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

DevFeed: [Build a semantic layer for agentic AI on AWS with AtScale and Amazon Bedrock AgentCore](<https://devfeed.tech/articles/build-a-semantic-layer-for-agentic-ai-on-aws-with-atscale-and-amazon-bedrock-agentcore-91289.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/build-a-semantic-layer-for-agentic-ai-on-aws-with-atscale-and-amazon-bedrock-agentcore/>)

Author: Frank Lapolito

Published: 2026-10-20T15:33:54Z

Content type: article

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [semantic-layer](<https://devfeed.tech/topics/semantic-layer.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [OpenID connect (OIDC)](<https://devfeed.tech/topics/oidc.md>)

Tags: [3](<https://devfeed.tech/tags/3.md>), [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents](<https://devfeed.tech/tags/agents.md>), [aggregates](<https://devfeed.tech/tags/aggregates.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon-aurora](<https://devfeed.tech/tags/amazon-aurora.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-eks](<https://devfeed.tech/tags/amazon-eks.md>), [amazon-redshift](<https://devfeed.tech/tags/amazon-redshift.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-database-migration-service](<https://devfeed.tech/tags/aws-database-migration-service.md>), [aws-secrets-manager](<https://devfeed.tech/tags/aws-secrets-manager.md>), [customer-360](<https://devfeed.tech/tags/customer-360.md>), [identity](<https://devfeed.tech/tags/identity.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [rbac](<https://devfeed.tech/tags/rbac.md>), [security](<https://devfeed.tech/tags/security.md>), [semantic-layer](<https://devfeed.tech/tags/semantic-layer.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

## AI overview

AtScale lets a Strands agent query a governed customer 360 model on Amazon Redshift through its MCP server, while the same dimensional definitions are available to BI tools over SQL and XMLA. The model is authored as YAML in the open Semantic Modeling Language and versioned in Git; AtScale plans dimensional queries into native SQL for one warehouse engine and can route matching patterns to automatically managed aggregates. AgentCore Gateway and Identity carry the human user's identity to AtScale, where roles, perspectives, and row security are applied at query time. Query records include both the agent's dimensional SQL and the translated warehouse SQL. Unlike the Stardog and Denodo approaches described earlier, AtScale does not federate live across engines: data must be consolidated upstream or accessed through warehouse-level federation. The walkthrough deploys AtScale on EKS and connects the agent through an AgentCore Gateway MCP target.

## Source excerpt

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.