https://www.youngju.dev/blog 천천히 올바르게. AI Researcher & DevOps Engineer Youngju's tech blog. GPU/CUDA, LLM, MLOps, Kubernetes AI workloads, distributed training, and data engineering. ko fjvbn2003@gmail.com (Youngju Kim) fjvbn2003@gmail.com (Youngju Kim) Thu, 02 Jul 2026 00:00:00 GMT https://www.youngju.dev/blog/culture/2026-07-02-how-to-use-ai-agents-2026-claude-code-mcp-automation-multi-agent-deep-dive.en https://www.youngju.dev/blog/culture/2026-07-02-how-to-use-ai-agents-2026-claude-code-mcp-automation-multi-agent-deep-dive.en In 2026, AI agents are everyday tools, not demos. This guide covers what an agent actually is (LLM + tools + loop), workflows versus agents, Claude Code in depth (CLAUDE.md, Skills, Hooks, parallel subagents), when to reach for Cursor, Devin, or Copilot Workspace, task decomposition with tests as the gate and a git safety net, building and vetting MCP servers, automating email, meeting notes, and research, the real GitHub Issue to blog post pipeline behind this site, orchestrator-worker and evaluator-optimizer patterns, hallucination defenses and human-in-the-loop design, model tiering and prompt caching, and prompt injection defense — in 26 chapters. Thu, 02 Jul 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) ai-agentsclaude-codemcpautomationmulti-agentproductivitycoding-agents https://www.youngju.dev/blog/culture/2026-07-02-how-to-use-ai-agents-2026-claude-code-mcp-automation-multi-agent-deep-dive.ja https://www.youngju.dev/blog/culture/2026-07-02-how-to-use-ai-agents-2026-claude-code-mcp-automation-multi-agent-deep-dive.ja 2026年、AIエージェントはデモではなく日常の道具になった。エージェントの定義(LLM+ツール+ループ)とワークフローとの違い、Claude CodeのCLAUDE.md・Skills・Hooks・並列サブエージェント、Cursor・Devin・Copilot Workspaceの使い分け、タスク分解とテストをゲートにした検証ループ・gitセーフティネット、MCPサーバーの自作とセキュリティ、メール仕分け・議事録・リサーチの自動化、GitHub Issueひとつでこのブログが記事を自動公開する実際のパイプライン、オーケストレーター・ワーカーや評価者・生成者などのパターン、ハルシネーション対策と人間の介入設計、モデルティアリングとプロンプトキャッシング、プロンプトインジェクション防御まで、26章で整理する。 Thu, 02 Jul 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) ai-agentsclaude-codemcpautomationmulti-agentproductivitycoding-agents https://www.youngju.dev/blog/culture/2026-07-02-how-to-use-ai-agents-2026-claude-code-mcp-automation-multi-agent-deep-dive https://www.youngju.dev/blog/culture/2026-07-02-how-to-use-ai-agents-2026-claude-code-mcp-automation-multi-agent-deep-dive 2026년, AI 에이전트는 데모가 아니라 일상 도구다. 에이전트의 정의(LLM+도구+루프)와 워크플로우와의 차이부터 Claude Code의 CLAUDE.md·Skills·Hooks·병렬 서브에이전트, Cursor·Devin·Copilot Workspace의 용도 구분, 작업 분해와 테스트 게이트·git 안전망, MCP 서버 제작과 보안, 이메일·회의록·리서치 자동화, GitHub Issue 하나로 이 블로그가 글을 발행하는 실제 파이프라인, 오케스트레이터-워커·평가자-생성자·토론 패턴, 환각 대응과 인간 개입 설계, 모델 티어링과 프롬프트 캐싱, 프롬프트 인젝션 방어까지 26개 챕터로 정리했다. Thu, 02 Jul 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) ai-agentsclaude-codemcpautomationmulti-agentproductivitycoding-agents