---
type: "raw_signal"
id: "build-a-semantic-layer-for-agentic-ai-on-97fee5"
slug: "build-a-semantic-layer-for-agentic-ai-on-97fee5"
title: "Build a semantic layer for agentic AI on AWS with Strategy Mosaic and Amazon Bedrock AgentCore"
description: "AWS and Strategy published a walkthrough that connects a Strategy Mosaic semantic layer to a Strands agent hosted on Amazon Bedrock AgentCore."
retrieval_nugget: "AWS and Strategy published a walkthrough that connects a Strategy Mosaic semantic layer to a Strands agent hosted on Amazon Bedrock AgentCore."
observed_at: "2026-10-20"
record_date: "2026-10-20"
date_kind: "observed_at"
why_it_matters: "AWS and Strategy published a walkthrough that connects a Strategy Mosaic semantic layer to a Strands agent hosted on Amazon Bedrock AgentCore. The example builds a customer-360 domain across Amazon Redshift and Amazon Aurora, with the agent reaching Mosaic through its MCP server. The post says joins, metric definitions, and caller-specific row and column filters remain inside Mosaic rather than in"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "aws.amazon.com"
topics: []
entities: ["Amazon Web Services","Strategy","Strategy Mosaic","Amazon Bedrock AgentCore","Strands","Model Context Protocol","Amazon Redshift","Amazon Aurora"]
related_patterns: ["agent-ready-software-exposes-capabilities","agent-protocols-become-interoperability-layer"]
novelty_label: "new_fact"
what_changed: "Introduces Strategy Mosaic’s semantic layer as a distinct AWS agentic-AI use case, integrating with Bedrock AgentCore and data services."
prior_refs: ["memory:0b572ebb-a65a-88df-aa48-5186d219475d","memory:abfdbb86-97f8-885e-a29a-e971a1b0ec77","memory:bcf6c489-b1d3-8808-a382-12d68aaee388","memory:19890ba8-d098-8983-abf5-e290909d7b1d","memory:f101535e-90e6-8877-a60b-8ece867cdbe6"]
source_url: "https://aws.amazon.com/blogs/machine-learning/build-a-semantic-layer-for-agentic-ai-on-aws-with-strategy-mosaic-and-amazon-bedrock-agentcore"
source_urls: ["https://aws.amazon.com/blogs/machine-learning/build-a-semantic-layer-for-agentic-ai-on-aws-with-strategy-mosaic-and-amazon-bedrock-agentcore"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:build-a-semantic-layer-for-agentic-ai-on-97fee5"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/build-a-semantic-layer-for-agentic-ai-on-97fee5/","markdown":"https://newruntime.com/signals/build-a-semantic-layer-for-agentic-ai-on-97fee5.md","json":"https://newruntime.com/signals/build-a-semantic-layer-for-agentic-ai-on-97fee5.json"}
---

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

## Retrieval answer

AWS and Strategy published a walkthrough that connects a Strategy Mosaic semantic layer to a Strands agent hosted on Amazon Bedrock AgentCore.

AWS and Strategy published a walkthrough that connects a Strategy Mosaic semantic layer to a Strands agent hosted on Amazon Bedrock AgentCore. The example builds a customer-360 domain across Amazon Redshift and Amazon Aurora, with the agent reaching Mosaic through its MCP server. The post says joins, metric definitions, and caller-specific row and column filters remain inside Mosaic rather than in the agent prompt. It describes user-identity propagation to preserve those controls end to end. The same Mosaic definitions are also exposed through JDBC/ODBC, XMLA, and REST. This is a vendor-described architecture example; the post does not establish independent performance or security validation.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)