ecommerce_ops · ecommerce · workflow
Mercury: eBay's Agentic AI Platform for LLM-Powered Personalized Recommendation Experiences
Scaling LLM-powered recommendation experiences to serve hundreds of millions of eBay customers across billions of listings is both challenging and costly, and LLMs alone cannot access eBay's dynamic real-time inventory.
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 · User shopping signal received
User shopping missions and activity patterns trigger the recommendation pipeline.
Tools used
MercuryRAGLLMsVector DatabasesKNNBERTCommon CrawlLangGraphGoogle
Outcome
Mercury enables eBay to deliver highly accurate, recent, and contextually relevant product recommendations at scale, setting a new standard for AI-driven large-scale e-commerce solutions.
Results
Time savedas little as hundreds of ms
Grounding & classification
Source type: technical build writeup
31 fields verified against source quotes, 1 dropped as unverifiable.
agentic workflowanomaly detectionmulti agent workflowpersonalizationragrecommendation systemknowledge baseproduct catalognamed customerproduction runtime claimedtools describedworkflow describedecommerceaccuracy improvementcycle time reductiontechnical build writeupecommerce opsagentic task executionextract classify routerag answering