AWS Machine Learning Blog · Saumya Shah · 3 天前精选模型评分61
Worldwide Express 如何用 Amazon Bedrock 自动处理运费账单异常
How Worldwide Express automated freight exceptions with Amazon Bedrock
导读
Worldwide Express（隶属 ShipStation Global）与 AWS、LTM 合作，基于 Amazon Bedrock 构建多智能体方案并接入其运输管理系统 SpeedShip，自动处理零担货运的账单异常。
推荐理由
物流企业用三个分工智能体处理运费账单争议，并给出人工审批与准确率门槛的落地细节，可迁移到其他对账场景。
分类置信度
高
- 官方或准官方来源，且无冲突类别。
- 正文、可信日期、主分类和证据摘录完整。
来源级别：官方一手
应用领域：交通与物流
事件类型：业务采用
证据摘录
- “Worldwide Express worked with AWS and LTM to build a multi-agentic AI solution with Amazon Bedrock that plugs directly into their transportation management system (TMS), SpeedShip.”
- “Initially, a human reviewer would use the existing SpeedShip UI to approve recommendations before they’re finalized.”
- “Eventually when accuracy exceeded 99 percent, bulk approval became the default.”
- “Six months in, Worldwide Express has deployed the solution across over 40 LTL carriers.”
- “The agents currently close 10,000 (approximately 50 percent) exceptions weekly with a less than 1 percent error rate.”
来源：AWS Machine Learning Blog · aws.amazon.com