AWS shows a voice ordering system that uses Connect, Lex V2, and AI agents to handle calls from greeting to confirmation.

AWS published a walkthrough for building a restaurant telephony AI host with Amazon Connect. The AI host answers inbound calls, handles menu questions, finds a nearby pickup location, and confirms the order out loud without an app, website, or sign-in.

Amazon Connect handles the phone call, Amazon Lex V2 with Agentic Voice provides real-time speech recognition and synthesis, and an Amazon Connect AI agent orchestrates the conversation. The walkthrough also covers using an AI Guardrail to keep the conversation safe and on topic.

The design keeps agent logic and backend services as separate modules, so builders can update one without touching the other. Because MCP is an open standard for connecting agents to tools, the restaurant backend can change without altering the Amazon Connect front end.

The walkthrough includes deployment with AWS CDK and explains how Agentic Voice speeds up turn-taking. Operators can use this reference to build voice ordering systems for other industries beyond restaurants.

What matters

• AWS published a walkthrough for a phone-based restaurant AI host powered by Amazon Connect.
• MCP separates agent logic from backend services, letting builders change one side without the other.
• Watch for the walkthrough on reducing turn-taking latency with Amazon Connect Agentic Voice.

Why it matters

Watch for the walkthrough on reducing turn-taking latency with Amazon Connect Agentic Voice.

This GenAI News article was prepared in original wording using reporting and materials published by AWS Machine Learning Blog. Source reference: https://aws.amazon.com/blogs/machine-learning/building-a-restaurant-telephony-ai-host-with-amazon-connect/.

Drafted by the GenAI News review pipeline.