{
  "id": 15759049,
  "title": "Build a semantic layer for agentic AI on AWS with Strategy Mosaic and Amazon Bedrock AgentCore",
  "url": "https://urgent.news/2026/10/20/build-a-semantic-layer-for-agentic-ai-on-aws-with-strategy-mosaic-and",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-20T15:36:39.000Z",
  "source": {
    "name": "AWS Machine Learning",
    "slug": "aws-machine-learning",
    "url": "https://aws.amazon.com/blogs/machine-learning/build-a-semantic-layer-for-agentic-ai-on-aws-with-strategy-mosaic-and-amazon-bedrock-agentcore/"
  },
  "original_language": "en",
  "account": "This post continues the series by building a semantic layer on AWS using Strategy Mosaic and Amazon Bedrock AgentCore. It demonstrates how to model a Customer 360 (C360) domain across Amazon Redshift and Amazon Aurora using two linked models, without any ETL. The article explains Mosaic's metric syntax, including base metrics, advanced metrics with named filter objects, level qualifiers, and compound metrics. It also covers how to expose the model to a Strands agent hosted on AgentCore runtime through the Mosaic MCP server, and how user identity propagates for Row-Level Security (RLS) and Object-Level Security (OLS). The post provides guidance on choosing between live pushdown and in-memory execution for agent traffic, and how to publish the governed definitions to various tools like Power BI, Tableau, notebooks, and custom apps. The source of truth for the walkthrough is Strategy One (March 2026), when Mosaic access through the MCP server became available by default.",
  "summary": "The third post in our semantic-layer series builds a customer 360 across Amazon Redshift and Amazon Aurora with Strategy Mosaic, exposes it to a Strands agent on Amazon Bedrock AgentCore through the Mosaic MCP server, and enforces per-user row and column security end-to-end.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 2,
    "also_reported_by": [
      {
        "outlet": "AWS Machine Learning",
        "title": "Build a semantic layer for agentic AI on AWS with Denodo and Amazon Bedrock AgentCore",
        "url": "https://urgent.news/2026/10/20/build-a-semantic-layer-for-agentic-ai-on-aws-with-denodo-and-amazon",
        "published": "2026-10-20T15:39:04.000Z"
      }
    ]
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}