Blog

1. Introduction The problem I faced while participating in the Medical System MSA Transition Project was data duplication. The new MSA system (PostgreSQL) and the existing legacy system (Oracle) had to be operated side by side, and there was a requirement to maintain data consistency in real-time while both

This article provides a hands-on guide to implementing and applying 'Skills', a Claude Code feature designed to automate repetitive workflows and establish consistent execution patterns. We will explore the structural limitations that can arise when attempting to create Skills solely through prompts and examine why a more

This article explores Skills, a core capability of Claude Code built upon and extended from Anthropic's Agent Skill standard. By encapsulating recurring workflows into reusable operational playbooks, Skills enable AI agents to perform tasks with greater consistency, efficiency, and reliability. We will examine how this approach helps standardize

When many teams decide to adopt a design system, the first thing they do is open Figma and start creating components. However, it is not uncommon to witness cases where the system fails to take root in practice and becomes ineffective. This often stems from viewing the design system through

The moment I thought, "Once I attach OCR, it will be done," is when the real problem-solving began. To pre-validate the pipeline for structuring unstructured documents, I chose a math problem PDF as a test case. This was suitable data for simultaneously verifying layout analysis and

1. ag-Grid data update issue Data tables used in practical projects rarely offer only simple query functions. Particularly in admin systems or work platforms, it is very common for users to directly modify data or change states within the table. For example, there is a requirement that when a

1. Background of technology selection: Maximizing the given environment (Ag-Grid) and the necessity of TypeScript One of the biggest challenges of the project was to provide a user-friendly interface that allows users to quickly and intuitively query tens of thousands of data entries. Particularly, since it needed to

1. Background of Technology Selection As the requirements for protecting personal data in the system have strengthened, the application of data encryption has become a mandatory task. In particular, personal information such as names, phone numbers, and emails needs to be encrypted when stored, and must be managed securely in

-Understanding React Rendering Timing for Improved Screen Quality- 1. Issues discovered during the operation process: screen flickering phenomenon While handling the frontend operations of this year's project, I organized the previously complex component structure to make it more understandable, and improved the repetitive state handling and style calculation

1. Background of the project and reasons for choosing Modbus TCP The first challenge I faced while conducting the IoT project was reliably collecting data from various equipment on site. The site had heterogeneous equipment with different manufacturers and communication methods, such as PLCs, sensors, and controllers, and it was

1. The Strategic Necessity of PMO for Project Success As the scale of the project increases and the number of stakeholders grows, the difficulty of project management rises sharply. Particularly in large-scale SI (System Integration) projects, numerous organizations such as the client, the contractor, the development team, the operations

Introduction to QueryDSL starting from the limitations of JPA: from setup to dynamic queries 1. Why was QueryDSL necessary? Using Spring Data JPA allows for rapid development of simple query functionalities. This is because you can easily create query methods like findById and findByUserIdAndStatus just by following method naming conventions.

The evolution of AI collaboration infrastructure -From simple context injection to a team-wide AI development and operation platform- Nowadays, AI agents like Claude, Codex, and Cursor write, review, and test code. Their technical capabilities are impressive. However, when working with AI on large-scale platforms, their limitations quickly become

As projects grow in scale and the number of rules increases, token costs rise and context management becomes increasingly difficult. In this lecture, we will explore the modularization of rules (Rules Pattern), which effectively solves these challenges, along with the Auto-Memory feature that enables AI to continuously learn and

Understanding Claude Code’s Memory System: Permanently Retaining Project Context Beyond Sessions This lecture explores Claude Code’s Memory System, a mechanism designed to permanently retain project context even after a session has ended. Traditional context windows (short-term memory) had a fundamental limitation: once a session was terminated using

1. Problem Situation I was implementing a function to view a list of specific users on the admin page, using a retrieval logic that had many conditions and complex sorting criteria. In the retrieval process, not only was data simply being fetched, but also target condition calculations, state determinations, and

Recently, the term “AI agent” has been coming up very frequently. At first, it felt like just another trend, but as I experienced various customer environments, I realized that there is definitely a growing demand for “a business agent engine that operates safely in our environment.” Against this background, we

- Development of an editor to transform vanilla JS based survey forms into a modern structure- In this post, I would like to share my experience in developing a survey form editor for a recent project and the core architecture behind it. 1. Background and Problem Situation The existing survey form

1. Overview During the project, I experienced the issue of increasingly complex management of color and style variables while operating a SCSS-based style system. Initially, simple variable declarations were sufficient, but as the scale of the service grew and various UI components were added, the roles of the variables

Introduction When operating Kubernetes, it is natural to have thoughts like this: "It would be great to be able to see at a glance whether the Pods in the cluster are operating normally and to collect the status of each Pod." What starts as a simple curiosity turns

-Case study of building a video manual service based on ReactPlayer- 1. Project Overview This case is a project carried out to transition the existing PDF-based user manual system to a video content-based service. In the existing system, when users clicked the manual button, the frontend directly accessed

1. Introduction: Why was distributed scheduling necessary? In Vizend, each service was previously handling scheduling individually. This structure works fine in simple environments, but as the services scale, issues such as duplicate execution of the same task running across multiple instances, unrecoverable loss of schedules during failures, and operational complexity

1. Overview and Background During the testing phase of the large hospital next-generation construction project, thousands of logs were continuously generated daily. To quickly identify issues occurring during the testing process and verify quality, it was essential to check the logs daily and categorize and organize the types of

Introduction When you attach AI features to a service, you quickly encounter situations like this. I want to use different ChatModels based on functionality, how should I manage that? I encountered this issue while developing an AI service for recommending tourist attractions. At first, I thought a text-based conversation

During the process of refactoring the frontend code of the last project, we also modified the permission management structure. Permission management is a cross-cutting concern used throughout the service, including in router settings, menu rendering logic, and individual screen components. Through refactoring, we developed a structure that allows us