Build a semantic layer for agentic AI on AWS with AtScale and Amazon Bedrock AgentCore

What happened

This guide builds a Customer 360 semantic layer with AtScale over Amazon Redshift, connecting it through MCP to a Strands agent hosted on Amazon Bedrock AgentCore. It covers Git-versioned SML models, query aggregation, identity propagation, access controls, and deployment on Amazon EKS. The walkthrough uses Claude Sonnet 4.6 and compares agent results with Excel totals, while explaining that each AtScale query executes in one warehouse engine.

The story so far

AWS published a tutorial showing how to build a Customer 360 semantic layer with AtScale over Amazon Redshift and connect it through MCP to a Strands agent hosted on Amazon Bedrock AgentCore. The walkthrough uses Claude Sonnet 4.6 and compares the agent’s results with Excel totals. The guide covers defining datasets, dimensions, hierarchies and measures in Semantic Modeling Language (SML), with models versioned in Git. It also explains query aggregation, identity propagation, access controls and deployment on Amazon EKS. AWS notes that each AtScale query executes in a single warehouse engine.

Keep reading

Trending now

1. 1DeepSeek Open-Sources DeepInfer and Companion Components, With Model and Hardware Limits
2. 2Mistral Releases Voxtral 3 Speech Models, Voice Agents API and LiveKit-Based SDK
3. 3Perplexity Adds Fully Local Mac Operation to Computer
4. 4Meta Pauses Muse Conversation Sharing After Researchers Find Links Exposing Sensitive Information