AWS walkthrough: wire AtScale's SML semantic layer to Bedrock AgentCore via MCP
AWS ML Blog · rss · 2026-10-20
AWS ML Blog's fourth semantic-layer walkthrough applies the same Customer 360 pattern with AtScale on Amazon Bedrock AgentCore.
- AtScale models dimensions, hierarchies, and measures in the open YAML-based Semantic Modeling Language (SML), versioned in Git, and exposes one deployed model over SQL, XMLA, and MCP simultaneously.
- Claude Sonnet 4.6 on Bedrock plans queries; the Strands agent on AgentCore reaches the model through an AtScale MCP server registered with AgentCore Gateway.
- Unlike Stardog/Denodo, AtScale doesn't federate at query time: analytical data is consolidated in Redshift Serverless via DMS or Aurora zero-ETL, and joins push down as native warehouse SQL.
- User identity flows from the enterprise IdP through AgentCore Identity to AtScale, which enforces RBAC, row security, and perspectives at query time.
- Autonomous aggregate management materializes summary tables for expensive agent query patterns; the post also covers EKS deployment via Helm. Based on AtScale C2026.7.
More from coding & agent
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- 3 flight-booking rules my AI agent checks that I'd never do by hand — Efistoffeles · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23
- How do you audit AI agent decisions in regulated workflows? A field survey — Ok_Way_1993 · 2026-10-23