/AI3h ago

Exa CEO Explains Why AI Agents Require New Search Architecture

--0--
Original posts
Sarah Wang#1838
Original post
Sarah Wang@sarahdingwang#1838inAI

Exa CEO @WilliamBryk explains why agents require a new search paradigm:

"Agents to humans is like humans to sloths."

"They just want to make complex queries very fast and analyze it really fast, and they want perfect output for their human users."

"You want something that can actually semantically handle complex queries, but also handle keywords, really just expose all the fundamental toggles to the agent."

"Because the agent, by the way, has the patience to add a domain filter here and a keyword filter there, or search in this way, search in that way."

"An agent doesn't just want 10 results or 10 pieces of information, it wants everything."

"I have a list of 20 different ways humans and agents are different, and when you just build it from scratch for agents, you just make fundamentally different architectural decisions."

8:47 AM · Jun 4, 2026 · 1.3K Views
Sentiment
Sentiment building, check back later.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
VIEWS1KBOOKMARKS2LIKES18RETWEETS3
Sarah Wang@sarahdingwang

Exa CEO @WilliamBryk explains the trends that predict agentic search will be a bigger business than Google within a decade:

"You could get this from basically estimating the number of LLM calls and the percentage of those LLM calls that require search, then the cost of the search, and then you just play it out."

"If you follow that trend even conservatively, you get to a massive TAM for agentic search in the '20s."

"It's hard to express how many searches will come from agents"

"The world will be filled with search in the way that the world is filled with electricity. It's a fundamental infrastructure that powers everything."

2hViews 1KLikes 18Bookmarks 2