Skip to content

Wyze Agentic Commerce Pipeline

Click-to-delivery fell by more than 50%, with every order routed on live stock and carrier data.

Shopping agents buy Wyze products and then manage the order, with fulfillment routed autonomously per order.

What the agents do

External shopping agents complete a purchase, and each order is then routed autonomously across fulfillment centers and third-party partners.

Brand
Wyze
Built by
Pipe17, with the Wyze ecommerce and operations team
Contributed by
Pipe17 (Order operations and MCP server), Stripe (Agentic Commerce Suite)
Industry
Retail, Technology
Audience
B2C
01
The problem

Why this exists

There was no established playbook for processing an order placed by an AI agent. When a consumer asks an assistant for a smart home camera under a price, the agent has to discover products, evaluate options, and transact, and the resulting order still has to flow through validation, fulfillment routing, shipping, and post-purchase support. No conventional ecommerce workflow was designed for that.

Read more

Underneath sat a second problem. Wyze already ran a multi-channel, multi-fulfillment operation across Amazon Multi-Channel Fulfillment, direct warehouse, and 3PL partners, and routing decisions were made by dedicated staff, per order, on inventory levels, geography, shipping cost, and carrier availability. Rules-based routing tables handled the simple cases but could not react to real-time inventory movement or carrier disruption.

The third constraint was structural. Adding AI agents as a channel could not mean adding another operational silo, or the overhead would scale linearly with channels and defeat the point of composable architecture.

02
Outcomes

What changes when this is in place

  • Order-to-fulfillment handoff moved from hours per batch to seconds, with routing decided per order in real time.
  • Click-to-delivery time fell by more than 50%, with each order routed to the optimal location on live inventory, geography, and carrier performance.
  • The same infrastructure carries direct-to-consumer, marketplace, retail, and agentic orders with no incremental operational headcount. Adding AI agent buyers required no additional manual processes and no changes to existing fulfillment infrastructure.
Read more
  • Post-purchase support runs agent to agent. An MCP-enabled assistant queries order status, tracks shipments, and starts returns without a human touch.
  • The agentic interface is also more accessible than a conventional storefront for consumers who find site navigation difficult or who prefer a conversational route.
03
How it works

Architecture

The pipeline has two layers. Before purchase, external shopping agents browse the Wyze catalog through an agentic commerce API that exposes products, pricing, and real-time inventory, and pay through Stripe's Agentic Commerce Suite. The agents are third-party: ChatGPT, Claude, Gemini, and Perplexity, built and operated independently of both Wyze and Pipe17.

Read more

After payment, order data flows to Pipe17. The orchestration engine runs as an independent microservice: it receives the order, reads live inventory from each fulfillment partner through their own APIs, evaluates the options, and routes autonomously to the best location. Order lifecycle events flow back to Wyze's ERP and logistics partners.

The post-purchase interface is a Model Context Protocol server purpose-built for order operations. Any agent in any framework can query and act on orders in natural language with no custom integration, which is what removes the per-platform integration cost. Order events stream back over webhooks, and the open onX (Order Network eXchange) schema standardizes the order objects exchanged.

Pipe17 built the order-operations orchestration and the MCP interface in partnership with Wyze's ecommerce and operations team. Wyze owns catalog, merchandising, and fulfillment-partner selection. The system has been operational since January 2026; Wyze has run on the orchestration platform since 2023 and the order-management MCP server launched in September 2025.

Before purchase, third-party shopping agents browse the Wyze catalog through an agentic commerce API and pay through Stripe's Agentic Commerce Suite. After payment the Pipe17 orchestration engine, an independent microservice, reads live inventory from each fulfillment partner and routes autonomously to the best location, with events flowing to Wyze's ERP and logistics partners. An order operations MCP server lets any agent in any framework act on orders, and the open onX schema standardizes the order objects.

Before purchase, third-party shopping agents browse the Wyze catalog through an agentic commerce API and pay through Stripe's Agentic Commerce Suite. After payment the Pipe17 orchestration engine, an independent microservice, reads live inventory from each fulfillment partner and routes autonomously to the best location, with events flowing to Wyze's ERP and logistics partners. An order operations MCP server lets any agent in any framework act on orders, and the open onX schema standardizes the order objects.
Open standards used
Model Context Protocol (MCP)onX (Order Network eXchange)REST APIsWebhooks
Tech stack
Pipe17 order orchestrationPipe17 MCP serverStripe Agentic Commerce SuiteAmazon Multi-Channel Fulfillment3PL partners
Get hands-on

Resources

Next step

Request an intro

Pipe17 is behind this solution. Ask about routing agentic orders automatically, and the MACH Alliance will put you in touch with the person who can answer.

The MACH Alliance passes your details to a named contact at Pipe17 who knows this work and can answer your questions. We aim to reply within 2 business days. Your details are handled under the MACH Alliance privacy policy.

Not ready to talk to anyone? MACH Insider is the Alliance mailing list. New solutions, program openings, and the research behind them, once a month.

Everyone credited on this solution

  • Pipe17Order operations and MCP server
  • StripeAgentic Commerce Suite

Every organization named here has a page listing the rest of its work on the Hub.

Keep reading

Related solutions

Verification

Published case study

The detail on this page is drawn from a case study published by the contributor or the MACH Alliance. Any figures on this page are the ones that case study states.

Where this came from

Solution detail is published from the contributor's 2026 Agent Ready submission to the MACH Alliance. Submitter names and contact details are not published. Additional detail is drawn from the published MACH Alliance case study on Wyze.

Status: Live in productionAdded Apr 29, 2026A listing is an editorial decision, not a MACH Alliance certification.

Built something worth showing?

Put your agentic solution in front of the enterprise leaders who use the hub to decide what to build next. Submissions are open to MACH Alliance Members, Collaborators, or Ambassadors.