“Humans are so lazy. The average search query is like three to five words, and then you click one of the first links and that's what you read and believe to be true. Agents are totally different beasts. They can output a search query of arbitrary length really fast, and then they can read all the results. They don't need to read one or two results. They can read a thousand.”
sputnikintelligence.com
Asked what would surprise people used to traditional search, Wang, of the agent search company Exa, says the biggest surprise is how much agents search and how differently from people.
…or the harnesses. Somehow making a search engine that conceptually is different from how you think about how the model is tied with the search engine. And it's going to be like, it might be hitting the public web as part of that process, although caching is a nice approach because you get speed.
We'll talk a little bit about the X engine itself. What do you think would surprise people who are familiar with? With any sort of traditional search?
Good question. I would say that one surprising thing is just how much agents search. Like I think it is really hard to think about how agents are different from humans. Like humans are so different. Like humans are so lazy that I think the average search query is like three to five words or something like that. Like humans type these like small search queries. Nowadays people just like a lot of people just read the Google AI overviews. But before, you know, before that, it was like you type in like three to five words to a search engine, and then you'd click like one of the first links that you saw on the search engine results page. And you'd just be like, okay, cool. Like that's going to be what I'm going to read and like what I believe to be true. And the agents are just so different. Like agents can output a search query of arbitrary length really, really fast now. And then after they do that, they can read all the results. They don't need to read one, two results. They can read a thousand results. And so, yeah, it's just the agents are totally different beasts.
Yeah. It's that's interesting that because most of us humans that go to the web search, we're sort of trained on the keyword search, right? We're like, what are the important things? Are we at a place where the sort of semantic agentic search gets better results the more words you put in?
That's correct. Yeah. I think in the long term and even now, the more information an agent is able to provide about what it wants, the better the results that it can find can be.
That's interesting. And sort of on the other end of the surprise side, are there any sort of implementations or use cases of EXA that surprised you?