StubHub International built and launched a powerful AI customer support agent in 90 days using Voiceflow, empowering non-technical teams and transforming their support operations.
Read the StubHub storyCommon use cases
What teams in e-commerce & retail automate first
Every one of these is a real agent conversation, running in the channel the customer started in.
The agent reads the carrier scan and the delivery photo, issues the replacement, and a human catches the order before it leaves the warehouse.
See how order agents are built
A size swap done in four messages: exchange created, QR label sent, the medium shipping before the large is even dropped off.
See how returns agents are built
From a one-line brief to three fitting picks with sizing advice, and a store associate holding the gift-wrapped one downtown before Saturday.
See how discovery agents are built
Setup help, a fix for a mis-seated burr collar, automatic warranty registration, and a monthly care reminder: the product kept working after the sale.
See how care agents are built
90
Days from idea to launch
Also building on Voiceflow
Peak-season scale
Built for peak-season volume. Certified for customer data.
Production volume, and the certifications to run it on regulated data.
99.95
%
Agent uptime
50
ms
Voiceflow latency
300
K
Messages per minute scale
Works with the retail CX stack you already run.
Voiceflow hands off to your human team with the full conversation, so nobody asks the customer to start again.
There is no migration project. Voiceflow sits on top of the CX stack you already run, and speaks to anything else through the API.
Most retailers are live on their existing helpdesk the same day, with no change to commerce or fulfilment systems.
Frequently asked questions
Can agents act on live order data?
Yes. Agents call your commerce platform directly — Shopify, a custom OMS, or both — so status, returns, and cancellations reflect real state, not a cached copy.
How do agents handle peak season?
Capacity scales with traffic, and deflection holds through spikes because resolution does not depend on staffing.
Do agents work across channels?
The same agent runs on web chat, in-app, SMS, WhatsApp, and voice, with one set of logic and one transcript history.