Adaptive Instructed-Retriever delivers high-quality search at reduced latency.
search
9 tracked signals on search.
Agents will use the web 1,000x more than humans, requiring reinvented search infrastructure
“We started parallel with the bet that agents would do it a thousandx more than humans ever have.”
DoorDash distills LLM capabilities into traditional search systems using four semantic primitives
“the real bottleneck is semantic understanding. That is, it's knowing what elements actually mean to users, given a certain context, and what the shopper actually intends to do”
Traversal builds SRE agents that search petabyte-scale logs with no labeled training data
“a single investigation's probably gonna cost you the GDP of a small country”
Google integrates hotel booking, airfare tracking, and loyalty rewards into AI Mode Search
Use LLM-hallucinated tags plus vector embeddings to match against large existing vocabularies
Google promotes Search-based home decor discovery as a consumer AI use case
Google Search integrates AI features for consumer lifestyle tasks like party planning.
Apple's WWDC26 session details new search field patterns and Liquid Glass design for iOS, iPad, and Mac apps.
“And with liquid glass, we introduce new patterns that make search more ergonomic on iOS, and that take full advantage of the larger displays on iPad and Mac.”