AWS released a technical blueprint for building an AI voice ordering system that answers restaurant phone calls using Amazon Bedrock AgentCore and Amazon Nova 2 Sonic.
The system addresses a widespread problem: restaurants miss an average of 150 calls per location monthly, with about 60 percent of those being orders or reservation requests that arrive during peak service times when staff are unavailable.
The architecture separates the phone layer, agent layer, and restaurant backend, allowing the same agent to serve multiple channels (phone, mobile app, kiosk) without rewriting the backend logic.
What happened
AWS published a technical guide showing how to build a voice AI system that answers restaurant phone calls, takes orders, and books tables. The system uses Amazon Bedrock AgentCore to run the conversation logic, Amazon Nova 2 Sonic for speech processing, and connects to a restaurant backend through the Model Context Protocol. The full stack deploys via AWS CDK and bridges phone calls through a SIP gateway on Amazon ECS Fargate.
Why it matters
Restaurants miss an average of 150 phone calls per location every month, with about 60 percent of those being customers trying to place an order or book a table—calls that often come during dinner service when staff are busiest. This AI host can answer those calls without pulling workers off the floor, solving a problem that website or app ordering alone cannot address.
What to watch
The solution warms the agent session while the phone is still ringing to avoid dead air, and uses a microVM-per-call isolation model in AgentCore Runtime. A sample repository and deployment script are available on GitHub, with prerequisites including access to Amazon Nova 2 Sonic in Amazon Bedrock, Amazon Chime SDK PSTN Audio, and AgentCore Runtime availability.
Ask the AI about this article →
The problem this solution addresses is concrete and widespread: restaurants lose business because they miss inbound calls during peak service hours, when answering the phone becomes logistically impossible. The article notes that approximately 60 percent of the 150 calls per location monthly are order or reservation requests—precisely the calls that represent lost revenue. Adding a website or mobile app helps customers who prefer to order online but does nothing for callers who prefer the phone, creating a gap that no single digital channel has closed.
The technical architecture reflects a deliberate design principle: separating the phone layer (SIP gateway, media handling), the agent layer (conversation logic and speech processing), and the restaurant backend (menus, orders, locations). This separation means the ordering logic is decoupled from the telephony channel, allowing the same agent and backend to serve multiple interfaces (phone, app, kiosk) without duplication. The use of the Model Context Protocol as an open standard between the agent and backend further enables the restaurant to change backend systems without redeploying the agent itself.
The system also solves a user-experience problem that is often overlooked: cold start latency. By warming the agent's microVM session while the phone is still ringing, the solution ensures the caller hears a greeting immediately, avoiding the awkward silence that would damage trust in an automated system. This detail reveals an understanding that voice ordering systems are sensitive to timing in ways web-based systems are not.
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
Visko raised $10 million in pre-seed funding from Llama Ventures and opened public access to its first foundat…
U.S. markets ended August higher, with the S&P 500 up 2.6% and the Nasdaq up 3.9%
Neurovia AI, an Abu Dhabi-based company, is pitching Saudi security agencies software that it says can compres…
AI company Runway has unveiled Solaris, the first model in a new category it calls "Interface World Models." I…
Google's AI search gave advice to call emergency services for users alone with an African, Indian, or Pakistan…
John Deere introduced JD, a conversational AI tool that lets farmers ask open-ended questions about their hist…
