Superpower Daily
OpenAI Loses Data Center Chief While Pursuing a Reported $600 B...Alibaba Raises HK$80B for Full-Stack AI as Investors Question t...LLMScholarBench Tests 22 Models and Finds an Accuracy-Represent...Meta Adds Voice-Controlled AI and Navigator Home Screen to Ques...Harvard Uses 7 AI Faculty Avatars in a $699 Founder Bootcamp, W...DeepSeek V4 Pro Lands on Fireworks With $2.50 CyberGym Solves,...OpenAI Loses Data Center Chief While Pursuing a Reported $600 B...Alibaba Raises HK$80B for Full-Stack AI as Investors Question t...LLMScholarBench Tests 22 Models and Finds an Accuracy-Represent...Meta Adds Voice-Controlled AI and Navigator Home Screen to Ques...Harvard Uses 7 AI Faculty Avatars in a $699 Founder Bootcamp, W...DeepSeek V4 Pro Lands on Fireworks With $2.50 CyberGym Solves,...
Toolspublished

AWS Publishes a Phone-Ordering AI Pattern That Connects Restaurant Data to Claude

The sample shows how a voice agent can take an order from a phone call through backend tools, but restaurants must supply and operate the systems holding their own menus, carts, orders and locations.

By 3 min read
AWS Publishes a Phone-Ordering AI Pattern That Connects Restaurant Data to Claude
Sign in to save and react

Listen to this story

The audio brief

About 1:42
0:001:42
Read transcript
AWS has published a deployable pattern for an AI phone host that can answer restaurant calls, discuss the menu, recommend a pickup location, manage a cart, and confirm an order aloud. The important distinction is that this is not a ready-made restaurant system. It is an integration blueprint connecting the phone channel, the AI agent, and a backend the operator must provide and run. Amazon Connect receives the call and starts the contact flow. Amazon Lex V2 handles speech recognition and spoken responses through Agentic Voice, while Claude Haiku 4.5, running in Amazon Bedrock, manages the conversation. When the agent needs menu data or has to change a cart or place an order, it calls backend functions exposed through Amazon Bedrock AgentCore Gateway using the Model Context Protocol, or MCP. In the sample, those functions run through API Gateway and Lambda, with DynamoDB and Amazon Location Service supporting menus, carts, profiles, orders, and locations. AWS supplies sample code and an AWS CDK deployment, but not the live data layer. Restaurants still have to connect their own records, APIs, and business rules—and govern what the agent is allowed to do. The design also includes an Amazon Connect AI Guardrail for content filters, denied topics, and profanity, alongside authorization for gateway and REST APIs. Deployment depends on regional service availability, access to Claude Haiku 4.5, a Connect phone-number quota, and configured AWS tooling. The practical constraint is clear: making the call work is easier than safely turning live restaurant operations into agent-accessible tools.

Story brief

3 key points

AWS has released a deployable CDK reference pattern for voice-based restaurant ordering, combining Amazon Connect, Lex V2, Claude Haiku 4.5 on Bedrock, and MCP-connected backend tools. The sample demonstrates calls, menus, carts, locations, profiles, and order placement, but it is not a managed restaurant system: operators must supply and govern the live data and APIs. Deployment also depends on regional service...

  1. 01

    The sample’s restaurant backend uses API Gateway, Lambda, DynamoDB, and Amazon Location Service for menus, carts, profiles, orders, and locations.

  2. 02

    AgentCore Gateway exposes backend functions as discoverable MCP tools, keeping ordering logic separate from the Amazon Connect phone channel.

  3. 03

    AWS provides sample code and CDK deployment—not a managed data layer—so operators must connect their own menus, orders, and business rules.

AWS has published a deployable reference architecture for a restaurant AI host that answers phone calls, handles menu questions, recommends pickup locations, manages a cart and confirms an order aloud. The useful distinction is not a finished restaurant product: it is an integration pattern that joins Amazon Connect telephony, an AI agent and an operator-managed ordering backend.

One call, several specialized layers

The design divides the work. Amazon Connect receives the inbound call and runs its contact flow. Amazon Lex V2, using Amazon Connect Agentic Voice, converts speech to text and generates spoken replies. An Amazon Connect AI agent drives the conversation with Anthropic Claude Haiku 4.5 in Amazon Bedrock.

When the agent needs restaurant information or must change an order, it calls named tools exposed by Amazon Bedrock AgentCore Gateway through the Model Context Protocol, or MCP. The gateway passes those requests to backend APIs, which the sample implements with API Gateway and Lambda functions backed by DynamoDB and Amazon Location Service.

The boundary that makes the sample useful

AWS’s sample backend contains the restaurant-facing functions: menu retrieval, cart management, order placement, customer profiles and location lookup. But AWS supplies the CDK deployment and sample code, not a managed restaurant data system. An adopter must connect and operate the backend that reflects its own menu, orders, locations and customer records.

That separation is the architecture’s central design choice. AWS says MCP is an open standard for connecting agents to external tools, allowing the backend to change without altering the agent. The pattern therefore aims to keep ordering logic independent of the phone channel rather than embed it inside the telephony workflow.

Controls and deployment conditions

The reference design attaches an Amazon Connect AI Guardrail to the agent, with content filters, denied topics and profanity filtering. Its backend gateway validates custom JWT authorization against the Amazon Connect instance, while the sample places its REST endpoints behind IAM authorization.

What an operator needs before deployment

  • Amazon Bedrock access to Anthropic Claude Haiku 4.5 in the selected AWS Region.
  • An Amazon Connect phone-number quota and a Region where Agentic Voice, Connect AI agents, AgentCore Gateway and the selected Bedrock model are available.
  • An AWS account, configured AWS CLI credentials, Node.js, Git and a bootstrapped AWS CDK environment.

The full implementation is available as a sample repository and deploys its stacks through AWS CDK. For restaurant operators, the practical test is less whether the call can reach an agent than whether their live order data and business rules can safely become the tools that agent is allowed to use.

Sources

  1. aws.amazon.comBuilding a restaurant telephony AI host with Amazon Connect | Amazon Web Services

Related coverage

Continue reading