AWS posts walkthroughs for semantic layers for agentic AI on Bedrock AgentCore

1. 11:39 AM
   AWS Machine Learning BlogOfficialPick

   How to build a semantic layer for agentic AI with Denodo and Amazon Bedrock AgentCore

   AIAWS Machine Learning Blog describes building a semantic layer for agentic AI using the Denodo Platform and Amazon Bedrock AgentCore. The Denodo MCP Server exposes governed views to a Strands agent, which queries Amazon Aurora, Amazon Redshift, and an on-premises PostgreSQL database through VQL without moving data between sources. The post also covers identity propagation through AgentCore Identity and Global Security Policies that mask PII per caller.

2. 11:36 AM
   AWS Machine Learning BlogOfficial

   Build a semantic layer for agentic AI with Strategy Mosaic and Amazon Bedrock AgentCore

   AIAWS Machine Learning Blog shows how to build a semantic layer for AI agents using Strategy Mosaic and Amazon Bedrock AgentCore. The walkthrough models a customer 360 domain across Amazon Redshift and Amazon Aurora with two linked Mosaic models and no ETL. A Strands agent on AgentCore reaches Mosaic through its MCP endpoint, with joins, metrics, and per-user row and column security kept inside Mosaic.

3. 11:33 AM
   AWS Machine Learning BlogOfficial

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

   AIAWS Machine Learning Blog describes building a customer 360 semantic layer on AWS with AtScale and Amazon Bedrock AgentCore, using the same pattern as earlier posts in the series. AtScale models the data dimensionally in the open Semantic Modeling Language, exposed over SQL, XMLA and MCP, with the agent querying Amazon Redshift through the AtScale MCP server. The walkthrough uses the AtScale C2026.7 release and Anthropic Claude Sonnet 4.6 on Amazon Bedrock.

The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.