A new blog post on AWS describes how to build an AI-powered real estate assistant on WhatsApp using the Strands Agents SDK and AWS End User Messaging. The solution aims to close the gap between form submissions and delayed sales team responses by providing instant answers. It delivers property discovery, home loan pre-approval, and site visit booking entirely within WhatsApp. The architecture uses four AI agents built with the Strands Agents SDK, each handling a specific task: identity verification, credit scoring, fraud detection, or property valuation. The agents run on Amazon Bedrock with the Nova Lite model and are deployed to AWS Lambda using the official Strands Agents Lambda Layer. AWS End User Messaging Social handles WhatsApp Business API integration, publishing incoming messages to Amazon SNS for routing. A webhook handler Lambda function processes these events and invokes a supervisor agent, which orchestrates the conversation flow, maintains session state in Amazon DynamoDB, and sends rich interactive messages back to customers. Prerequisites include an AWS account with permissions for AWS CloudFormation, Lambda, Amazon SNS, Amazon Bedrock, and DynamoDB, as well as a WhatsApp Business account integrated with AWS End User Messaging.