Hyunjoong Kim's Technology Blog

Practical writing on AI agents, SDLC documentation automation, full-stack architecture, and product validation.

29 results

01Engineering
2026-08-24 · 9 min

Static First: Deferring Decorative WebGL Until the Page Is Ready in Next.js

A practical design for keeping a full-screen WebGL background without making it part of the initial render: static fallback, capability gates, idle loading, visibility and accessibility handling, and policy tests.

Read more
02Engineering
2026-08-23 · 12 min

What Is an AI Agent? How It Differs from a Chatbot and Where MCP Servers Fit

A practical guide to AI agents: the difference between chatbots and agents, the plan-tool-observe-verify loop, how to build a first agent, and what MCP servers actually do.

Read more
03Engineering
2026-08-10 · 9 min

Treat Content Publishing Like a Release: Fail Closed on the Exact PR Head

A bilingual MDX post is more than two text files. This release-oriented workflow makes locale contracts, local assets, CI checks, and the immutable PR head explicit before content reaches production.

Read more
04Engineering
2026-06-08 · 8 min

Designing Agent Observability: Leave Improvement Loops, Not Just Logs

When coding agents become part of team operations, prompts are not enough. This guide shows how to connect traces, decision logs, evals, and regression checks into an improvement loop for AI-native development.

Read more
05Engineering
2026-06-07 · 8 min

An Operating Model for AI Agent Sandboxes: Permissions, Networks, and Worktrees

To use coding agents more often, teams do not need heavier supervision. They need clearer boundaries. This guide turns permissions, network access, worktrees, and CI gates into a practical sandbox operating model.

Read more
06Engineering
2026-06-06 · 10 min

Delegation Packets for AI-Native Teams: The Small Spec Coding Agents Need

Claude Code, Codex, and other coding agents do not need longer prompts as much as they need better delegation packets. This practical guide shows how to define outcome, scope, permissions, verification, and stop conditions before handing work to an agent.

Read more