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

- Company: Amazon (amazon.com)
- Announced: 2026-10-20T15:39:04+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://aws.amazon.com/blogs/machine-learning/build-a-semantic-layer-for-agentic-ai-on-aws-with-denodo-and-amazon-bedrock-agentcore/
- Record: https://forck.live/items/25272-build-a-semantic-layer-for-agentic-ai-on-aws-with-denodo-and-amazon-bedrock
- Subject: Bedrock / Nova

Amazon's walkthrough shows how to build a semantic layer with the Denodo Platform on AWS so an agent hosted on Amazon Bedrock AgentCore can query governed enterprise data. It follows an earlier post that used Stardog's knowledge graph, swapping in Denodo and adding a source outside AWS. The customer 360 example federates Amazon Aurora, Amazon Redshift and an on-premises PostgreSQL cluster, where the rewards_account table sits, into a single view the agent queries in VQL, Denodo's SQL dialect. Denodo plans the federated query at execution time, deciding what to push into Aurora, what to push into Redshift, what to fetch from the on-premises cluster, and how to combine the results, with no data moving between sources. The Denodo MCP Server exposes governed views to the agent through the Model Context Protocol and is registered as an AgentCore Gateway target, while AgentCore terminates inbound authentication and manages the outbound credential the agent presents to Denodo. The post also covers how the end user's identity flows from the enterprise identity provider through AgentCore Identity On-Behalf-Of token exchange, and how Global Security Policies apply row and column filters at query time. Denodo can be deployed on AWS as the fully managed Agora service or self-managed on Amazon EC2 or Amazon EKS.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/build-a-semantic-layer-for-agentic-ai-on-aws-with-denodo-and-amazon-bedrock-agentcore/:

> Denodo plans the federated query at execution time, deciding what to push into Aurora, what to push into Amazon Redshift, what to fetch from the on-premises cluster, and how to combine the results. No data moves between sources, and the semantic layer stays declared once for every consumer to reuse.

---

Record: https://forck.live/items/25272-build-a-semantic-layer-for-agentic-ai-on-aws-with-denodo-and-amazon-bedrock
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md