{"id":"2fa9247c-925a-462a-bc26-6c365a196120","url":"https://api.tumn.com/news/2fa9247c-925a-462a-bc26-6c365a196120","title":"Trust in Depth: Giving agents more autonomy without losing control","summary":"Enterprise leaders want AI agents to take on more work but don't fully trust them to act correctly every time. Trust in Depth is AWS's layered approach-scope, know, bound, observe, and prove-that lets agents act on their own when their actions can be verified, reserving human jud","sections":[],"faq":[],"sources":[{"url":"https://aws.amazon.com/blogs/machine-learning/trust-in-depth-giving-agents-more-autonomy-without-losing-control/","title":"AWS Machine Learning Blog","publishedAt":"2026-10-15T15:05:35.000Z"}],"author":"TUMN 큐레이션","aiAssisted":false,"reviewStatus":"automated","reviewNote":"원문 제목과 공개된 발췌를 인용하고 원문으로 연결합니다. 내용을 재작성하거나 요약하지 않았습니다.","publishedAt":"2026-10-15T15:05:35.000Z","modifiedAt":"2026-10-15T22:25:17.000Z","checkedAt":"2026-10-15T22:25:17.966Z","language":"ko","kind":"link","sourceLabel":"AI 공식","profile":null,"via":null,"formats":{"json":"https://api.tumn.com/news/2fa9247c-925a-462a-bc26-6c365a196120.json","markdown":"https://api.tumn.com/news/2fa9247c-925a-462a-bc26-6c365a196120.md"}}