Uzha
Sign in
← Today's brief

Tools · Updated 20 Oct, 09:09 pm IST

AWS shows how to add vendor semantic layers for agentic AI with Bedrock AgentCore

Image: AWS Machine Learning Blog

Why it matters for readers: Demonstrates how agents can get consistent answers from the same semantic model rather than from ad hoc prompts.

  • AtScale provides a dimensional semantic model authored in an open YAML-based Semantic Modeling Language and serves the same model over SQL, XMLA, and the Model Context Protocol (MCP).1
  • Strategy Mosaic uses a dimensional model and exposes a single definition via MCP for agents, JDBC/ODBC (over Trino) for SQL clients, XMLA for BI, and REST for custom apps, with certified sources like Snowflake and Databricks supported.2
  • Denodo’s platform exposes governed, live views to agents in VQL via a Denodo MCP Server and the example extends the source mix to include an on‑premises PostgreSQL alongside Aurora and Redshift.3
  • Across the series a foundation model on Amazon Bedrock (the AtScale walkthrough uses Anthropic Claude Sonnet 4.6) plans and writes queries while Amazon Bedrock AgentCore hosts the Strands agent and handles authentication and outbound credentials.123
SaveAsk about this story
Report a mistake in this summary

Get a brief like this every morning

Uzha reads hundreds of sources and gives you the stories that matter for your work, with every source linked. Free.

Get started

How this story developed

  1. 20 Oct, 09:03 pm · AWS Machine Learning Blog

    Build a semantic layer for agentic AI on AWS with AtScale and Amazon Bedrock AgentCore

  2. 20 Oct, 09:06 pm · AWS Machine Learning Blog

    Build a semantic layer for agentic AI on AWS with Strategy Mosaic and Amazon Bedrock AgentCore

  3. 20 Oct, 09:09 pm · AWS Machine Learning Blog

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