Scalable Language System for Product Size Naming
Data scientists figured out how to enable shoppers to filter options based on their ideal size choice for everyday essential items. They just needed a way to accurately express it. I developed the guidelines behind a Scalable Language System for Product Size Naming that helped create a more convenient shopping experience that saves time and money.
WHAT I DID
• Transformed static size labels into a dynamic UX system, treating naming as a conversational problem to ensure LLM outputs remained intuitive and human-centered.
• Developed distinct nuanced behavioral definitions for seemingly synonymous terms—such as "Travel Size" (portability) vs. "Compact" (space efficiency) vs. "Individual" (portioning)
• Introduced scalable decision trees that enabled LLMs to ensure accuracy across hundreds of product types.
• Designed a repeatable four-step process to standardize how AI systems select and deploy sizing language.
More Amazon portfolio samples
Trade Across
Guiding customers to discover relevant items by developing an LLM-driven framework for personalized shopping.
Rufus
Developing the next generation of conversational guardrails to help shoppers better understand product features.
