From Ticket to PR — A Development Pipeline Agent Built with Claude Code

From AWS EC2 backend operations to automatic error fixing, we are revealing the entire development process of Sidabari (https://github.com/cx8537/sidabari), a Claude Code-based automation tool. In this course, we provide all the actual prompts and conversation history used as learning materials, allowing you to experience the entire prompt input process involved in its creation.

Build an AI agent from scratch using Python and a single while loop, without any frameworks. In the introductory section, you’ll add tool design, failures and costs, memory, human approval, evaluation, and a web interface one by one to complete a small coding agent. In the hands-on section, you’ll implement RAG, multi-agent systems, and an MCP server yourself using real business reports from DART, then compare them numerically with LangChain and LangGraph.

Are you just telling Claude Code, “Build it for me”? It works well at first. But as the project grows, the AI modifies the wrong files, forgets the rules, and repeats the same mistakes. In this course, you’ll learn how to leverage **the latest Claude Code** to delegate coding while still keeping the developer in control of **design, permissions, context, and verification**. **Design → Plan → Implement → Test → GitHub PR** Based on the developer’s judgment and review, AI-powered development automation is applied throughout this entire process.

[Let's Build!] Have you ever given up because you were tired of connecting nodes? "Create a daily morning briefing on Slack" — that's all it takes. Claude Code designs it, and the n8n server runs it 24/7 for you. [Let's Operate!] If adopting n8n was easy but managing it felt overwhelming, this lecture is the answer. "Organize everything according to the conventions" — dozens of workflows are tidied up at once. Creation, organization, monitoring, and backup—operate everything using natural language.

The actual sequence of how I organized insurance for all four family members in one day with Claude—after learning from a registered letter from the district office that my father’s mandatory car insurance had been lapsed for a month. I gathered information scattered across six sources and turned it into a Google Sheets ledger, calendar schedule, and one-page card for my parents, while also showing the line where humans handle passwords, identity verification, payments, and consent all the way through.

You may have experienced Claude Code producing different results for the same request each time, violating the rules specified in its instructions, and being overly lenient in approving its own output. While developing platform servers in Pangyo and spending over $1,000 a month on Claude Code, I addressed these issues by building a harness consisting of instructions, Hooks, permissions, and a Sandbox instead of relying on prompts. In this course, you’ll build that harness from scratch, add Subagents, Agent Teams, and headless execution, and leave with a complete setup that you can copy and use as-is in other projects.

The latest trend in generative AI: AI agents! How to stay ahead with Cursor, which handles all your development tasks, and MCP, which expands its functionality!

We invite you to the fascinating world of coding where you analyze and visualize financial statements using only prompts. Without a single line of code, you create and deploy a service in consultation with AI.

Drawing from my own experience of feeling despondent when trying to implement practical code during my first MSA transition—despite knowing the theory—I will help you grow into a developer who guarantees perfect data consistency amidst any system failure by directly rolling back daunting compensation logic through 9-step practical patterns and AI Agent coding.

This course is intended for developers who use Claude Code but only at a basic level, roughly equivalent to chatting with a chatbot. It focuses on explaining the key principles and conceptual understanding needed to use Claude Code effectively.

AI is only as good as you are. Learn vibe coding properly in three steps: how to use AI → essential foundational knowledge → project development. For those who want to learn vibe coding the right way, we deliver the core concepts that remain unchanged regardless of which AI you use, broken down into bite-sized pieces.

Deploy a Spring Boot SNS app to local Kubernetes, and automate deployments with GitHub Actions and Argo CD. Identify the causes of failures through metrics, logs, and traces, and review them based on AI analysis results.

If you’ve found it difficult to explain what’s happening under the hood while using AI and embeddings, this course may be the answer. Drawing on the experience of a practicing AI developer in Silicon Valley, it helps you understand the principles of AI through code by implementing everything from embeddings and Word2Vec to automatic differentiation and transformers yourself.

The starting point for a successful AX (AI Transformation) is not technology, but the leadership's understanding of AI. This course is designed to help executives grasp the overall flow of AI easily and clearly, while covering ways to maximize business productivity through the familiar Google Workspace and Gemini. Moving beyond mere theory, we provide 5-minute hands-on tasks for each session and a 1:1 customized online meeting (30 minutes) with AX Cody to systematically guide your company's tailored AI adoption strategy.

This course covers CI (Continuous Integration) and CD (Continuous Deployment) pipelines, which are one of the four core elements (MSA, CI/CD, DevOps, Container) that make up cloud native applications. Through this course, you can understand and practice the processes needed to build and deploy your own automated pipeline in both local and cloud environments using Jenkins, a CI/CD tool.

SonarQube | SonarCloud | SonarLint – DevOps + Security + QA (Most Widely Used Open-Source Tool) SonarQube is a leading open-source platform for continuous inspection of code quality. It performs automatic code reviews using static code analysis to detect bugs, code smells, security vulnerabilities, and maintainability issues across 27+ programming languages.This course is designed with a learn-by-doing approach, enabling you to gain deep, practical expertise in SonarQube and its ecosystem. Audience: This course is suitable for:Freshers, Developers, Project Managers, Architects, QA Engineers, Support Engineers, DevOps, DevSecOps, InfoSec, and Process Engineers who want to master code quality, security, and CI/CD best practices. Fundamentals & Concepts Introduction to SonarQube, SonarCloud, and SonarLint Purpose and benefits of static code analysis Understanding DevOps & DevSecOps use cases SonarQube architecture, editions, versions, and ecosystem Core SonarQube terminologies and metrics Maintainability, Reliability, and Security concepts Installation & Setup Installation and setup of SonarQube using Docker & Docker-Compose Installation and configuration of Jenkins Installation & configuration of Sonar Scanner Setup of build tools: Ant, Maven, Gradle NodeJS, Python Overview of SonarQube UI and navigation Hands-On Code Analysis Onboarding projects into SonarQube & CI pipelines Running code analysis for multiple programming languages Publishing and interpreting analysis results Reporting code coverage, unit and integration test results Understanding and analyzing: Bugs Vulnerabilities Code Smells Technical Debt Complexity Duplicated lines, files, and blocks SonarLint & IDE Integration Installing SonarLint in: Eclipse IntelliJ IDEA VS Code Configuring SonarLint Connected Mode Real-time code analysis and issue detection in IDEs Quality Management Quality Gates and Quality Profiles Creating and managing custom rules & rule templates Enforcing quality standards across teams Failing builds based on Quality Gate conditions Handling and fixing identified issues Administration & Configuration Project administration User, group, permission, and token management Plugin installation and management Security configuration of SonarQube SMTP configuration and email notifications Branding SonarQube UI with company logo SonarQube Marketplace & system details Security & SAST SAST (Static Application Security Testing) fundamentals Security vulnerability analysis SAST integration with CI/CD pipelines CI/CD & DevOps Integrations Integration with Jenkins (Jobs & Pipelines) Integration with GitHub & GitHub Actions Integration with GitLab & GitLab CI/CD Automating quality checks in CI/CD workflows Failing CI/CD pipelines based on SonarQube Quality Gates Advanced Topics Using the SonarQube Web API for automation, monitoring, and data extraction Best practices for enterprise-grade SonarQube deployments By the End of This Course, You Will Be Able To: Define and manage Quality Gates, Quality Profiles, and Rules Analyze code locally using SonarLint Perform secure and scalable static code analysis Integrate SonarQube with GitHub, GitLab, and Jenkins Enforce code quality and security standards across CI/CD pipelines Confidently administer and customize a SonarQube instance

We are living in an era where AI can create 10 files at once. But if you can’t track where the code was changed, it conflicts with your teammates’ code, and you don’t know how to undo it—then no matter how well you use AI, you won’t be productive. This course is not simply a lesson that lists commands like `git add` and `git commit`. It will help you visually understand the principles behind safely managing the code AI produces and merging your code with your teammates’ code. Two hours from now, you’ll be a developer who can freely track, undo, and merge any code—whether it was created by AI or written by you.

Go beyond a simple system prompt to build an AI character chatbot that remembers users and whose relationship with them evolves, using persona design and Structured Outputs. In this 30-minute hands-on session, you’ll learn how to safely call the OpenAI API based on the provided starter project, process emotions, trust levels, and memories in a verifiable format using JSON Schema and Zod, and use an AI coding agent within defined constraints.

Covers the topics you need to know to work on projects using Kubernetes.

We explore how to create an AI judge by combining knowledge graphs, reasoning systems, and various agent frameworks such as CrewAI, LangChain, and AutoGen, which enable the implementation of LLM-based multi-agent technology.