---
type: "raw_signal"
id: "build-a-semantic-layer-for-agentic-ai-on-3b2053"
slug: "build-a-semantic-layer-for-agentic-ai-on-3b2053"
title: "Build a semantic layer for agentic AI on AWS with AtScale and Amazon Bedrock AgentCore"
description: "AWS published a third implementation in its semantic-layer series for agentic analytics, this time using AtScale with Amazon Redshift and Bedrock AgentCore."
retrieval_nugget: "AWS published a third implementation in its semantic-layer series for agentic analytics, this time using AtScale with Amazon Redshift and Bedrock AgentCore."
observed_at: "2026-10-20"
record_date: "2026-10-20"
date_kind: "observed_at"
why_it_matters: "AWS published a third implementation in its semantic-layer series for agentic analytics, this time using AtScale with Amazon Redshift and Bedrock AgentCore. The walkthrough uses a dimensional model authored in the YAML-based Semantic Modeling Language and exposes one deployed model through SQL, XMLA, and MCP. A Strands agent accesses it through the AtScale MCP server; the post describes identity p"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "aws.amazon.com"
topics: ["mcp"]
entities: ["AtScale","Amazon Bedrock AgentCore","Amazon Redshift","Strands","Semantic Modeling Language","Amazon Web Services"]
related_patterns: ["agent-ready-software-exposes-capabilities","agent-protocols-become-interoperability-layer"]
novelty_label: "new_fact"
what_changed: "Adds an AtScale semantic-layer approach for agentic AI on AWS, distinct from the prior AgentCore contract-intelligence example and general agent-building guidance."
prior_refs: ["memory:abfdbb86-97f8-885e-a29a-e971a1b0ec77","memory:cc5d9997-c399-8edf-adaf-f038d74de95b"]
source_url: "https://aws.amazon.com/blogs/machine-learning/build-a-semantic-layer-for-agentic-ai-on-aws-with-atscale-and-amazon-bedrock-agentcore"
source_urls: ["https://aws.amazon.com/blogs/machine-learning/build-a-semantic-layer-for-agentic-ai-on-aws-with-atscale-and-amazon-bedrock-agentcore"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:build-a-semantic-layer-for-agentic-ai-on-3b2053"
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-3b2053/","markdown":"https://newruntime.com/signals/build-a-semantic-layer-for-agentic-ai-on-3b2053.md","json":"https://newruntime.com/signals/build-a-semantic-layer-for-agentic-ai-on-3b2053.json"}
---

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

## Retrieval answer

AWS published a third implementation in its semantic-layer series for agentic analytics, this time using AtScale with Amazon Redshift and Bedrock AgentCore.

AWS published a third implementation in its semantic-layer series for agentic analytics, this time using AtScale with Amazon Redshift and Bedrock AgentCore. The walkthrough uses a dimensional model authored in the YAML-based Semantic Modeling Language and exposes one deployed model through SQL, XMLA, and MCP. A Strands agent accesses it through the AtScale MCP server; the post describes identity propagation and enforcement of RBAC, row security, and perspectives at query time. Metric definitions, joins, and caller-specific filters reside in the semantic layer rather than the prompt. The source describes an implementation pattern, not a comparative evaluation of security, accuracy, or performance.

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`.

- topic hub: [Mcp](https://newruntime.com/topics/mcp.md): Explore the mcp topic hub.
- 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)