Wayfair Uses OpenAI to Fix 2.5 Million Product Tags and Automate 41,000 Support Tickets

Wayfair has corrected 2.5 million product tags and automated 41,000 support tickets per month after integrating OpenAI models into its operations.

The home goods retailer, one of the world's largest, embedded OpenAI models into core workflows—not as experiments, but as production systems. The focus: supplier support and product catalog quality at scale.

"The better our data quality, the more trust we build with the customer," said Jessica D'Arcy, Associate Director of Catalog Merchandising at Wayfair. "It's essential because it empowers shoppers to make the right buying decisions, directly reducing costly downstream issues like returns from misrepresented products."

Wayfair's catalog team manages tens of millions of products across nearly a thousand product classes. Before OpenAI, tagging improvements relied on suppliers and customers reporting errors—manual effort that couldn't keep up. Early custom AI models worked but were expensive to build and maintain.

To scale, Wayfair created a tag-agnostic system built on a single OpenAI model. The team is now expanding model coverage to new attributes at 70x the rate of a year ago. A controlled A/B test showed substantial increases in impressions, clicks, and page rank for products with enhanced attributes.

On the support side, Wayfair built an AI assistant named Wilma that reads incoming requests, fills in missing context, and routes tickets to the appropriate team. It went from prototype to live in about one month.

"Wilma gives associates leverage," said Graham Ganssle, supplier support operations at Wayfair. "It reads the ticket, identifies intent, fills in context from our databases, reaches back out to suppliers if necessary, and points the issue in the right direction."

The company has deployed a dozen agentic AI flows for specific resolution teams. When alignment between AI recommendations and human decisions consistently reaches a threshold, workflows shift from assistive "co-pilot" to semi-autonomous "autopilot" modes.

Wayfair has also deployed over 1,200 ChatGPT Enterprise seats across its ~12,000-person workforce.