The walkthrough uses a dimensional model authored in the YAML-based Semantic Modeling Language and exposes one deployed model through SQL, XMLA, and MCP. A Strands agent accesses it through the AtScale MCP server; the post describes identity propagation and enforcement of RBAC, row security, and perspectives at query time. Metric definitions, joins, and caller-specific filters reside in the semantic layer rather than the prompt. The source describes an implementation pattern, not a comparative evaluation of security, accuracy, or performance.
Build a semantic layer for agentic AI on AWS with AtScale and Amazon Bedrock AgentCore
In one minute
AWS published a third implementation in its semantic-layer series for agentic analytics, this time using AtScale with Amazon Redshift and Bedrock AgentCore.
What changed: Adds an AtScale semantic-layer approach for agentic AI on AWS, distinct from the prior AgentCore contract-intelligence example and general agent-building guidance.