AI Engineer Code 2025
Building in the Gemini Era – Kat Kampf & Ammaar Reshi, Google DeepMind
Read the talk
Building with Gemini: from generated interfaces to multiplayer apps
Kat Kampf and Ammaar Reshi build search-grounded stickers, branching comics and a multiplayer racing game, showing how AI Studio connects model capabilities to working applications.
From a talk by Kat Kampf and Ammaar Reshi
Before you start: Basic familiarity with web applications and APIs is helpful; the demonstrations do not require prior experience with Gemini or AI Studio.
What should a coding model be good at?
Do you want a polished website from one prompt, or an agent that can work through a large codebase? Those tasks demand different capabilities. Kat Kampf, who works on vibe coding and AI Studio, and Ammaar Reshi, who leads its product and design team, introduce both as parts of the same building experience. The historical backdrop runs through the Transformer and AlphaGo; even their timeline, ending at Gemini 2.5, has already fallen behind the launch week.
Gemini 3 Pro, announced earlier that week, is presented along two axes:
- Design understanding: generate a website with coherent aesthetics and a usable interface in one shot.
- Agentic tool calling: perform more complex work across large codebases through tools and successive actions.
Kat reports that Gemini 3 outperformed the comparison models in a SWE-bench experiment using a base agent harness. The talk does not supply enough evaluation detail to turn that chart into a reproducible comparison; its practical role here is to introduce the tool-driven side of the model before the live application demos.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Images that use knowledge, text and references
Nano Banana Pro, introduced as having launched the previous day, supplies the image capabilities used later in the applications. Ammaar starts with a tea-making question. Google Search provides information that the model turns into an illustrated recipe: the selected slide shows cardamom chai ingredients, preparation steps and tips. Search grounding supplies the informational context; image generation arranges it into a diagram with readable text.
Text rendering matters beyond flat labels. Ammaar shows lettering wrapped around a can, then a Korean localization that retains the reference image's composition. He next describes a group image with 14 people as the team's consistency benchmark so far, rather than a hard maximum. That spoken example differs from the published launch specification, which distinguishes up to 14 input images from maintaining the resemblance of up to five people.
The next comparison is a selective edit: a woman and flowers remain in the scene, but the focal subject changes. The instruction is simply, “Change the focus to the flowers.” The useful property is preservation: the requested attribute changes without asking for a new composition. Multiple aspect ratios then extend the same image workflow to wallpapers, banners and advertising boards.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
From an AI chip to a generated application
Google AI Studio provides model chat and API-key access, but Kat moves into its Build experience. An example gallery gives users starting points; a prompt field lets them request an application directly. The AI chips below it expose capabilities beyond model selection, including Google Search grounding and Google Maps grounding. They make those capabilities part of the application request rather than a separate integration exercise.
The Live API adds continuous interaction. Kat describes an app that watches a webcam view of her tennis swing and gives corrections, alongside a posture-feedback example that reacts when someone leans too far forward. These are applications in which the input changes over time and the response needs to arrive while the activity is happening.
In the experience described onstage, prompt-to-app building is free, most models do not require an API key, and visitors to shared applications use their own AI Studio free quota. Kat presents this as protection against a popular shared app generating an unexpected bill for its creator. This is historical billing behavior: current Build documentation assigns shared-app usage to the creator, with paid-model charges where applicable.
Kat then starts a laptop-sticker application, drawing on a trend of generating personalized sticker illustrations. The request combines Google Search grounding with the Pro image-model chip. The roles are distinct: Gemini 3 builds the application; the image model supplies the application's generated images.
- Kat submits the sticker-app request with the Pro-model capability selected.
- Gemini 3 breaks down the task and generates the end-to-end application.
- While generation runs, the loading screen uses Gemini to suggest ways the app could be extended.
The build remains in progress as Ammaar moves to other examples. Even the waiting screen is treated as an opportunity to refine the user's intent.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
A comic in progress, a website in between
Improved text rendering and character consistency suggest a natural application: put yourself into a comic book. Ammaar's generated app accepts face uploads and offers genre and language choices. He selects Kat and himself, then supplies a premise: they are presenting AI Studio at AI Engineer in New York, vibe coding and winging their presentation. That request starts the comic generation.
While the comic renders, he switches to a website example. His complaint about earlier generated sites is specific: too many purple gradients. This site instead uses shader animations, transitions across pages, visual effects and typography selected by the model. The initial request was to create a slick animation website, with an explicit instruction excluding cyberpunk styling. The example connects Gemini 3's design capability to a practical prompting technique: specify the desired effect and rule out an aesthetic you do not want. Ammaar presents this as a way for people who struggle with design tools such as Figma to reach a useful visual starting point.
Returning to the comic, the generated pages combine story text with images of the presenters rushing to the conference. An AI Engineer banner appears in the background. Gemini 3 supplies the narrative, while Nano Banana Pro supplies the images and rendered lettering. Their combination lets the app produce a story in which the environment, characters and text all contribute to the scene.
The app also lets the reader choose a direction midway through. Should the characters find a quiet corner and check their API keys, or embrace the situation and improvise? Ammaar chooses improv. The story changes, and the remaining pages begin generating from that choice. One line describes a “suspiciously functional robot dog,” illustrating the kind of incidental humor he likes in the output. The interaction is more than a request for another picture: a user decision becomes context for the next part of a multimodal narrative.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Search becomes a sheet of personalized stickers
Back in Kat's app, the first step is adding an API key. The newly launched image model is a paid experience in AI Studio at the time, an exception to the earlier description of keyless access for most models. The generated interface offers two input paths: enter words for sticker themes or use Google Search. Kat chooses Search, enters Ammaar's name and selects 1K image resolution. The intended sequence is to retrieve current sources, build context about him and turn that context into plausible laptop stickers.
The completed image includes a Weekend Builder design and references to Ammaar's children's book, Alice and Sparkle. Those details make the grounding visible: the output reflects information associated with the person searched for, rather than only generic sticker motifs. Kat then extends the same mechanism to news, where retrieving information from that day can provide context beyond the model's training cutoff.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Using AI Studio to prototype AI Studio
The next application begins with a product-team constraint: Kat and Ammaar have more ideas than available engineering time. They use AI Studio to explore interactions before committing to an implementation. One such idea is a path into Antigravity, Google's newly announced agentic IDE. A browser-based builder may be enough to start an application, but certain features or mobile-specific work can require moving into an IDE.
Kat supplies a screenshot of AI Studio and asks the model to clone the interface closely, then add an export flow to Antigravity. The generated prototype reproduces the light-mode interface and adds an Antigravity button, an export interaction and a route to opening the project in the IDE. This is a product concept being explored, not a demonstration of a generally available export integration.
The value is also in the alternatives. Kat asks the model to be creative rather than stay inside existing AI Studio patterns. Across iterations, it sometimes produces a command-line-style display of export status. A screenshot constrains the surrounding interface while the prompt leaves room to invent the new interaction, making the prototype useful for comparing product directions.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
A racing game reaches beyond the frontend
Ammaar next opens a 3D racing game generated with Three.js. Simple prompts produced the scene, a bot opponent and a start screen. He then added a boost so that he could pull ahead of the bot. This is a different test of generated software from the earlier website: the output has a running scene, player input and game behavior, not just a visual layout.
Up to this point, Ammaar says, the applications have been frontend React apps. He now previews backend support and a full-stack runtime, described as coming soon in the recorded experience. Examples include installing shadcn by prompt and translating a request for a multiplayer app into an Express backend with the necessary wiring. The proposed interface starts with the desired behavior; the builder infers the supporting packages and server work.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
The lobby works; the race cannot start
The presenters have already converted the racing game to multiplayer with a couple of prompts. They display a QR code and invite the audience to join, noting that they have never tried it with nearly this many people. Cars begin loading into the game, and Ammaar asks everyone to mark themselves ready.
Two application rules become visible under the larger crowd. Car-to-car collisions are enabled, so vehicles bounce against one another and crowd the starting line. Ammaar calls out 19, then 20, then 23 players in the lobby. These are observed lobby participation counts, not measurements of completed-race capacity.
The other rule is a readiness barrier: every player must be ready before the race starts. A JavaScript expression of that rule makes the blocking condition clear:
javascript
const players = [
{ id: "kat", ready: true },
{ id: "ammaar", ready: true },
{ id: "guest", ready: false }
];
function canStartRace(players) {
return players.length > 0 && players.every(player => player.ready);
}
const before = canStartRace(players); // false
const updatedPlayers = players.map(player =>
player.id === "guest" ? { ...player, ready: true } : player
);
const after = canStartRace(updatedPlayers); // true
In this three-player illustration, the final guest becoming ready releases the barrier. In the live demo, the barrier remains unresolved: the presenters cannot start the race. The crowd has exposed a coordination problem as well as a collision problem.
Ammaar nevertheless reports that the runtime did not crash. That separates three outcomes that would otherwise be easy to conflate:
| Part of the demo | Observed outcome |
|---|---|
| Joining the multiplayer lobby | Audience cars loaded |
| Starting the race | Blocked by the readiness requirement |
| Runtime stability | Ammaar reported no crash |
The live result is a populated multiplayer application with a stalled game flow. It demonstrates the connection path while also revealing rules that need to change for an audience-sized session.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Let the application request imply the infrastructure
The runtime's intended scope extends beyond games. Kat describes plans to make first-party and popular third-party APIs easier to integrate over the following months. A backend provides somewhere to connect those services and support capabilities that cannot live entirely in a frontend preview.
The reason to build that infrastructure into the experience is a change in who gets to make software. Kat recalls meeting a tech-support worker that morning who had started building in AI Studio after watching a YouTube video. For that user, a conventional IDE need not be the entry point. The tool's job is to understand enough of the desired application to help the person build it.
User intent should imply the required capability. Kat's closing examples are storage and payments: an application that needs persistence should receive storage without requiring its creator to ask explicitly for a database; an e-commerce application should have a path to a payment solution. These are product ambitions in the talk, rather than completed demonstrations. They set a more demanding goal for the builder than generating an attractive first screen: infer what the application needs to do, then supply the software capabilities that make it possible.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Resources
From the talk
Launch-era overview of Gemini 3's interface generation, coding benchmarks and the introduction of Google Antigravity.
Google's introduction to Gemini 3 Pro Image, including Search-grounded infographics, multilingual text, reference-image composition and focus editing.
Updates since the talk
Current instructions for generating, editing, sharing and exporting applications, including API-key handling and shared-app billing.
The speakers' later announcement of multiplayer applications, Firebase backends, external libraries and secure service integrations.
Practical documentation for server-side Node.js, package installation, secrets, databases and testing multiplayer applications.
Read the complete timestamped transcript
- 0:11
[upbeat 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 week over here at DeepMind.
- 0:29
Um, so super excited to chat with you about our newest models and build some demos live with you all. I'm Kat. I work on Vibe Coding and AI Studio.
- 0:37
This is Ammaar. He leads our product and design team for AI Studio. Uh, but I wanna step back for a second and talk about, uh, the journey at DeepMind generally.
- 0:45
So what's, I think, particularly unique about Google's journey right now is that DeepMind has been innovating here for not just this week or this past year, but for years and years, uh, with things like the Transformer, AlphaGo, et cetera.
- 0:58
And this is obviously a graphic from five days ago because it ends with Gemini 2.5. [laughs] And we are super excited to have announced earlier this week Gemini 3 Pro.
- 1:10
Hopefully, this message has reached you all already. If not- [laughs] ... 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.
- 1:27
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.
- 1:40
And the second is with agentic tool calling. So I think this goes back to the sort of spectrum we're seeing with models. Sometimes you want a one-shot website, and sometimes you wanna 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.
- 1:57
So with Gemini 3, we see on the right is a suite bench, 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.
- 2:18
Uh, so super excited to see what you folks build with this 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.
- 2:30
So I hand it off to Ammaar to talk about- [laughs] ... our pro image model.
- 2:33
Yeah. So at DeepMind, I think you have a few days left in the week, you choose to launch another breakthrough model. [laughs] And so, uh, we're really excited about Nano Banana Pro, which came out yesterday.
- 2:42
Uh, and it's a huge leap on our, our, our already state-of-the-art image model. So with Nano Banana Pro, uh, one of the things that I love about it the most is its world knowledge.
- 2:51
So it's powered by 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 Google Search, create an, a detailed infographic for you and diagram for you.
- 3:03
Uh, and there are all sorts of things now with accurate information that it can do. And the other thing you're noticing here is improved text rendering. So the text is one of those small details that if you get it wrong, you can pretty much pick it up quickly.
- 3:14
But in Nano Banana Pro 2, it 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.
- 3:27
So it can translate images as well and render them perfectly on the exact same reference image. Uh, on top of that, consistency is improved, so, uh, you can now put up to 14 people in an image, and it can create this group shot you can see on the right.
- 3:42
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.
- 3:51
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.
- 3:59
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.
- 4:09
And a range of aspect ratios, so if you wanna 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 gonna show you a bunch of demos live of what we've been building with these products, uh, over the last week.
- 4:25
Um, and yeah, excited to jump into it. So let's do that. Uh, all right. So Kat.
- 4:31
Yes.
- 4:32
Take it away.
- 4:32
Here we go. Kat Kampf. 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 with the latest models, including Gemini 3 and Nano Banana Pro.
- 4:47
Uh, but today we're gonna be focusing on this build 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.
- 5:02
Um, but you can also go prompt to app super easily 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.
- 5:14
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.
- 5:28
We also let you build with our live API, so you can do one-shot examples of... I have one that lets me input a webcam of my tennis swing, and it'll give live corrections on my swing.
- 5:38
Um, so-
- 5:39
You also may want to improve my posture, uh-
- 5:41
Yeah. [laughs]
- 5:42
... which would really help.
- 5:42
Yeah, if you lean forward too much- [laughs] ... Live API will yell at you. [laughs] Um, so it's a very flexible way to get started building AI-powered apps. Um, and the other cool thing is you don't actually need an API key here for most of the models.
- 5:55
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.
- 6:04
So you don't have to worry about, you know... Hopefully, you have an app that goes super viral. You won't have to worry about a crazy surprise API bill or anything like that.
- 6:12
Um, so I'm gonna actually shoot off a prompt here that is using our latest Nano Banana model, and that basically allows us to use Google Search grounding to create a im- illustration of laptop stickers, and this is one of the viral trends we've been seeing with Nano Banana Pro.
- 6:29
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 end-to-end application.
- 6:43
Uh, but while that builds, I'm gonna hand it off to Ammaar to show some demos in the meantime.
- 6:47
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.
- 6:54
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 through breaking those typical d- vibe coding paradigms as well and helping you iterate with the model as your partner.
- 7:11
But anyway, let me jump right into the text rendering demo. So, um, when I th- heard of text rendering for the first time and the consistency that we were getting with Nano Banana Pro, my mind went to comic books.
- 7:21
Uh, and so I was thinking, "Why can't I now be in my own comic book adventure, um, and also place Kat in there, and then maybe we can tell a story?"
- 7:29
And so, uh, in this app, uh, also vibe coded, you can just upload, uh, a face of somebody. So I've got Sunir's face, of course. [laughs] [laughs]
- 7:37
But I'll use, I'll use Kat 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.
- 7:48
Uh, I'm gonna 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. [laughs]
- 7:59
That's what we're gonna be doing in this comic book story. So we'll fire 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 wanna show you the design sensibilities as well.
- 8:12
So you know that if you've been working with AI models and generating websites, they've been creating purple gradients and things- [laughs] ... that just, you know, they kill me as a designer. [laughs]
- 8:20
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 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
- 8:39
website." Kinda actually did say no cyberpunk shit, though. [laughs] [laughs]
- 8:44
But-
- 8:45
Close. [laughs]
- 8:47
Just gotta make sure. [laughs]
- 8:49
Yeah.
- 8:49
But, but yeah, you get some incredible results. Um, and, and now what I love about this is so many folks who, you know, are struggling with design or might have, you know, still tried to grok their way around Figma don't have to do that anymore.
- 9:01
They can actually just go in, prompt their way to something pretty nice. Okay, back to the comic book. Okay, pretty flattering, uh- [laughs] ... comic book here. Um, that is... [laughs]
- 9:11
You know, I'll take it.
- 9:12
Yeah. [laughs]
- 9:12
Uh, and [laughs] 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 that, uh, because it's powered by Gemini 3, it's actually really creative at the story it's generating.
- 9:27
And honestly, some of these stories have genuinely made me laugh, which is a first time, uh, that's happened with one of these 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.
- 9:41
And of course, since it's a vibe coded out, we can take this story in any direction. So one feature I did introduce is that you can choose the direction of the story midway.
- 9:50
So, you know, do we find a quiet corner and try to check if our API keys work? [laughs] Or do we just embrace it and go full improv? [laughs] I think we're gonna go full improv.
- 9:59
Uh, and so that's changed that story. Uh, and so talking about the humor here, you can see Ammaar dodged a woman carrying a suspiciously functional robot dog. [laughs] So I don't know if that was announced at the conference today, but, uh, pretty cool.
- 10:12
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 Banana Pro's image capabilities.
- 10:26
Love it.
- 10:27
Yeah. Back to you, Kat.
- 10:28
Yeah, yeah. I will show, let's hope my sticker demo is finished up. Uh, cool. So I'm gonna add an API key. So Nano Banana is a new model, and it's, uh, fresh off our launch of Gemini 3, so for now it is a paid experience in A- AI Studio.
- 10:46
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.
- 10:54
So let's try the Google Search. I'm gonna type in Ammaar's name, and one of the other cool things about this new model is that you can select the resolution as well.
- 11:04
So in this case, I'll just do 1K. Uh, but what this will hopefully do, but again, you saw it one shot live, uh, [laughs] is go talk to Google Search, g- grab their latest sources on Ammaar, build the context about what he likes, what his laptop stickers might look like.
- 11:19
I think it's just DeepMind, but if he were more, uh, [laughs] if he wanted to express himself more.
- 11:25
Oh, boy.
- 11:25
Uh, and so he can see here-
- 11:28
Oh, boy. [laughs]
- 11:29
Yeah. There he is. Weekend builder. [laughs]
- 11:32
Right. That's true. Yeah.
- 11:33
Uh, yeah, and for those who don't know, Ammaar has a children's book, Alice and Sparkle-
- 11:36
Yeah
- 11:36
... which, yeah, is clearly, he's talked about a lot 'cause it's highly represented here. [laughs] [laughs]
- 11:41
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 cutoff of the model.
- 11:55
Um, so one other thing I'll show you folks is how we use AI Studio to build AI Studio. Uh, so Ammaar and I have a lot of ideas, only so many engineers to work on these ideas, so we love to use AI Studio to ideate and explore different concepts.
- 12:10
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 Antigravity, and we know that sometimes these web-based vibe coding tools, you, they have their limits, and you may want to go into an IDE to add certain features to the application
- 12:28
or make it specific to mobile, things like that, that might be a bit limited in AI Studio right now. So we want it to be super easy to migrate into Antigravity.
- 12:37
So what I did here was just a one-shot 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 Antigravity app."
- 12:48
So we can see it did a pretty great job of cloning light mode, the screenshot was in light mode too, of our AI Studio application, and copying it, and improving a little bit on Ammaar's designs. [laughs] [laughs]
- 12:59
But then we see this new Antigravity button that is creating my, an export, and then exporting it to Antigravity, 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, 'cause if we had went and jammed on this feature, we
- 13:18
probably would've 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.
- 13:26
Sometimes it gives a command line interface for exp- or showing the status of the export, et cetera. Uh, so I think it's a super cool way for you to ideate on new ideas for U- UI, and kind of expand on your product.
- 13:40
Uh, but I'll hand it back to Ammaar.
- 13:43
Let's do it. Uh, and then the other thing that Gemini 3 has been really impressed, like, i- impressed us with is just making video games. And so this one was, again, pretty simple prompts.
- 13:52
Make this racing game where I have a bot now, add a start screen, um, and so you can see, I got this 3D racing game in Three.js. Uh, it drew all the things.
- 14:01
I'm racing with a bot 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. [laughs]
- 14:09
But, but the thing I wanna tease, actually, is that, um, s- all of these apps so far have been front-end React apps. Uh, and so the thing that's coming very, very soon to AI Studio is going to be back-end support, um, and full stack runtime.
- 14:22
So if you wanna install ShadCN, if you want to do all of those things, you'll be able to do that w- again, with one prompt. And the principle with AI Studio here is that we don't want you to think about those details.
- 14:32
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.
- 14:40
So we're gonna try something a little risky here. [laughs] Which is we did turn this racing game into a multiplayer one. Um, and, uh, this was, again, a couple of prompts.
- 14:50
Uh, so we're gonna put a QR code up if you wanna join us, uh, in the racing game.
- 14:54
We've never tried with nearly this many people-
- 14:56
We've never tried with more, yeah
- 14:56
... so we'll see. [laughs] [laughs]
- 14:58
Hopefully this works.
- 14:59
Yeah.
- 14:59
Uh, but QR code's up here. Uh, so if you scan that, we should load the game. I'm really afraid of how this is gonna explode.
- 15:07
Yeah. [laughs] Oh, here we go. [laughs]
- 15:08
Got all these cars loading in.
- 15:10
Nice.
- 15:10
Um, so yeah, if people have scanned that, we can switch back to the game.
- 15:14
Yeah.
- 15:14
Okay. Oh, my God. [laughs] [laughs] So yeah, just hit ready, uh, when you're all ready. [laughs] [laughs]
- 15:22
Oh, boy. [laughs] Uh, [laughs] I think this lobby's gonna explode.
- 15:27
Yeah, [laughs]
- 15:29
Yeah. [laughs] Uh-
- 15:30
I'm gonna leave. [laughs]
- 15:31
So this is where I shouldn't have added collisions with other cars- [laughs] ... because you can clearly see that we're bouncing around. [laughs]
- 15:37
Yeah. [laughs]
- 15:38
19 players, 20 players. [laughs] I don't know if this race will ever start, but, uh- [laughs] ... we're all blocked on the, uh, you know, the, the start line. [laughs] But 23 players, pretty cool.
- 15:47
Uh, yeah, you do all have to hit ready for us to start this race, so. [laughs] [laughs]
- 15:53
So we might be here all day.
- 15:54
Yeah. [laughs]
- 15:56
Uh, but, [laughs] uh, but yeah, that is pretty, pretty incredible. Um-
- 15:59
Yeah
- 15:59
... I can't start this race.
- 16:00
Yeah.
- 16:00
So do you wanna wrap up? [laughs]
- 16:02
Yeah, yeah.
- 16:02
Cool to see you all in here, though. [laughs] Oh, that's pretty cool. The runtime didn't explode.
- 16:06
Ah.
- 16:06
Um, yeah.
- 16:07
Yeah, and I think we're super excited not only about the multiplayer game, so next time we'll have even more of you folks join, uh, [laughs] but also, you know, the extensibility that comes with a full stack runtime.
- 16:17
Uh, we wanna make it super easy for you to integrate with our 1P and popular third-party APIs, et cetera. So very exciting next few months on the AI Studio vibe coding side, and super excited for you all to try it.
- 16:29
Um, but I think the one thing I wanna step back and emphasize is, was 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.
- 16:43
So I think what's beautiful about things like vibe coding is watching people. We were actually talking to a tech support person earlier this morning who said they started vibe coding in AI Studio after seeing a YouTube video, and we're really democratizing who can create things, and we're all getting to build those tools that enable that.
- 16:58
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 as much of the user intent as possible?
- 17:10
And that's what we wanna do with full stack runtime in 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.
- 17:19
If you wanna 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 joining us.
- 17:29
If you have any cool examples you've built or questions, feel free to ping me and Ammaar on Twitter. Uh, and yeah, enjoy the rest of the day.
- 17:36
Yeah. Thank you. [audience applauds] [upbeat music]