Reported evidence
AWS WhatsApp ordering assistant → uses → Shared customer memory across three channels
The tutorial describes shared memory for recognizing the same customer across text, voice notes, and real-time calls, while keeping channel handling separate from ordering. It does not establish improvements in accuracy, customer experience, or maintenance effort.
Read the evidence
The AWS tutorial introduces a WhatsApp ordering assistant built on Amazon Bedrock AgentCore and Amazon Nova 2. It accepts text, voice notes, and real-time voice calls, separates the channel and ordering layers, and uses shared memory to recognize the same customer across the three channels.
[S5] AWS Machine Learning Blog
Read the full research