# Amazon — Build a semantic layer for agentic AI with EDB Postgres AI and Amazon Bedrock AgentCore

- Company: Amazon (amazon.com)
- Announced: 2026-11-03T16:41:13+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-with-edb-postgres-ai-and-amazon-bedrock-agentcore/
- Record: https://forck.live/items/31095-build-a-semantic-layer-for-agentic-ai-with-edb-postgres-ai-and-amazon-bedrock
- Subject: Bedrock / Nova
- Models affected: Anthropic Claude

Amazon's guide shows how to build a semantic layer for agentic AI using EDB Postgres AI, running a Strands Agents agent on Amazon Bedrock AgentCore that queries the layer to answer customer 360 questions. EDB Postgres AI places the semantic layer inside the operational Postgres database as an AIDB extension, so business meaning lives next to the data in standard Postgres COMMENT statements. The join graph comes from Postgres foreign keys, and governance uses Postgres GRANT and row-level security through the Model Context Protocol endpoint that ships with AIDB. The model layer is Anthropic Claude on Amazon Bedrock, the runtime layer is AgentCore runtime, and AgentCore Gateway handles inbound authorization while AgentCore Identity holds outbound credentials for tool targets. The guide walks through building an AIDB semantic knowledge base over a Postgres schema, exposing the AIDB tool catalog to an external agent through the built-in EDB MCP endpoint fronted by an Application Load Balancer and registered as an MCP target on AgentCore Gateway. It also shows how Postgres roles, column-level GRANT statements and row-level security produce different results for different callers while the prompt, tool catalog and agent code stay the same, and how AIDB captures OpenTelemetry traces for every SQL execution as rows in the aidb_otel schema, queryable with ordinary SQL. The example dataset is the Stardog C360 Knowledge Kit loaded into a single EDB Postgres AI instance in a dedicated c360 schema, with four tables and one derived view.

## Evidence

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

> In this post, we show how to build a semantic layer for agentic AI using EDB Postgres AI . We run a Strands Agents agent on Amazon Bedrock AgentCore that queries the layer to answer customer 360 (C360) questions. Earlier posts in this series built the same C360 pattern with Stardog’s knowledge graph , Denodo’s data virtualization platform , AtScale’s dimensional model , and Strategy Mosaic’s linked models .
> 
> EDB Postgres AI puts the semantic layer inside the operational Postgres database as an AIDB extension . Business meaning lives next to the data in standard Postgres COMMENT statements, the join graph comes from Postgres foreign keys, and governance uses Postgres GRANT and row-level security through the Model Context Protocol (MCP) endpoint that ships with AIDB.
> 
> By the end of this post you will know:
> 
> How to build an AIDB semantic knowledge base (SemKB) over a Postgres schema, how COMMENT ON statements and aidb.create_semantic_alias behave as the authoring surface, and how foreign keys crawl into join paths.

---

Record: https://forck.live/items/31095-build-a-semantic-layer-for-agentic-ai-with-edb-postgres-ai-and-amazon-bedrock
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md