AITOPAI热报
ProductsOfficialSelected

HEMA builds HAL AI assistant with MCP and Amazon Bedrock

From portal-hopping to instant answers: HEMA’s journey with MCP and Amazon Bedrock

Primary sourceAWS Machine Learning Blog@Mauro Rallo
Blog/Media
Read the original
Why we picked it

The setup shows an enterprise pattern worth copying: MCP as the governance layer that keeps AWS credentials off the client and authenticates through Microsoft Entra ID instead. Platform and security engineers evaluating MCP in production can use it as a reference architecture on Bedrock AgentCore. It contrasts with agent frameworks that require exposing cloud credentials to client tools.

Dutch retailer HEMA built HAL, an internal AI assistant, on Amazon Bedrock AgentCore to replace developer portal-hopping with instant answers.

Image · AWS Machine Learning Blog
Body

HAL uses the Model Context Protocol (MCP) to deliver governed knowledge inside the tools teams already use.No AWS credentials sit on the client, with security anchored in Microsoft Entra ID.

HEMA is a retailer with a 100-year history.

Original · AWS Machine Learning Blog

From portal-hopping to instant answers: HEMA’s journey with MCP and Amazon Bedrock

HEMA, a 100-year-old Dutch retailer, turned developer portal-hopping into instant answers by building HAL, an internal AI assistant on Amazon Bedrock AgentCore. Using Model Context Protocol (MCP), HAL delivers governed knowledge inside the tools teams already use, with no AWS credentials on the client and security anchored in Microsoft Entra ID.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on Europe's AI governance and technology ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Amazon Bedrock, MCP and tools, HEMA, AgentCore.

Primary source verification: published directly by AWS Machine Learning Blog with first-party authority.

#Amazon Bedrock#MCP and tools#HEMA#AgentCore

Keep reading

Recent stories with the same tag or section
ProductsBuildersOfficialSelected06:02
Natera's SWARM agentic AI system for lab operations on Amazon Bedrock AgentCore

The transferable part is the design pattern: a knowledge base plus AgentCore-hosted agents with built-in evaluation, applied to a domain where answers must be precise and auditable. Teams in healthcare, logistics, or enterprise support with scarce senior expertise can map SWARM's pipeline onto their own ticket flows. AWS customers considering Bedrock AgentCore get a reference architecture with real coverage metrics instead of vendor claims.

#Amazon Bedrock#AgentCore#Natera#agents
Primary sourceAWS Machine Learning Blog@Ariel JirauSource
How-toBuildersOfficial05:15
Chinese contentAmazon Bedrock 推理省钱的 4 个请求级参数

很多人调完提示词发现 Bedrock 账单还在涨，这篇讲的就是原因：缓存时长、service tier、推理力度和 maxTokens 这 4 个请求参数在偷偷决定你的费率。每个都附了测试和验证方法，接了 Bedrock 的开发者直接照着改就行。

#Amazon Bedrock#AWS#Claude#prompt engineering
Primary sourceAWS Machine Learning Blog@Sai Pavan KasaniSource
How-toBuildersOfficialSelected03:08
Amazon Bedrock: calculating true cost per task and agent ROI

The real takeaway is that model choice based on listed token prices can invert once caching, routing and output behaviour are priced in per task. Engineering leads and platform teams evaluating Bedrock agents should apply the four cost drivers as a checklist before locking in a provider. The five-dimension scorecard also gives a concrete template for defending agent budgets to finance stakeholders, replacing intuition with holdout experiment data.

#Amazon Bedrock#prompt engineering#agents#cost optimization
Primary sourceAWS Machine Learning Blog@Majd ArbashSource
How-toBuildersOfficialSelected03:08
Amazon Bedrock and LiteLLM build self-service LLM gateway

The practical takeaway is that OpenAI-compatible gateways are becoming the default abstraction layer for enterprises, letting internal tools switch between Bedrock, OpenAI or self-hosted models with a base-URL change. Platform engineers and ML infrastructure teams should evaluate this recipe when their organisation needs quota isolation and cost attribution without building proxy infrastructure from scratch. Compared with running raw Bedrock integrations per team, this approach trades a small latency overhead for centralised governance. Teams in ASEAN and China markets serving multi-region AWS workloads can adapt the same pattern to their local Bedrock endpoints.

#Amazon Bedrock#LiteLLM#AWS Fargate#prompt engineering
Event
Primary sourceAWS Machine Learning Blog@Sitaraman Vijay KrishnaSource
ProductsBuildersOfficial00:40
Chinese content用编码智能体迁移到 Amazon Bedrock Managed Knowledge Base

AWS 把知识库迁移做成了给编码智能体用的 skill：只读盘点、生成 IaC 模板、切流前自动验证检索。正在用 Bedrock 自管知识库的团队可以少写一堆 CloudFormation，也比手动迁移多了检索质量校验这一步。

#Amazon Bedrock#AWS#RAG#coding assistants
Primary sourceAWS Machine Learning Blog@Josh DeMuthSource
How-toBuildersOfficialSelected23:47
Amazon Bedrock adds per-user access control for knowledge base MCP tools

The non-obvious part is that authorization is enforced outside the agent, by gateway policy plus a resource-based policy on the knowledge base, so a compromised or careless agent cannot leak documents. Teams deploying multi-tenant RAG agents on AWS should replicate this three-layer pattern rather than trusting agent-level filtering. Compared with self-built MCP gateways, it reuses AgentCore's identity injection, cutting custom auth plumbing.

#Amazon Bedrock#AgentCore#MCP and tools#RAG
Primary sourceAWS Machine Learning Blog@Renya KujiradaSource