AI / ML
Vector Search
Searching by semantic similarity rather than keyword matching. Instead of finding documents containing the exact words 'budget moisturizer for dry skin,' vector search finds products whose meaning is closest to that intent — including products described as 'affordable hydrating cream for sensitive, dehydrated complexions.' AI shopping agents use vector search to match user queries to products, which is why keyword-stuffed titles perform worse than naturally descriptive ones.
Why it matters
It is the retrieval half of RAG and the reason an agent can find the relevant past decision without anyone having tagged it.
In practice
Judge it on whether the retrieved items are actually the right ones. Most disappointing agent answers are retrieval failures, not reasoning failures.
Related terms