Build an autonomous ecommerce assistant with AWS End User Messaging, Amazon Bedrock AgentCore, and OpenClaw
Messaging & Targeting Blog
This article presents Claw Boutique, an open-source reference architecture for building an autonomous ecommerce assistant that integrates WhatsApp, email, Telegram, and web storefronts using AWS services and AI agents.
- Buyers interact via WhatsApp and web storefront; sellers manage operations through Telegram with AI-powered commands
- Amazon Bedrock AgentCore Runtime with Amazon Nova Lite handles real-time buyer conversations with sub-second responses
- OpenClaw AI agent on Amazon EKS manages seller-side tasks including restocking, refunds, and escalation resolution
- AWS End User Messaging Social provides managed WhatsApp Business API integration
- Single Store API backed by Amazon RDS MySQL converges all channels; Amazon SES sends transactional emails
- Full stack deploys with one AWS CDK command in 25-30 minutes
The architecture demonstrates how to build multi-channel ecommerce experiences where buyers use preferred messaging apps while sellers manage business operations through natural language commands.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
2026
2026
2024
2025
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.