Build a semantic layer for agentic AI on AWS with AtScale and Amazon Bedrock AgentCore
AtScale exposes a single dimensional semantic model to AI agents and BI tools via MCP, SQL, and XMLA simultaneously
AWS published the third post in a series on semantic layers for agentic AI, this time using AtScale's dimensional modeling approach with Amazon Bedrock AgentCore. The architecture allows a Strands agent and existing BI tools to query the same computed metrics from one deployed model, with identity-propagated RBAC enforced at the semantic layer rather than in prompts. The pattern is a reusable enterprise blueprint for consistent, governed AI analytics on AWS.