用 AtScale 与 Amazon Bedrock AgentCore 为智能体搭建语义层
Build a semantic layer for agentic AI on AWS with AtScale and Amazon Bedrock AgentCore
AWS 教你把 AtScale 语义层接到 Bedrock AgentCore 的智能体上，权限控制和审计在语义层做，不用靠提示词兜底，做企业级数据智能体的可以照着搭。
AWS 机器学习博客发布语义层系列第三篇教程，演示在 Amazon Redshift 上用 AtScale 构建受治理的 Customer 360 模型。该模型通过 AtScale MCP 服务器暴露给运行在 Amazon Bedrock AgentCore 上的 Strands 智能体。身份传播、RBAC、行级安全和完整查询审计都在语义层强制执行，而非依赖提示词。
Build a semantic layer for agentic AI on AWS with AtScale and Amazon Bedrock AgentCore
The third post in our semantic-layer series builds a governed customer 360 model on Amazon Redshift with AtScale, then exposes it to a Strands agent on Amazon Bedrock AgentCore through the AtScale MCP server. Identity propagation, RBAC, row security, and full query audit are enforced at the semantic layer, not the prompt.