NEWS · COMPANIES · #896
HEMA builds internal assistant HAL using Model Context Protocol and Amazon Bedrock AgentCore
Dutch retailer HEMA created HAL, an internal AI assistant that consolidates fragmented internal knowledge and delivers answers inside existing tools by exposing sources as MCP tools and running agents on Amazon Bedrock AgentCore. Identity is anchored with Microsoft Entra ID, and AgentCore features (Gateway, Runtime, Memory, Guardrails) were used to avoid custom MCP server infrastructure.
KEY POINTS
- Dutch retailer HEMA created HAL, an internal AI assistant that consolidates fragmented internal knowledge and delivers answers inside existing tools by exposing sources as MCP tools and running agents on Amazon Bedrock AgentCore.
- Identity is anchored with Microsoft Entra ID, and AgentCore features (Gateway, Runtime, Memory, Guardrails) were used to avoid custom MCP server infrastructure.
- This shows MCP can standardize integrations across clients while Amazon Bedrock AgentCore lets enterprises host agents without building custom MCP server infrastructure, speeding knowledge access and reducing onboarding friction.
WHY IT MATTERS
This shows MCP can standardize integrations across clients while Amazon Bedrock AgentCore lets enterprises host agents without building custom MCP server infrastructure, speeding knowledge access and reducing onboarding friction.