Woro AI/Blog/AWS Machine Learning

AWS Machine Learning

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

· 1 min read · Summary from AWS Machine Learning

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.

Read the full story at AWS Machine Learning →

Our take

HEMA built an internal AI assistant called HAL using Amazon Bedrock AgentCore and Model Context Protocol. HAL gives instant answers inside the tools teams already use, without exposing AWS credentials to clients.

Small businesses can reduce time spent switching between tools and searching for information. By integrating AI directly into existing workflows, owners can improve productivity and keep data secure with identity management like Microsoft Entra ID.

Try adding a simple AI chatbot to your WhatsApp business account in WORO this week, using the built‑in AI assistant feature. If you’re not ready to deploy, watch for updates on how WORO integrates with Amazon Bedrock for future AI enhancements.

Woro AI

Read about it here. Run it from WhatsApp.

Start free