A retail/e commerce business wanted customers to be able to place orders by phone without a human taking every call, while keeping the order accurate and synced with their online store.
- 01Call intake
Customer calls a dedicated number; an ElevenLabs conversational agent answers and walks them through placing an order, covering product, quantity, and delivery details.
- 02DTMF confirmation steps
Key decision points (e.g. confirming an order total, choosing a delivery slot) use keypad (DTMF) input for accuracy, rather than relying purely on speech recognition for critical values.
- 03Product lookup
The agent queries the store's product catalogue via the Shopify GraphQL API in real time to confirm product availability and pricing before finalizing the order.
- 04Order creation
Once confirmed, an order is created directly in Shopify via a GraphQL mutation, so it appears in the merchant's normal order management flow exactly like a web order.
- 05Confirmation
The customer receives a spoken order summary on the call, functioning like a live checkout confirmation.
Orders placed by phone flow directly into the same system as online orders, with no manual re entry step.
Originally built for the retail sector, the same architecture applies to any team facing a similar volume, compliance, or coordination problem. The stack (ElevenLabs, Twilio, DTMF, and others) is stable, self hosted where it matters, and designed to be operated by a small team without a platform crew.
- AI voice ordering
- Shopify voice AI integration
- phone ordering automation
- AI phone assistant for retail
- ElevenLabsSpeech synthesis for the voice agent. Chosen for latency and voice quality on production calls.
- TwilioTelephony carrier. Handles inbound and outbound PSTN, SMS, and recording.
- DTMFKeypad input capture on live calls, used for menus and payments.
- Shopify GraphQL APIExternal API integrated into the workflow for a specific step.
- n8nWorkflow runtime and orchestration. Every scheduled job, webhook, and branch lives here so the logic is version controlled and observable.
The next iteration would push more of the intent routing into a smaller, cheaper model with structured outputs, keeping the expensive model only for the last mile. It cuts cost noticeably at scale without hurting quality.
Turning a phone call into a Shopify order with voice AI. Architecture walkthrough with the DTMF for accuracy design decision as a key insight.
Does it work with Shopify or only headless commerce?+
It ships with a Shopify GraphQL integration by default, and the pattern extends to any commerce backend with a product and order API.
How does it handle payment?+
DTMF capture through Twilio for card entry, or a link sent by SMS mid call for customers who prefer to complete checkout on their phone.