ticket_triage · ecommerce · workflow
Wayfair automates supplier ticket triage with a hybrid LLM-agent workflow (Wilma)
Wayfair's supplier associates performed manual, rote ticket triage — reviewing unstructured ticket data, looking up supplier IDs in a database, and entering structured fields by hand — causing slower response times and accuracy problems in classification.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Supplier email creates ticket
When a supplier emails Wayfair, a new ticket is created in SupportHub and a Pub/Sub event invokes the LangGraph orchestration graph.
Tools used
WilmaLangGraphPub/SubBigQueryJIRA APIArizeSupportHubReAct
Outcome
The hybrid Wilma workflow achieved better-than-human performance with 93% accuracy on question type (vs. 75% for humans), 98% on language, and 88% on supplier ID, while reducing ticket processing time and freeing associates for high-value work.
What failed first
A fully agentic design using a supervisor coordinating multiple sub-agents failed due to inter-agent communication errors and unnecessary repeated calls; in one case an agent incorrectly decided not to invoke the JIRA API to update the ticket.
Results
Time savedreduces the time it takes to process a ticket
Volume93%
Grounding & classification
Source type: technical build writeup
33 fields verified against source quotes.
agentic workflowai agentdata extractiondocument classificationemailsupport ticketfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedecommerceaccuracy improvementcycle time reductionemployee productivitytechnical build writeupback office opsticket triageagentic task executionextract classify route