Assertion certainty 4/5 debate potential 1/5

Sehgal: Gemini Deep Research lacks turn limits, but users rarely go deep

Arush Sehgal · Why is everyone cloning Deep Research? · Feb 18, 2025 · at 27:13

Arush Sehgal (Lead PM for Gemini Deep Research) discusses user interaction patterns and conversation turn depth in the product.

0:00 / 0:08exact quote · 8.5s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“We don't have any hard limits on the, how many turns you can do. One thing I will say is most users don't go very deep right now.”

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 Sehgal Feb 18, 2025 ▶ 21:11 Why 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 Sehgal Feb 18, 2025 ▶ 2:59 Why 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 Sehgal Feb 18, 2025 ▶ 24:53 Why 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 Sehgal Feb 18, 2025 ▶ 32:09 Why 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 Sehgal Feb 18, 2025 ▶ 34:58 Why is everyone cloning Deep Research?
Disclosure
Sehgal: Early Gemini Deep Research testers never edited initial research plans
“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.”
Arush Sehgal Feb 18, 2025 ▶ 5:30 Why 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.