Build a semantic layer for agentic AI on AWS with Denodo and Bedrock AgentCore
AWS ML Blog · rss · 2026-10-20
An AWS ML Blog tutorial shows how to build a semantic layer for agentic AI using Denodo Platform on Amazon Bedrock AgentCore, extending an earlier Stardog knowledge-graph pattern.
- Adds an on-premises PostgreSQL source alongside Amazon Aurora (customer profiles) and Amazon Redshift (orders), so federation is no longer VPC-bounded
- Zero-copy federation: Denodo pushes down and combines queries at runtime, no ETL; the customer-360 semantic view is declared once and reused
- Agent chain: Claude Sonnet 4.6 on Bedrock plans queries; the Denodo MCP Server exposes governed views via AgentCore Gateway; AgentCore Identity performs On-Behalf-Of token exchange to pass end-user identity
- Governance: Global Security Policies apply row filters and column masks at query time per caller; VQL syntax is supplied to the LLM via a skill
- Two deployment options covered: Agora managed cloud or self-managed on EC2/EKS
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23