Arush Sehgal, lead PM for Gemini Deep Research at Google, discusses user interface adaptations made to encourage human-in-the-loop steering before the model runs web searches.
“Actually like in early rounds of testing, we saw no one was editing, and so we were just like, if we just put a button here, Maybe people will, like, engage more.”
quote is from the automated transcript, cleaned for reading:
filler sounds and stutters are removed, nothing is rephrased. names can be misheard
(the analysis reads context, assessments check outside sources). how →
More from Arush Sehgal
Insight
Sehgal: Keep recent research tasks in context, relegating older ones to RAG
“Just to add to that, I think like, just like a simple rule of thumb that we use is like, if it's the most recent set of research tasks where the user is likely to ask lots of follow-up questions, that should be in context. But like, as stuff gets 10 tasks ago,…”
Arush SehgalFeb 18, 2025▶ 21:11Why is everyone cloning Deep Research?
Insight
Sehgal: AI deep research provides most lift on niche, non-Wikipedia topics
“We love to test, like, super niche random things, like, things where there's, like, No Wikipedia page already about this topic or something like that, right? Because that's where you'll see the most lift from a feature like this.”
Arush SehgalFeb 18, 2025▶ 2:59Why is everyone cloning Deep Research?
Insight
Sehgal: Deep research evals should categorize research behavior, not domain verticals
“And really what we tried to do is like, stay away from like verticals, like travel or shopping and things like that, but really try and go into like, what is the underlying research behavior
Type that a person is doing.”
Arush SehgalFeb 18, 2025▶ 24:53Why is everyone cloning Deep Research?
Disclosure
Sehgal: Google shipped a 5-minute Deep Research mode fearing user drop-off
“I remember we actually built two versions of deep research. We had like a hardcore mode that takes like 15 minutes. And then what we actually shipped is a thing that takes five minutes. And I even went to Eng and I was like, there has to be a hard stop, by the…”
Arush SehgalFeb 18, 2025▶ 32:09Why is everyone cloning Deep Research?
Insight
Sehgal: Users always max out AI power toggles if given the option
“If you like give a max power button, users are always just going to hit that button, right? So then the question comes like, why don't you just decide from the product POV where's the right balance?”
Arush SehgalFeb 18, 2025▶ 34:58Why is everyone cloning Deep Research?
AssertionSupported
Sehgal: Gemini Deep Research retains all browsed websites in context
“We actually keep everything in context, like all the sites that it's read remain in context. So if there's a piece of missing information, it can just fetch that.”
Arush SehgalFeb 18, 2025▶ 12:35Why is everyone cloning Deep Research?
Made with StarZero
Turn any episode into a week of clips.
This entire site, over 200 episodes transcribed, diarized, checked and made playable,
runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the
moments worth sharing, cuts them, captions them, and reframes them for every feed.
We use essential cookies to make the site work. With your permission we
also use analytics cookies (Google Analytics and Mixpanel) to understand
usage and improve StarZero. See our Cookie Policy.