PilotOpen protocol for stores.Explore ACP
Back to Glossary

AI / ML

Embedding

A numerical representation of text in a high-dimensional vector space where semantically similar items are positioned close together. 'Running shoes for flat feet' and 'supportive athletic footwear for low arches' would have similar embeddings despite different words. AI agents use embeddings to match product data to user queries by semantic meaning, not just keyword overlap. This is why natural, descriptive product content outperforms keyword-stuffed titles in agent commerce.

Why it matters

It is what lets a system find things by meaning rather than by keyword, which is why a search for winter creative can return an ad tagged only cold weather.

In practice

Mostly infrastructure. It matters when semantic search returns near-misses: the embedding is grouping by a similarity you did not intend.

Related terms