Abnormal AI 用 Bedrock AgentCore 实现大规模智能体邮件安全
原标题：Abnormal AI: Amazon Bedrock AgentCore for agentic email security at scale
AI 摘要
Abnormal AI 在 AWS 博客中介绍了其基于 Amazon Bedrock AgentCore Code Interpreter 构建的智能体邮件安全系统。该系统采用三层检测架构，最高层由内联智能体在沙箱中动态编写脚本分析威胁情报，每天处理数十万最难判定的案例，整体每天处理数十亿封邮件。Abnormal AI 还部署了批处理分析智能体，每周运行约 100 个批处理任务，用于生成候选启发式规则并改进模型。此外，该公司 80% 的代码变更由智能体参与完成，40% 完全由后台智能体端到端构建。
正文节选
Abnormal AI: Amazon Bedrock AgentCore for agentic email security at scale AI agents now run in production at a scale of billions of operations a day, and a recurring architectural pattern has surfaced: agents need a compute scratch pad. Not only for coding tasks, but for data aggregation, analysis, verification, and any workflow where semantic reasoning alone isn’t enough. Abnormal AI, a behavioral security service that protects more than 25 percent of the Fortune 500, has deployed Amazon Bedroc