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, 25 Jun 2026 00:00:00 GMT https://www.youngju.dev/blog/ai/2026-06-25-agentic-coding-code-as-harness.en https://www.youngju.dev/blog/ai/2026-06-25-agentic-coding-code-as-harness.en This post reframes code not as an LLMs final artifact but as the execution harness through which an agent interacts with its environment. Centered on verification loops, tool calling, and execution feedback, it lays out agent design patterns and the pitfalls to watch for. Thu, 25 Jun 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) aiagentic-codingllm-agentstool-callingreactswe-benchharness https://www.youngju.dev/blog/ai/2026-06-25-agentic-coding-code-as-harness.ja https://www.youngju.dev/blog/ai/2026-06-25-agentic-coding-code-as-harness.ja コードを単なる LLM の最終成果物ではなく、エージェントが環境とやり取りする実行基盤(harness)として捉え直します。検証ループ、ツール呼び出し、実行フィードバックを中心に、エージェント設計パターンと落とし穴を整理します。 Thu, 25 Jun 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) aiagentic-codingllm-agentstool-callingreactswe-benchharness https://www.youngju.dev/blog/ai/2026-06-25-agentic-coding-code-as-harness https://www.youngju.dev/blog/ai/2026-06-25-agentic-coding-code-as-harness 코드를 단순한 LLM의 최종 산출물이 아니라 에이전트가 환경과 상호작용하는 실행 기반(harness)으로 다시 바라봅니다. 검증 루프, 도구 호출, 실행 피드백을 중심으로 에이전트 설계 패턴과 함정을 정리합니다. Thu, 25 Jun 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) aiagentic-codingllm-agentstool-callingreactswe-benchharness