Run an online store by texting commands to an agent
Web page · https://agentusecases.ai/use-case/run-an-online-store-by-texting-commands-to-an-agent
Done with OpenClaw. A reference build where an OpenClaw agent runs store API calls from the owner's Telegram texts, while a buyer-facing agent handles WhatsApp orders and status questions.
First seen by Oriel on .
AI summary
Claw Boutique is an AWS reference build where agents manage store operations through Telegram and WhatsApp, coordinating Store API calls, customer communications, refunds, and order status.
- A Strands agent on Bedrock AgentCore using Nova Lite handles buyer WhatsApp chats, while an OpenClaw agent on EKS manages owner Telegram interactions.
- The agents share one Store API and support commands such as restocking products, apologizing to customers, and processing related refunds.
- An apology workflow sends a WhatsApp message and refund email, marks the order refunded, and closes the escalation.
- One CDK deployment provisions the system, but cold deployment takes 25-30 minutes and requires WhatsApp Business, Telegram, and verified SES credentials.
- The build demonstrates a complete web store, WhatsApp, email, Telegram, and admin dashboard lifecycle without production performance or business figures.
#ai agents #whatsapp #telegram #aws
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| Agent Use Cases | https://agentusecases.ai/use-case/run-an-online-store-by-texting-commands-to-an-agent | https://agentusecases.ai/use-case/run-an-online-store-by-texting-commands-to-an-agent Read discussion |