Build a semantic layer for agentic AI on AWS with Denodo and Amazon Bedrock AgentCore
Build a governed semantic layer for agentic AI on AWS with the Denodo Platform and Amazon Bedrock AgentCore. It federates Amazon Aurora, Amazon Redshift, and an on-premises PostgreSQL database into a single customer 360 view an agent queries in VQL, with identity propagation and row- and column-level access control enforced at the semantic layer.
First seen by Oriel on .
AI summary
The post shows how to build a Denodo semantic layer that federates Aurora, Redshift, and on-premises PostgreSQL for a governed customer 360 agent hosted on Amazon Bedrock AgentCore.
- Denodo Virtual DataPort combines live source queries at runtime, joining customer, order, and rewards data without moving data or maintaining an ETL-built customer table.
- The model uses six base views, a customer_360 derived view, and a reusable lifetime_customer_value metric view.
- AgentCore Gateway routes agent tool calls through the Denodo MCP Server; AgentCore Identity exchanges the user's inbound token for a scoped Denodo token.
- Denodo validates the token, maps the caller to a role, and applies Global Security Policies for row filters and column masks at query time.
- The walkthrough uses a Strands agent and Anthropic Claude Sonnet 4.6; the text also names Agora and self-managed EC2 or EKS as Denodo deployment options.
#denodo #amazon bedrock agentcore #model context protocol #data virtualization
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| AWS Machine Learning Blog | 35a19d20a9faf60985c6eccdb143b93a0781a1a3 | https://aws.amazon.com/blogs/machine-learning/build-a-semantic-layer-for-agentic-ai-on-aws-with-denodo-and-amazon-bedrock-agentcore/ Read discussion |