Blog
AI 에이전트를 위한 보안 생태계 지도: 2026년 필수 오픈소스 도구 20선
웹 브라우징, 도구 호출(Tool calling), 코드 실행, 내부 시스템 접근 및 사용자 대행 작업… LLM이 단순히 텍스트를 생성하는 수준을 넘어 스스로 판단하고 행동하는 ‘AI 에이전트(AI Agent)’ 시대가 본격화되면서, 보안 패러다임 또한 완전히 변화했습니다.
November 7, 2026
Plan Mode Didn't Die — It Moved Inside the Loop
Turning on plan mode before handing work to a coding agent was, until recently, simply the order of operations. Lately I see more people skipping it and just talking to the agent. Is that laziness, or did the approach itself hit a limit? I think it is the second one — but not in the way the “plan mode is dead” posts claim.
October 22, 2026
Prompt Caching: How to Cut LLM Operating Costs Dramatically Without Sacrificing Quality
One of the biggest headaches in operating an AI service is the combination of “input token cost” and “response latency.” That worry only deepens for services that reference long documents or rely on complex system instructions. You can’t shrink the context without hurting answer quality, and when the cost becomes unbearable, the first optimization strategy you should reach for is prompt caching.
July 1, 2026