Build a semantic layer for agentic AI on AWS with Stardog and Amazon Bedrock AgentCore
AWS just showed how to run agentic AI without the ETL nightmare. Here's what that means for your data stack.
Why it matters
AWS Bedrock AgentCore + Stardog semantic layer enables production agentic AI workflows that query multiple data sources in real-time without traditional ETL, lowering operational friction for enterprises building customer 360 agents.
The key facts
10 to knowAWS Bedrock AgentCore bundles inbound auth, hosting, and tool credentials as managed service
Stardog semantic layer deployed over Aurora and Redshift enables cross-source queries without ETL
Deployment pattern works across EKS, ECS, and Lambda compute options
Use case: agentic AI answering customer 360 questions across multiple data sources
Published: July 10, 2026
Stardog Semantic AI Application integrates with Amazon Aurora and Amazon Redshift
Amazon Bedrock AgentCore bundles inbound auth, hosting, and tool credentials as managed service
Semantic layer enables agent queries across multiple sources without ETL
Deployment patterns shown for Amazon EKS, Amazon ECS, and AWS Lambda
Use case: customer 360 queries across heterogeneous data sources
Go to the source
AWS Machine Learning Blogaws.amazon.com
Publisher excerpt: In this post we show how to build a semantic layer on AWS using Stardog’s Semantic AI Application over Amazon Aurora and Amazon Redshift, and how to run a Strands Agents agent on Amazon Bedrock AgentCore that queries the layer to answer customer 360 questions across both sources without extract,…