI Agent? IBM engineers answer with evidence they’ve put to the test, covering everything from LLM fundamentals to vendor-specific design, security, and evaluation—and help you create a Skill to take over your work.

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.

We invite you to become a ‘Top-Tier Enterprise AI Systems Architect’ Do not remain a micro-level technician (Prompt Writer) who merely assembles libraries created by others or polishes prompt sentences. From mathematical first principles to runtime control-loop kernels and autonomous recovery infrastructure — through 40 years of practical engineering insight that has driven industrial operations in South Korea, I will firmly guide you to become a top-level ‘Enterprise AI Systems Architect’ who protects your company’s business and digital sovereignty. Now, begin the great journey of transforming uncontrollable AI into a perfect industrial core. “Why does an AI that ran perfectly in a demo start spouting strange nonsense or bring the pipeline to a halt as soon as it is deployed to production?” “Why do AI projects that so many companies launch with great enthusiasm ultimately fail to escape the ‘PoC (Proof of Concept) swamp’ and get abandoned?” These are the most desperate questions that countless developers and systems architects I have met in the field have asked me. Hello. I am Hongjip Kim, who spent more than 40 years in the powertrain R&D division of the South Korean automotive industry (including 17 years as an executive in Hyundai Motor Group R&D), led the export of engine and drivetrain technologies worth 130 billion won, and commanded operations as the CEO/CTO of a listed mid-sized manufacturing company. From the perspective of an engineer who has spent decades in mechanical engineering and precision-control environments, a ‘risk of fatal uncertainty’ lurks behind today’s frenzy to adopt generative AI. In mission-critical industrial environments where even a mere 0.1% error or mistake can directly result in the destruction of physical equipment worth hundreds of millions of won and an enterprise-wide shutdown, integrating a probabilistic chatbot that simply relies on probability to generate plausible text directly into a service is like carrying a ticking time bomb into a fire. This course was designed to impart the “practical engineering methodology for training uncontrollable probabilistic AI into the most robust industrial control core, one that allows not even 0.000% of syntax errors.” 1. The 3 Major Fatal Bottlenecks You Face in the Field (Problem) Many engineers attempt to challenge production environments using an approach limited to one-off prompt tuning (Vibe Prompting), only to become frustrated when they encounter the following 3 structural defects: Finite Context and ‘Lost in the Middle’: As conversations or multistep executions grow longer, critical system instructions are pushed aside and the context window is exhausted, causing the system to lose its memory and amplifying hallucinations. Nondeterministic Outputs and Cascading Pipeline Collapse: Tiny probabilistic fluctuations, such as one missing closing bracket in JSON or an incorrect type, can paralyze legacy ERP/CRM API calls and destroy data integrity. Untrusted Code Execution and Infrastructure Security Bankruptcy: When scripts autonomously generated by an agent run in a non-isolated host OS environment, they create risks such as kernel escapes and sensitive-data leakage. As such, AI malfunctions in industrial environments are not merely quantitative accuracy problems; they become a massive financial disaster in the form of asymmetric business loss (Asymmetric Business Loss). 2. ‘How’ to Solve These Problems Perfectly (Solution) This course differs fundamentally from commercial courses that teach only how to use fragmented off-the-shelf tools. By combining 40 years of hands-on field expertise with computer systems engineering, it delivers 3 hardcore architectures for vertically integrated, system-level control of probabilistic AI: ① Move Beyond Prompting to ‘LLM-OS & Context Orchestration’ Following Andrej Karpathy’s paradigm, redefine the LLM not as a conversational respondent but as the central computational core (CPU) of a computer. Systematically organize the context window as ultra-low-latency volatile RAM, the internal vector DB as Disk, and external APIs as an I/O bus. Through MemGPT hierarchical virtual-memory paging, preserve critical state without saturation even during infinite conversations, while scaling a dynamic agent network through MCP-based Liquid Swarm MAS, minimizing token costs. ② ‘Deterministic Harness Engineering’ That Constrains Probabilistic Hallucinations to 0.000% Leave the language model’s creative flexibility open only during the Reasoning phase, while firmly confining the physical output layer that interacts with external systems using mathematical Boolean algebra and compilers. Apply EBNF / XGrammar-based CUDA logit masking to forcibly block the generation probability of invalid tokens at P = 0.000%. Form a physical security isolation ring so that code generated by agents runs only once inside a Firecracker MicroVM micro-virtualization sandbox with 5ms snapshot restoration capability. ③ ‘High-Reliability MLOps·LLMOps Autonomous Recovery Infrastructure’ Without Wasting GPU Resources Build vLLM PagedAttention and S-LoRA hot-swapping to suppress idle VRAM waste to below 4%. When a multi-agent API fails, restore data consistency 100% through SagaLLM reverse compensation transactions. Through an OpenTelemetry/Langfuse distributed observability network, defend system availability by executing an unmanned automatic canary rollback whenever a decline in the RAGAS faithfulness score (Data Drift) is detected. 3. Practical Value That Drives Spiral Growth (Pedagogy & ROI) This course is systematically designed according to the 5 levels of Bloom's Taxonomy. Starting from simple theoretical recall (Remember), learners directly code and validate a 5-stage debugging pipeline (analyzing deceptive baseline trap source code ➔ deconstructing adversarial engineering ➔ establishing a Robust integrity pipeline ➔ calculating the TEI ROI formula ➔ SOTIF/ISO 42001 governance). Going beyond the intuitive satisfaction of simply “working well,” I will apply the Forrester TEI (Total Economic Impact) financial model to visualize, from an executive perspective, how much the AI system you build reduces your company’s rework cost (Rework Cost), avoids failure risks worth hundreds of millions of won, and proves an ROI of more than 200%.

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!

This is a 4-session intensive course designed to transform Claude from a simple conversation tool into a business automation system. You will learn core concepts such as agents, Claude Code, and workflows through practical use cases, gaining the hands-on ability to build end-to-end automation systems in your own field—even without development knowledge. This powerful weapon is most effective in the hands of non-developers who possess tacit knowledge. On the other hand, if you are a developer, it is good to understand why. An AI tsunami is approaching. Do not be swept away; use this as your weapon.