HEMA Ends Portal-Hopping With AI Knowledge Layer

Dutch retailer HEMA built HAL, an internal AI assistant, using Model Context Protocol and Amazon Bedrock AgentCore to solve a persistent knowledge fragmentation problem. Engineers previously spent hours navigating disconnected wikis, service catalogs, and IT portals to find answers. HAL consolidates HEMA's structured technology knowledge into one governed source, delivering it through tools staff already use, including IDE environments and chat windows. MCP enables a single integration point for multiple AI clients, while Amazon Bedrock AgentCore handles authentication, hosting, and tool creation without custom server infrastructure.