● Covered by 1 source · 1 reportLow impact1 neutral
Building a Restaurant Telephony AI Host with Amazon Connect
Key points
- AI host answers calls, takes orders, and confirms details.
- Uses Amazon Connect, Lex V2, Agentic Voice, and AI agents.
- Solution handles telephony channel, identifies callers by phone number.
- Ordering logic is separate from the communication channel.
Addressing Phone Orders with AI
Many restaurants still receive a significant number of orders via phone, often leading to staff being overwhelmed and customers experiencing hold times. This new solution aims to automate this process, allowing restaurants to manage call-in orders more efficiently without requiring additional staff or forcing customers to use apps or websites.
Technical Implementation
The system leverages several Amazon Web Services components. Amazon Connect Customer handles the telephony channel, while Amazon Lex V2 with Amazon Connect Agentic Voice provides real-time speech recognition and synthesis. Amazon Connect Customer AI agents orchestrate the conversation, connecting to a restaurant backend via the Model Context Protocol (MCP) and Amazon Bedrock AgentCore.
System Capabilities
When a customer calls, the AI host greets them, answers menu questions, helps find a nearby pickup location, and confirms the order verbally. The solution is designed to handle the audio over the phone network and identifies callers by their phone number. The architecture separates the ordering logic from the communication channel, allowing for flexible deployment and integration.
Deployment and Features
The guide details how to deploy the system using AWS Cloud Development Kit (AWS CDK). Key features include answering inbound calls with Amazon Connect, routing through a contact flow, real-time speech recognition and synthesis with Amazon Connect Agentic Voice, conversation orchestration with an Amazon Connect AI agent, and maintaining conversation safety with an Amazon Connect AI Guardrail. The agent connects to backend services as discoverable tools through AgentCore Gateway and MCP.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
Primary sources
GitHub aws-samples/sample-restaurant-telephony-ai-host-using-amazon-connect-customerReporting from
Amazon Web Services published a guide on how to build an AI-powered voice ordering system for restaurants using Amazon Connect. This system allows customers to place orders over the phone without human intervention, addressing a common challenge for restaurants with high call volumes.