Building a semantic layer for agentic AI on AWS with Denodo and Amazon Bedrock AgentCore
In brief
- Federation of databases (Aurora, Redshift, PostgreSQL) into a unified view for agents.
- Fine-grained access control (rows and columns) enforced at the semantic layer according to the announcement.
- Identity propagation for agent queries via VQL.
AWS introduces a solution to build a governed semantic layer for agentic AI using Denodo Platform and Amazon Bedrock AgentCore. The layer federates multiple data sources (Amazon Aurora, Amazon Redshift, and on-premises PostgreSQL) into a unified view queryable by an agent in VQL, with identity propagation and row- and column-level access control enforced according to the announcement.
What it changes for you
- Public SectorEnables public administrations to centralize and secure data access for AI agents while complying with governance rules.
This summary gives you the essentials. The full article, its figures and quotes are on Artificial Intelligence.
Read the original articleAI-generated summary of the source, checked by rules. How we write · Report an error