Amazon Quick推出AI智能体操作智能审批功能
AWS表示,Amazon Quick的Smart Approvals功能使用单独的分类器,根据用户请求和有界的对话上下文评估符合条件的AI智能体操作。符合条件的操作可能被自动批准;分类器未批准的操作、超时及其他审核失败会返回用户处理,且不会获得自动批准。策略拒绝的操作仍会被阻止。该功能不会增加权限或取消强制人工审批。AWS同时提醒,模型审核可能出错,并建议在扩大使用前先进行有限试点。
Smart Approvals旨在减少常规操作中的重复提示,同时保留人对高影响决策的控制。AWS表示,是否扩大使用应依据试点证据,包括抽查自动批准、测试高影响场景,以及确认团队能够追踪操作从审批到执行的完整过程。
How should security leaders preserve human oversight as AI agents take on more work? Permissions establish which actions agents can take, but a permitted action can still warrant a person’s judgment. Requiring approval for every step might seem like the safest approach, yet multi-step tasks can produce repeated prompts, even for routine actions. Research on security warnings shows that attention and adherence can decline with repetition. The challenge isn’t to require more approvals, but to preserve attention for decisions that need human review.
Smart Approvals in AWS Quick addresses this challenge by reviewing eligible actions within your existing controls. It evaluates each proposed action against the user’s request and either approves it automatically or returns it to the user for review. It does this without granting additional permissions or removing required human approvals. Security leaders retain control over which actions must always go to a person, while Smart Approvals is designed to reduce unnecessary interruptions in routine work.
Figure 1: Policy determines eligibility. Smart Approvals approves eligible actions or returns them to the user for review. Policy denials remain blocked
#Amazon Quick#Amazon Quick Smart Approvals#AWS#AWS CloudTrail#Amazon CloudWatch Logs