Building in the Gemini Era – Kat Kampf & Ammaar Reshi, Google DeepMind

[music] We are super excited to be here. It's

been obviously a very exciting week in AI. It's been a very exciting and busy

AI. It's been a very exciting and busy week over here at DeepMind. I'm so super excited to chat with you about our newest models and build some demos live with you all. I'm Cat. I work on Vibe

Cody and AI Studio. This is Amomar. He

leads our product and design team for AI Studio. Uh but I want to step back for a

Studio. Uh but I want to step back for a second and talk about uh the journey at DeepMind generally. So what's I think

DeepMind generally. So what's I think particularly unique about Google's journey right now is that Deep Mind has been innovating here for not just this week or this past year but for years and

years uh with things like the transformer, Alph Go, etc. And this is obviously a graphic from 5 days ago because it ends with Gemini 2.5 and we

are super excited to have announced earlier this week Gemini 3 Pro.

Hopefully this message has reached you all already. If not, we have a lot of

all already. If not, we have a lot of work to do. Uh but this is our latest most intelligent state-of-the-art model.

Um and ultimately what we want folks to understand with Gemini 3 is that we can really build anything and that comes in two major capabilities. I think the first is the UI and aesthetic

sensibilities of Gemini 3. It's very

very strong at design understanding and generating websites and good UIs uh in one shot. And the second is with agentic

one shot. And the second is with agentic tool calling. So I think this goes back

tool calling. So I think this goes back to the sort of spectrum we're seeing with models. Sometimes you want a

with models. Sometimes you want a oneshot website and sometimes you want to do really complex tasks within you know massive code bases and that's where tool calling and agentic use can be uh

be particularly powerful. So with Gemini 3, we see on the right is a SWE um experiment where it was a base agent harness across a few different models

and we can see Gemini 3 is vastly above uh in performance in Agentic scenarios and then as well leaps above our previous models and state-of-the-art across the board. Uh so super excited to

see what you folks build with this model. Um, and in in the meantime, we,

model. Um, and in in the meantime, we, you know, launched this on Tuesday, but there was still three days left in the week, so we had to launch something else as well. So, I hand it off to Amara to

as well. So, I hand it off to Amara to talk about our pro image model.

>> Yeah. So, at Deep Mind, I think you have a few days left in the week. You choose

to launch another breakthrough model.

And so, uh, we're really excited about Nano Banana Pro, which came out yesterday. Uh, and it's a huge leap on

yesterday. Uh, and it's a huge leap on our our already state-of-the-art image model. So with Enter Pro, uh, one of the

model. So with Enter Pro, uh, one of the things that I love about it the most is its world knowledge. So it's powered by Google search. Uh, and so you can ask it

Google search. Uh, and so you can ask it all sorts of things like how do I make this tea? And it'll actually go search

this tea? And it'll actually go search Google search, create an a detailed infographic for you and diagram for you.

Uh, and there all sorts of things now with accurate information that it can do. And the other thing you're noticing

do. And the other thing you're noticing here is improved text rendering. So text

is one of those small details that if you get it wrong, you can pretty much pick it up quickly. But an Anim Pro 2 does an amazing job at text rendering.

Uh, and you can see that in a bunch of examples like here where it wraps around the can perfectly and it also has a bunch of localization as well. So, tons

of languages, Korean on the right, so it can translate images as well and render them perfectly on the exact same reference image. Uh, on top of that,

reference image. Uh, on top of that, consistency is improved. So, uh, you can now put up to 14 people in an image and then can create this group shot you can

see on the right. uh and that uh it can do more but 14 is basically our our kind of benchmark so far. Um and that also enables a whole set of new use cases. Uh

and then creative controls as well. So

you can see here on the left the focus is on the woman and on the right on the flowers and this was just a simple prompt. All you had to say was change

prompt. All you had to say was change the focus to the flowers. Maintains

everything in the previous image just changes the focus. So incredible outputs as well uh with Nano Banana Pro and a range of aspect ratios. So, if you want to generate uh wallpapers or big banners

or advertising boards, you can do all of that as well. Um, so anyway, instead of talking, we decided we're just going to show you a bunch of demos live of what we've been building with these products

uh over the last week. Um, and yeah, excited to jump into it. So, let's do that. Uh, all right. So, cat,

that. Uh, all right. So, cat,

>> yes, >> take it away.

>> Here we go. Cat tabs. Um, cool. So, for

folks who aren't familiar, this is Google AI Studio. It's our home for getting started with the latest Gemini models. You can get your API key, chat

models. You can get your API key, chat with the latest models, including Gemini 3 and a Banana Pro. Uh, but today we're going to be focusing on this build experience. So, this is our vibe coding

experience. So, this is our vibe coding experience in a studio. You can see here we have a gallery of a bunch of example apps, a bunch of very cool uh to the aesthetics point of Gemini 3, a bunch of

very cool Gemini 3 examples. Um, but you can also go prompt to apply here. And

this is free to use. And I think one of the unique things about AI Studio is how easy it is to integrate the Gemini API into your application. So we can see here at the bottom there's a bunch of

these what we call AI chips um that showcase a ton of the unique features beyond just the model you're choosing with the Gemini API. Different tools you can use like Google search grounding,

Google Maps grounding. We also let you build with our live API. So, you can do oneshot examples of I have one that lets me input a webcam of my tennis swing and it'll give live corrections on my swing.

Um, >> you also made one to improve my posture.

>> Yeah. [laughter]

>> Yeah. If you lean forward too much, live API will yell at you. Um, so it's a very flexible way to get started building AI powered apps. Um, and the other cool

powered apps. Um, and the other cool thing is you don't actually need an API key here for most of the models. So you

can build your application, you can share it with the world and anyone who comes and visits your shared application will be using their AI studio free quota. So you don't have to worry about,

quota. So you don't have to worry about, you know, hopefully you have an app that goes supervisible. You won't have to

goes supervisible. You won't have to worry about a crazy surprise API bill or anything like that. Um, so I'm going to actually shoot off a prompt here that is using our latest ano banana model. And

that basically allows us to use Google search grounding to create a illustration of laptop stickers. And

this is one of the viral trends we've been seeing with Nano Banana Pro. Um, so

I'll kick this off and what this will do, I have the AI chip that tells it to use the Pro model. And this will sum up my prompt and go talk to Gemini 3 to

break down the task and start generating my endto-end application. Uh but while that builds, I'm going to hand it off to Amara to show some demos in the meantime.

>> Cool. I think the other thing to point out here is that uh we're trying to think through how the vibe coding experience is also powered by AI every step of the way. So you're seeing here even in the loading screen, uh it is

using Gemini and thinking through this app that you're making and how you could extend it. Um, and so we're thinking

extend it. Um, and so we're thinking through breaking those typical vibe coding paradigms as well and helping you iterate with the model as your partner.

But anyway, let me jump right into the text rendering demo. So, uh, when I heard of text rendering for the first time and the consistency that we were getting with Nan Pro, my mind went to comic books. Uh, and so I was thinking,

comic books. Uh, and so I was thinking, why can't I now be in my own comic book adventure um, and also place cat in there and then maybe we can tell a story. And so uh in this app uh also

story. And so uh in this app uh also vibe coded you can just upload a face of somebody. So I've got some nurse face of

somebody. So I've got some nurse face of course [laughter] but I'll use I'll use cat here uh and myself um and then uh we can choose the

genre of the story um and and all the languages that we have so far. Uh, I'm

going to do a story about us presenting at AI Engineer um in New York uh presenting AI Studio and we are uh vibe coding and winging our presentation.

That's where we're going to be doing this comic book story. So, we'll fire that off. Uh but while we wait for that,

that off. Uh but while we wait for that, um the other cool thing about this is uh we'll wait for that to generate. But I

want to show you the design sensibilities as well. So, you know that if you've been working with AI models and generating websites, they've been creating purple gradients and things [laughter] that just, you know, they

kill me as a designer. So, um, and so it's been really nice to see how this model is able to build some beautiful websites. So, this is using shader

websites. So, this is using shader animations, uh, flowing through all these different pages, uh, and adds all sorts of cool transitions and effects.

Picked out the typography by itself. And

this was the initial prompt. Just create

a slick animation website. kind of

actually did say no cyber puncture that [laughter] >> but just got to make sure [laughter] >> but but yeah you get some incredible

results um and and now what I love about this is so many folks who you know were struggling with design who might have you know still tried to gro their way around Figma don't have to do that anymore they can actually just go in

prompt their way to something pretty nice okay back to the comic book okay pretty flattering uh comic [laughter] book here. Um, that, you know, I'll take

book here. Um, that, you know, I'll take it. Uh, and [laughter] you can see here

it. Uh, and [laughter] you can see here that it's rendering the comic book. It's

got, uh, rich text rendering showing us the story. And the other thing here is

the story. And the other thing here is that, uh, because it's powered by Gemini 3, it's actually really creative at the story it's generating. And honestly,

some of these stories have genuinely made me laugh, which is the first time uh, that's happened with one of these models. Uh, and so you can see we're

models. Uh, and so you can see we're rushing to the conference. even

background details like the AI engineer banner over here uh being rendered and of course since it's a vibe coded app we can take the story in any direction. So

one feature I did introduce is that you can choose the direction of the story midway. So you know do we find a quiet

midway. So you know do we find a quiet corner and try to check if our API keys work or do we just embrace it and go full improv? I think we're going to go

full improv? I think we're going to go full improv. Uh and so that's changed

full improv. Uh and so that's changed that story. Uh, and so talking about the

that story. Uh, and so talking about the humor here, you can see Amaraj, a woman carrying a suspicially functional robot dog. [laughter] So I don't know if that

dog. [laughter] So I don't know if that was announced at the conference today, but uh, pretty cool. Um, and then now it's generating the rest of the story here on the right while we wait. So

pretty cool to see how you can make these really dynamic, rich experiences with both the creativity of the model and Nano Pro's image capabilities.

>> Love it.

>> Yeah. Back to you, K.

>> Yeah. Yeah. I will show. Let's hope my sticker demo is finished up. Uh, cool.

So, I'm going to add an API key. So,

Nana Banana is a new model and it's uh fresh off our launch of Gemini 3. So,

for now it is a page experience in a AI studio. Um, but what I can do is I can

studio. Um, but what I can do is I can see that here I can enter different words that I want my stickers based off or I can go use Google search. So, let's

try the Google search. I'm going to type in a Mars name. And one of the other cool things about this new model is that you can select the resolution as well.

So, in this case, I'll just do 1K. Uh,

but what this will hopefully do, but again, you saw it on one shot live. Uh,

is go talk to Google search, grab the latest sources on Amar, build the context about what he likes, what his laptop stickers might look like. I think

it's just deep mind, but if he were more uh [laughter] if he wanted to express himself more.

>> Oh, boy. Uh, and so he can see here.

[laughter] >> Yeah, there he is. Weekend builder.

>> That's true.

>> Uh, yeah. And for those who don't know, Amar has a children's book, Alice and Sparkle, which, yeah, is clearly he's talked about a lot because it's highly represented here. [laughter]

represented here. [laughter] >> But, um, very cool to see how it can bring in that contextual knowledge. Um,

we've also seen this with like news events, getting relevant information on that day rather than having to rely on the knowledge cut off of the model. Um,

so one other thing I'll show you folks is how we use AI studio to build AI studio. Uh, so Amar and I have a lot of

studio. Uh, so Amar and I have a lot of ideas, only so many engineers to work on these ideas. So we love to use AI studio

these ideas. So we love to use AI studio to ideulate and explore different concepts. So, one of the concepts we've

concepts. So, one of the concepts we've been working on is I'm sure you folks have seen we announced a new Agentic IDE at Google earlier this week called anti-gravity. And we know that sometimes

anti-gravity. And we know that sometimes these web-based five coding tools you they have their limits and you may want to go into an IDE to add certain

features to the application or make it specific to mobile things like that that might be a bit limiting in AI studio right now. So, we want it to be super

right now. So, we want it to be super easy to migrate into anti-gravity. So,

what I did here was just a oneshot prompt of a screenshot of AI Studio. I

said, "Clone this UI as closely as possible and then add a flow to export to our anti-gravity app." So, we can see it did a pretty great job of cloning light mode. The screenshot was in light

light mode. The screenshot was in light mode, too, of our AI studio application and copying it and improving a little bit on Amar's designs. [laughter]

But then we see this new anti-gravity button that is creating my an export and then exporting it to anti-gravity. And I

can go and open in the IDE. And I think these are the types of creative interactions that web-based vibe coding tools can be particularly useful for because if we had went and jammed on this feature, we probably would have

constrained ourselves to existing patterns in AI Studio. And in this case, I told the model, be creative, think outside the box. And I've played with this one a bunch. Sometimes it gives a

command line interface for export or showing the status of the export etc. Uh so I think it's a super cool way for you to ideulate on new ideas for UI and kind

of expand on your product. Uh but I'll hand it back to Omar.

>> Let's do it. Uh and then the other thing that Gemini 3 has been really impressed like impressed us with is just making video games. And so this one was again

video games. And so this one was again pretty simple prompts. Make this racing game where I have a bot now at a start screen. Um, and so you can see I got

screen. Um, and so you can see I got this 3D racing game in 3JS. Uh, it drew all the things. I'm racing with a bot here. Uh, and then one thing I added for

here. Uh, and then one thing I added for myself to cheat is I can just boost away and beat the bot. So, uh, pretty nice.

But, [laughter] but the thing I want to tease actually is that um, all of these apps so far have been front-end React apps. Uh, and so the thing that's coming

apps. Uh, and so the thing that's coming very very soon to AI Studio is going to be backend support um, and full stack runtime. So if you want to install Shad

runtime. So if you want to install Shad CN, if you want to do all of those things, you'll be able to do that again with one prompt. And the principle with AI studio here is that we don't want you to think about those details. You should

just be able to ask, I want to make a multiplayer app, and we know that you need to use Express and wire that all up for you, uh, and abstract all those details away. So, we're going to try

details away. So, we're going to try something a little risky here, which is we did turn this racing game into a multiplayer one. Um, and, uh, this was

multiplayer one. Um, and, uh, this was again a couple of prompts. Uh, so we're gonna put a QR code up if you want to join us uh in the racing game.

>> We've never tried with nearly this many people, so we'll see. [laughter]

>> Hopefully this works. Yeah.

>> Uh, but QR codes up here. Uh, so if you scan that, hopefully should load the game. I'm really afraid of how this is

game. I'm really afraid of how this is going to explode. [laughter]

>> Here we go.

>> All these cars loading in.

>> Nice.

>> So yeah, if people have scanned that, we can switch back to the game. Okay. Oh my

god. [laughter]

So yeah, just hit ready uh when you're all ready. [laughter]

all ready. [laughter] Oh boy. Uh

Oh boy. Uh I think this lobby is going to explode.

[laughter] >> Never leave.

>> So this is where I shouldn't have added collisions with other cars because you could clearly see that we're bouncing around. [laughter]

around. [laughter] >> 19 players, 20 players. I don't know if this race will ever start, but we're all blocked on the uh you know the start line. But 23 players, pretty cool. Uh

line. But 23 players, pretty cool. Uh

yeah, you do all have to get ready for us to start this race. So, [laughter]

>> so we might be here all day.

Uh but yeah, that is pretty pretty incredible. Um I can't start this race,

incredible. Um I can't start this race, so do you want to wrap [laughter] up?

>> We'll see you Ollie.

>> That's pretty cool. The runtime didn't explode. Uh yeah, and I think we're

explode. Uh yeah, and I think we're super excited not only about the multiplayer game. So next time we will

multiplayer game. So next time we will have even more of you folks join uh but also you know the extensibility that comes with a full stack runtime. Uh we

want to make it super easy for you to integrate with our 1P and popular third party APIs etc. So very exciting next few months on the AI studio vibe coding side and super excited for you all to

try it. Um, but I think the one thing I

try it. Um, but I think the one thing I want to step back and emphasize is is what makes us so excited about this project and the work that a lot of us are doing is that we get to be the first generation of engineers who are building

tools for a world where anyone can build software. So I think what's beautiful

software. So I think what's beautiful about things like vibe coding is watching people. We actually talking to

watching people. We actually talking to a tech support person earlier this morning who said they started vibe coding and AI studio after seeing a YouTube video. And we're really

YouTube video. And we're really democratizing who can create things and we're all getting to build those tools that enable that. And I think it forces us to rethink the paradigms that we've

become so used to. So it may not be your base IDE that people are starting from, but how can we intuit it as much of the user intent as possible? And that's what we want to do with full stack runtime

and AI studio is make it very easy to not have to think about I want to add a database, but if your app needs storage, it'll have storage. If you want to have a if you have an e-commerce app, we'll

add a payment solution and make it as easy as possible to build the future of software. Um, so thank you folks for

software. Um, so thank you folks for joining us. If you have any cool

joining us. If you have any cool examples you've built or questions, feel free to ping me and Amara on Twitter.

Uh, and yeah, enjoy the rest of the day.

>> Yeah, thank you. [applause]

[music] >> [music] >> Heat.