October 15, 2025 • 49 mins
Check out my newsletter at https://TKOPOD.com and join my new community at https://TKOwners.com
━
I sat down with Logan Kilpatrick from Google DeepMind and we vibe coded real apps live with AI Studio. We went from idea to working prototypes in minutes, including a video analysis app that extracts takeaways from uploads and a voice lead-gen agent that greets visitors and fills a form for me behind the scenes. We talked about why vibe coding lowers the barrier to building, how to package simple tools for specific users, and where the biggest opportunities are with Gemini, VO3, voice agents, and computer-use agents. This isn’t sponsored, and Google didn’t pay me, but I am a Google shareholder. If you’re looking for practical ways to start building with Google’s AI today, this one’s for you.
Logan’s links:
🌐 Website: https://logank.ai
🐦 X (Twitter): https://x.com/OfficialLoganK
💼 LinkedIn: https://www.linkedin.com/in/logankilpatrick
💻 GitHub: https://github.com/logankilpatrick
Google Resources Mentioned:
AI Studio: https://aistudio.google.com
Google AI: https://ai.google
Google DeepMind: https://deepmind.google
Enjoy!
---
Watch this on YouTube instead here: tkopod.co/p-yt
Ask me a question on or off the show here: http://tkopod.co/p-ask
Learn more about me: http://tkopod.co/p-cjk
Learn about my company: http://tkopod.co/p-cof
Follow me on Twitter here: http://tkopod.co/p-x
Free weekly business ideas newsletter: http://tkopod.co/p-nl
Share this podcast: http://tkopod.co/p-all
Scrape small business data: http://tkopod.co/p-os
Mark as Played
Transcript
Episode Transcript
Available transcripts are automatically generated. Complete accuracy is not guaranteed.
(00:00):
I want the product experience when you land on my website to
be an AI voice agent. All right, it looks like it's
done 66 seconds. Let's try it.
Hey, how's it going? It's going well.
Thanks for asking. Could I get your full name,
e-mail address and company name?OK, my mind is buzzing with the
possibilities. How big is the opportunity to
have like an agency that helps implement these tools into small
(00:21):
businesses? I was at a an event in Santa
Barbara last week. The top executives in the world
from Fortune 200 companies and even these top executives.
Don't know how to use AI tools? You're 10 prompts away from the
home run. Could you imagine how arrogant
that advice would sound? Three years ago just launched 50
different things. Now it's like, no, that's 50
prompts. You can do that.
(00:41):
You're literally going from likeI have that idea to deploying
the thing into literally 90 seconds and like the cost and
barrier to entry is literally free.
All right guys, I just recorded a banger of an episode and I
feel the need to issue a public apology.
What apology? Well in the past I've talked a
little bit of crap about Gemini and or Google's AI products.
(01:04):
I'm a changed man. Today I chat with Logan
Kilpatrick. He is from Google's Deep mind
team. He knows a ton about all of
Google's AI products and about what ideas you should vibe code,
what AI tools you should use to vibe code, what types of ideas.
He shared a screen and we vibe coded 2 different apps with one
prompt each. This is not a sponsored episode,
Google paid me $0.00 to publish this.
(01:25):
But I am a shareholder of Googleand a personal fan of their
company, and I think there's a lot that we can learn and a lot
that we can build on top of Google's AI products.
So today we covered VO3, Nano, Banana, Gemini, AI Search and
more. So if you are here for ideas and
tactics and tools, this is the episode for you.
Please share with a friend and enjoy.
(01:46):
My name is Logan Kilpatrick. I lead the developer product
team for AI Studio and the Gemini API at Google DeepMind.
And we're really focused on how do we take the latest AI
capabilities coming from Google and coming out of DeepMind and
put those in the hands of peoplewho want to build stuff.
And the whole sort of spectrum of builders these days from
everyone from, you know, developers and enterprises who
(02:07):
are like building massive companies and products to like,
hey, I just have this idea and Iwant to build my first AI app or
build my first app at all and, you know, share with a friend or
someone in my family. So we're building for all of
those people, which is challenging, but also a lot of.
Of fun. That's exciting.
What of like all the products within Google's AI Studio?
What are like the main ones? Why don't you just list them
(02:29):
off? The fun part about Google is we
have a massive spectrum of products.
You get everything from if folkshave heard of of the Gemini
apps. So the Gemini app is like
Google's personal assistant powered by Gemini to you know
all of the Gemini integrations that you might find in like
other Google product services. So that's everything like Google
Docs and Sheets and Drive, etcetera, all have Gemini
(02:52):
integrations to search with AIO reviews and AI mode folks
haven't tried is like an awesomeexperience inside of search to,
as you mentioned, like actually custom built a like almost like
AI native products. And that's notebook LM, which is
sort of like a research assistant that takes all this
like content that you have and makes it infinitely repurposable
(03:14):
to AI Studio, which is a sort ofAI builder platform.
If you want to create software and you want to build something
powered by AI and put it in the hands of users, the platform for
you to Google Labs, which has all these like early stage bats
and things like Opal and and others.
So there's, there's a huge spectrum.
The simple answer to your question, Chris, is you can go
to Google dot AI and it has sortof like the suite of all of
(03:36):
these different products that are available and you can sort
of look through and find what maybe is most exciting to you.
OK, so you've got a really unique insight into all of
Google's AI products. If you were forced, heaven
forbid, to have to pick one of them to build a business with,
or to start a business with onlyone of them, what would you
choose and why? Yeah, it's a good question.
I'm biased because I spend my time thinking about AI Studio.
(03:58):
So probably AI Studio if you want to build a product and
build a business. I think the my pitch to you
would be build AI products. And the reason for this is like
AI is both extremely monetizable.
There's edges everywhere you look like there's all of these
emerging interesting product experiences that you could
potentially build. And actually the barrier to
entry is pretty, pretty minimal.The beauty is you don't need to
(04:21):
be an AI expert to go and like build AI products.
You just need to have some problem that you're trying to
solve. And like, there's a probably a
good chance if it's at least a digital problem that AI can help
solve that for you. It is this like unique
combination of all these things plus like consumer interest is
increasing, consumer willingnessto pay for AI products is
increasing, costs are going down, the technology is
(04:42):
improving. So there's like all of these
very unique tailwinds that are happening at the same time,
which I think makes this like such a exciting moment to build
AI products in AI. Studio, You've probably seen a
lot of people building cool stuff with Google products.
What are like some interesting stories or case studies of
people that have used your products to build something
awesome or something simple or something profitable or any and
(05:05):
all of the above? I'll give sort of 2 ends of the
spectrum from it from an answer perspective.
So on one hand, like in AI Studio today, teams across
Google are like prototyping the next versions of a flow, which
is our video editing creation product for creatives, like
experiences around Google searchand YouTube and other things
(05:26):
like that. So it is really like becoming
sort of the engine room for Google to prototype and like
build next Gen. AI experiences.
So I I see like one end of like,you know, these experiences
might end up impacting billions of users too.
With the nano Banana launch a few weeks ago, on day one of the
nano Banana launch, users insideof AI Studio were vibe coding
(05:46):
literally 10s of thousands of AIpowered apps using that new
model and like much thinner experiences, things that are
like kind of goofy, but also like interesting, like haircut
AI and like all these like photorestoration products.
These like very, very vertical use cases.
But like you're literally going from like, I have that idea.
I could see why people would want that to deploying the thing
(06:08):
into production and like puttingin front of users and literally
90 seconds and like the cost andbarrier to entry is is literally
free. It's paid when you deploy and
you have to like, you know, service external users and
stuff. But to actually build the thing
doesn't cost anything, which is just such a unique moment that I
don't think like if you look at the arc of what's happened in AI
historically, there's this lag of like new capabilities
(06:32):
relative to products on the market actually being available.
And I think what Vibe Coding is enabling is this like
compression of like new capability to there's 1000 new
products built on top of that capability on day one literally
being deployed, which is a really unique combination.
Now, if someone's hearing that, you know, 10s of thousands of
products being tested or deployed on day one or week 1,
(06:54):
give me reasons why. And I'm I'm in your camp here.
Give me reasons why people should not feel discouraged by
that. Like, oh, it's I'm already too
late. Oh, there's haircut.
AII had that idea. Like what are you seeing out
there? Yeah, that's such a great
question. I think a couple of things, like
1, the thing that gets me excited about this experience
that we're building in AI studiois how easy it is to go and
(07:17):
remix. So again, maybe somebody has
like generally the same idea, but like you're like like, oh,
actually, you know, I am a hair stylist and like I have some
unique insight or like I get my haircut and I hate these four
things about that experience. And like, therefore I'm going to
put a unique twist and a unique spin and like that's literally
like one that's a prompt away. So you're a prompt away from
(07:39):
like, yeah, maybe like roughly there's other people doing the
same thing, but like you have some unique differentiated
perspective. So I think even if you take like
all of those like very basic verticals, there's like this
massive like tree explosion at the bottom end of like how to
make it different and how to keep adding features and like
discoverability and how you position and how you make the
(08:00):
experience fun. So I really think it's like
every at every one of those different thousand 10,000
things, there's, you know, maybe1000 other additional options
that like could be interesting and fun and exciting.
Products. Yeah.
And I think it's important that people start with what they
know. Let's say you're a hairdresser,
right? And you just hear anecdotally,
(08:21):
you know, what's that going to look like?
What's it going to do? You want your hair like this.
What is it going to look like? You have a unique insight into
the market that makes you want to do haircut AI, right?
But if you're just listening to this and you have no background
in in working in a salon, you'reprobably not the person to do
this. But if you do a quick audit of
your own life and experience, you could have ideas that are 10
(08:41):
times more valuable than that, right?
Like when we solve our own problems with these vibe coding
tools, it has the greatest likelihood of succeeding because
we know it more intimately than anyone else.
Yeah, it is also fun. I I think while at the same time
that that's true, Chris, it is also fun to just like take
random shots at things that I know nothing about.
I'm like. I do it all the time.
(09:01):
Yeah, it's. All the time that it's like both
things are true at the same timethat like while the value of
your expertise and your edge is like very real, it's like also
so much more approachable to like go into domains in which
you're not an expert. And like, maybe you actually
just get lucky and stumble upon the thing that's like really
interesting or you have some like random unique site that
(09:22):
actually is super valuable. So it is just another another
plus in my book for this vibe coding moment being like such an
interesting experience. Have you ever read the book
Range? Yes, Yeah, yeah, yeah.
That's what I'm thinking of as we talk about this, because they
did a study and a lot of times the experts have like the worst
insight because they're so biased and they look at
something a very specific and narrow way.
(09:43):
Whereas in quote, UN quote, ignorant outsider comes in and
they, you know, it's like the Midwest meme.
They look at it like a caveman and they have this big unlock
because they're not biased by their previous history.
So I do think there's, there's arange there right between like
what you know what you recognizeyou being able to see
opportunities more clearly than others and like you being way
(10:04):
too biased, right? You being like the old fogey in
the room. That's like all that would never
work because I've been in that business for 10 years.
Like I've had people tell me that and I've launched anyway
and it's gone great, right? So I think it's a matter of like
finding where your place is on that spectrum and just taking
wild home run shots on goal justbecause you either win or you
learn, you know? I think you're 100% right and
(10:26):
it's also because of how accessible this is now.
Literally you could be doing andtaking a shot at building
something every single day, which is awesome.
And like, that's how I feel. Like I, I wish I had more time
in the day, but like there's 1000 things I want to build.
And like you actually could be building 1 AI app every day with
like probably 30 minutes of workor something like that.
(10:46):
And like again, maybe the 1st 50things you build aren't
interesting and no one cares. But like the 51st might be.
And like again, you spend $0.00 in that whole process to get to
the point where like you actually built something that
you're really excited about. So such a special moment again
from that perspective. Well, and could you imagine how
arrogant that advice would soundthree years ago?
Like just launched 50 different things.
It's like what? Like I don't have unlimited time
(11:09):
and money, and now it's like, no, that's 50 prompts.
Like you can do that. Yeah, there's something
interesting about if folks follow like levels IO and some
of these like people online who talk about like, you know, they
had like 20 ideas and only threeof them worked.
And the three that worked are now like, you know, $100,000 a
month businesses or whatever. Like that experience probably
(11:30):
doesn't perfectly generalize across everyone who tries to do
this. But like that is now like more
in reach than it's ever been. You can literally take a hundred
shots at it. And like, yeah, you should be
thoughtful and deliberate about what shots you want to take.
But like the barrier is like basically non existent, which is
really exciting. Like it really is just like, do
you have agency? You know, are you interested?
(11:50):
Are you spending your time doingthis?
Or is like there's something that's more high value in the
world that you're spending your time on instead?
Yeah, that's beautifully said. And I ask you this next question
more as like someone who I know is a student of the game and
like in the startup community ecosystem, seeing what's
happening, how are you seeing people find success at actually
marketing these apps that they vibe coded and not just building
(12:12):
them? Yeah.
One of the interesting things isthis goes back to like what is
the edge that you have? Like I'm somewhat biased because
I spend a lot of time on like seeing what people are building
on social, which I think is like1 version of this, of this like
flywheel of like how people are coming to market these days is
like you could basically for free social first engage and go
(12:32):
and do that. I think there's another angle of
this, which I've seen more and more startups and this is like
more in like the indie hacker bootstrapped space.
But people are building these like packages of not just a
single tool, but it's like, Hey,you're a student or hey, you are
XY and Z persona. Here's the package of like 10 AI
tools that you need. So it's not like I, I'm trying
(12:54):
to make the tool to rule all tools.
It's like actually, no, you have10 different needs as a student
or as a, as a lawyer or as a whatever your, your persona is.
And like I'm going to package all these things up.
I think some of the challenges like like how you go to market
with that package looks very different than how you would go
to market with one of those individual tools.
Like the search volume, for example, for like, you know,
(13:15):
haircut AI might be extremely thin, but you sort of package
together the like 7 different tools and some specific domain.
And then all of a sudden like you've actually reached a
critical mass where there might be a business that you can
build. So I think that's one of the
things that I've been most interested in.
And I, I don't know if like I haven't seen a lot of people
doing this and could be an interesting edge to like try to,
(13:38):
to try to come up with what thatpackage would look like for like
a getting to a wider audience. Well, I just interviewed a guy,
John Rush. Do you follow him at all?
I don't know. I'm not sure.
It was episode 228 and he he makes 3,000,000 bucks a year
from a dozen AI tools, maybe like 20 AI tools and it's
definitely 8020, right? Like most of them don't make
(13:58):
much money, but he has like an an AISEO tool and a marketing
tool and all these other tools and it's all like he's selling
them to start up guys to indie hackers, etcetera.
But he's able to cross sell and cross promote between all of his
e-mail lists and he's able to triple down on his same like
meta ad accounts and he's able to, you know, share all these
resources, his AWS account and all these things.
(14:21):
He just has a lot of surface area for learning what people
want and what they're asking foror not asking for.
And he's able to take all these shots on goal.
And you know, if I might have signed up for this, you know,
AISEO tool for 100 bucks a month, It never actually paid
for it or I turned out, but thenI end up spending $200 a month
for this other tool that he offered me.
(14:42):
I think that's a really smart idea.
Like there's no point in building something and not
hitting publish on it, right? Or telling people how or why
you're building it. Like it's very little
incremental friction to publish what what you're doing compared
to actually doing the thing. Right?
Yeah. I think there's also something
which is an interesting point that you're making, Chris, which
is I also think there's just like a level of complexity in
(15:05):
what you have to build. And if you think about like if
you're just getting started doing this stuff, like again,
building the like full end to end AI marketer that does SEO
and outbound and ads and five ofit's just like really daunting.
And I think for a lot of people like your experience is like
probably not broad enough that you would have enough domain
expertise to like really have a point of view on like what's the
(15:27):
right product experience for allthose things.
But like you can maybe build thelike sliver again, like thin
version of like three of those products pretty easily.
It makes me ponder what the future is going to look like as
as people sort of, you know, there maybe will be these like
all the like big companies or maybe not all of them, but like
all these companies are trying to build the everything app.
I mean, at the same time that everyone's trying to build the
everything app, like it's now becoming easier and easier to
(15:49):
also build the like just one thing app.
And I think users actually appreciate that sometimes.
Like, I don't want all this complexity.
I just want to take a picture ofmyself into an app and like see
what I look like with different haircuts.
I don't need a bunch of other stuff.
Like, I mean, Elon Musk isn't even really finding success at
building and everything out, butyou're you're out there trying
to build the next HubSpot, you know, Like what what do you just
(16:11):
build a tool that puts furniturein people's empty rooms and go
from there? There's like very specific
niches of this, like I love the furniture one, but like I was
helping my girlfriend with this.She wanted curtains.
That was the only thing that shecared about.
She was like, I don't need to redesign my whole room with AII
just want to see seven differenttypes of curtains and like going
deep on that experience. Like again, it's maybe it's
(16:31):
maybe the funnel to your, you know, furniture AI business.
But like really the thing that people are trying to solve is
like some very specific problem and you can win on the niche and
like. Then get people back into the
larger funnel. I love that.
Like I just wish people had moreof a bias towards like that's
not niche enough as opposed to that's too niche AI curtains,
(16:51):
you know? Like that's not too niche.
It's not too niche, but I do think, and it's interesting, I
think this like bias comes from like the historical cognitive
dissonance of like the cost to build software being high.
So like all the conventionalism,the way that humanity has been
programmed is like you have to take a big enough swing for it
to be worth it to build softwarebecause the cost of building
(17:12):
software is high. And I think it is like not
trivial. I think for a lot of people to
go through the like flipping theswitch that like actually the
cost of building software is nowtrivial.
And like the strategy in which you should employ in that world
looks very different than the conventional wisdom.
I genuinely think the way that the flip happens is you like
experience at first hand. Like you go build 15 different
furniture apps powered by AI in a single day and you're like,
(17:35):
wait, holy crap. The limitations are all
different than what I thought they were.
Yeah, you spoke on a different interview about I forget which
product it was that watched likea 30 minute museum video and
pulled out a list of exhibits. What what are you seeing with AI
tools that can quote UN quote watch video even if it's just
frame by frame? And what applications do you
(17:56):
think are exciting around that technology?
Yeah, that's a great question. Do you want to build stuff or I
can I can answer this question, but we should also I'm happy to
all sort of give vibe coded answers to all of these
questions. And then and then we'll try and
I'll also talk while it while itwrites the app, so.
This is a fairly selfish question because this is
something that I've been trying to do personally.
(18:18):
Like I want a tool that can likewatch short form videos for me
and like extract interesting points from it where I can ask
it questions that can go out agentically and find interesting
short form videos that I might be able to post content about,
right? Yeah, I love that.
So I'll kick off building something and then I'll give you
my answer. So we want to build.
(18:38):
Let's do, and then maybe I'll try.
I'll see if it's speech to text on a podcast doesn't work.
Let's see. Build me an app that takes in a
video and then parses out perhaps the most interesting
stuff from the video, picks up on the trends, gives me sort of
maybe an entire analysis of whathappened, what the gist of the
(18:59):
video is, what the take away should be. 10 insights, but make
it so that I can actually use AIto customize that report that's
being generated, in addition to using AI to analyze the video as
it's processed. What a prompt.
It's like watching Picasso in his prime.
Yeah, my my word vomit of watching that, doing that prompt
(19:21):
live without being more thoughtful about it, but.
No, that's great. Yeah.
So what to answer the question, like that example that I was
referring to about a tool that can like take videos and and you
know, in the example I was giving, it was a museum and you
can sort of extract all of the exhibits in the museum.
The beauty is it's just Gemini, like literally that is just like
(19:41):
the Gemini model out-of-the-box.So you can actually do this in
AI Studios. If you just go to AI dot studio,
you upload a video, you ask, theprompt is like extract all of
the different scenes from this video.
It will literally go and do thatfor you.
So it's like very simple, that works out-of-the-box.
The question then is like, what is the product experience that
you sort of build around that model?
(20:04):
And I think that's where the magic is.
I've just seen. Like Gemini has state-of-the-art
image and video understanding. It's it's one of the only models
that has native video understanding as well.
And it's more than just like theframe.
Like it's not just if you were to like pull sample a specific
frame, it's more than that. It's like the interleaved frame
and audio coming together and like the context that it's
(20:26):
shared on a like a frame and audio by audio basis.
So it's a little bit more complicated.
Than that. Oh man, all right, I've got a
video. Analysis Engine.
Now I need to see, do I actuallyhave a video on my desktop that
I can use for this? All right, 270 megabytes.
Let's see if it says I can do supposedly up to 1 GB.
(20:47):
So let me drag this in and analyze video.
Let's see and so just to give context on this, you know, the
prompt was build an application that takes a video, parses it
application should identify the most interesting etcetera,
etcetera. You can see it in the top left
hand corner. Gemini 2.5 Pro went and you
know, did a plan, wrote all the code for this and actually made
(21:08):
me an AI video analysis engine. I just copy and dragged this and
was able to get an analysis, wasable to get 10 key takeaways.
And then the cool thing is we can actually again, and this is
powered by AI in real time, we could to change what we want
from this analysis. So Chris, I don't know if you if
you have suggestions of like howwe would potentially change this
(21:30):
analysis, but we can change it if you want.
Yeah, what about videos that have no text or no audio?
It's just just just like pure video.
Yeah, Yeah, we can also do that.So I think it's it has, this
goes to like Gemini has like native image understanding and
video understanding. So it can, if there's no audio,
like it's perfectly fine. We could find a video that has
(21:51):
no audio and it'll actually likelook.
OK, my mind is just like buzzingwith the possibilities.
I don't know why I've never had much success with like an AI
watching videos but I just haven't but this.
Is I think it works really, really well.
So this is, we have like tons ofcustomers who are super
successfully doing like AI watching videos.
And there's this interesting loop now where it's like AI
(22:13):
watching video that is then AI generating video with VO3, which
is then like using nano banana to do something.
Like I've seen a lot more of this activity where you can sort
of take this full suite of models, stitch them all up
together. And we have some examples of
this where it's like, can you, yeah, can you stitch all these
things up together? And these are just a bunch of
the like random examples in our in our gallery right now.
(22:35):
But yeah, lots of cool stuff. And like, I genuinely think
you're probably 3 prompts away from something that works really
well. And again, it's like critically
the Gemini model that's enablingthat analysis.
What are some other use cases for watching videos that you've
seen people use? That's a good question.
I think one of the one of the most interesting ones is like
there's all of this intelligenceand videos and it's just like,
(22:56):
how do you extract intelligence from videos?
Like I talked to a lot of companies that just like have
lots of video data internally inside of the company and
they're like, yeah, wouldn't it be nice?
And I think like content creators actually is like
another great example where likeI, you know, very inactively do
my own podcast and like for that, I'm like, you know, if I
wanted some montage, I did this in the past where like I
(23:17):
basically uploaded all of the data and I built this pipeline
that would just like go through the video and I would ask a
question and I would like searchacross all of my videos
completely vibe coded and like pull out interesting insights
that like, I didn't even know that I talked about that on one
of my podcasts. It was super cool.
What are? Mistakes that you're seeing
people make that when it comes to prompting and or vibe coding
(23:39):
that are easily fixed. Yeah, I think the big one is
like people. And I actually think like
building software is very much like this as well.
It requires persistence. In this example of that, we were
just looking at it kind of worked.
It kind of didn't like maybe it kind of like missed the point of
like the second part of what I wanted.
But like the beauty is the cost to continue to iterate is
(24:00):
literally just like putting something in the prompt box.
And we even added a bunch of, you know, suggested downloading
the report as text or clearing error messages or refining
report sections. A bunch of pre made prompts that
will like show up here based on the context of what you're
building. So I think people often times if
that first one doesn't just likehit the home run.
They're like, this thing doesn'twork, but I think it's like
(24:23):
really, you know, you're 10 prompts away from the home run
and the important part is that you do the 10 prompts to get
there. I think that's the biggest
mistake right now. With everything changing so
fast, what skills or habits do you think will stay valuable
throughout all these changes that we're seeing with AI?
Yeah, it's funny. And like back to the a similar
thread of the last question you asked, I think everyone talks
(24:44):
about like building soft, you know, being a software engineer
is this like diminishing thing that you should be doing.
And it's, it's funny because I think about the skills that I
learned as somebody who's like traditionally trained in
building software as a, you know, a computer science
undergrad and someone who's formerly a software engineer, I
think about almost none of that,of what I learned having to be
(25:07):
like typing, typing letters intoa key into a keyboard that then
translates into code. And like, I think almost all of
it is like how to think about solving problems, how to be
resilient. And I don't know about you all
or other folks who have built software, but like my
experience, experience of building software is error
messages. And I think that's like spending
(25:29):
years of your life just seeing error messages.
I think like things basically not working, I think trains you
in a very different way of like how to be resilient.
And I think the reality is like how to be resilient and how to
have agency and like go and takeinitiative.
I think are like the two determining factors and all of
this and just life in general. The challenge is like, how do
you put yourself into an environment where you can do
(25:51):
both of those things? The nice thing is like for AI is
sort of enabling you to be have more agency.
Like you now have all these tools at your disposable.
The floor is sort of is leveled up so that you don't have to
worry about like the drudgery ofa lot of the tasks that you were
doing before. I think it's a beautiful moment
from that. Perspective.
Yeah. I mean, more agency can make or
(26:12):
break people depending on the person, right?
It could drive us to be our bestselves or more of our worst
selves. But I think the people listening
to and or watching this are are in the the former category.
What are some overhyped like AI use cases that you're seeing
right now that you're you're notbullish on travel?
I hate the idea that I'm going to be booking my flights with
(26:32):
and this is somebody who travelstoo much.
We were talking before this off camera.
I travel too much. I wish I wasn't traveling, but I
just think it's like the most quintessential like demo use
case that is like not actually valuable that much.
I think it's also because not the form factor that I've seen.
Like I do think there's something interesting and AI,
you know, enabled travel planning, but I think the
(26:54):
product experience that most people are building is like AI
to book your flight ticket. I'm like, I don't know about
you, but the United website is like pretty simple to use.
Like I don't actually have AI tobook my flight.
I need AI to like orchestrate the like actual complexity of
travelling. And like the most of the
products are not doing that. So it's just like the easy thing
(27:15):
they're actually helping me solve.
And I'm like, I don't need the easy thing to be solved.
I need the hard thing to be solved.
Yeah, people are trying to to solve a problem that's not a
problem. And the the cost of AI getting
it wrong is quite high. If I have AI book me a flight to
Vegas with a layover anywhere, you know, it's really messed up.
There's like 50 non-stop flightsfrom DFW to Vegas every day.
(27:35):
But that would happen like something in the logic would
happen to save me $3. It would, it would have me lay
over in Miami or something and that's to save me 3 minutes.
What are some travel AI use cases that you think could be
useful, if any? There's something interesting
about like, how do you bring together all of these like
disparate sources across the Internet?
Like, you know, I think there's some amount of useful signal
(27:58):
that you get from like main travel websites as an example,
but there's also like you kind of want to discount the opinions
that you get, like depending on what experience you're looking
for. If you want like a nuanced
travel experience, choose your favorite like rating websites
that that rates like places on travel.
Like oftentimes you might actually get like, you know,
it's 4 1/2 stars, but it's like very biased because it's like a
(28:21):
bunch of, you know, US travelersor it's like some, you know,
specific persona that is like maybe not the persona that
you're looking for, even though you might be a US traveler
yourself, which is the irony. So I think there's something
that like, how do you sort of connect all of this stuff
together and have like real sortof like travel intelligence of
like where you're going and likethe places that you should be
(28:41):
going to that like maybe are haven't bubbled up to the top
level of like, you know, the thehottest place to be.
And also like discounting a lot of those places like if you want
to avoid those things. And also just like the
logistics. I think about this like
traveling places that have like public transportation systems
that are like new. I was in London a few weeks ago
(29:03):
and hadn't used the like London train system to get from the
airport before. And I was like halfway through
this process of like walking around the airport.
I was like, I sure hope I'm going the right way.
The information about how these systems work is like out there
on the Internet. You just need to like build an
experience that make if I'd gotten like a e-mail from my
travel agent saying like, hey, by the way, you're in London,
(29:24):
here are your three options for how to travel.
And like, here's literally the map of how to do that.
Like that wouldn't even be that hard.
I could have probably if I codedit beforehand, but I just didn't
send it set it up. What if it was like a travel
companion that texted you like it was it tracked you right,
like Uber might and texted you as you got to different spots
along your journey, like, hey, Isee, I see you landed.
(29:44):
You're going to Terminal 4 because that's where the new,
you know, subway is, right? Oh, cool, you found the subway
awesome. I know you love Lebanese food.
There's a five star rated place right at this stop, right?
Like just kind of like text along the way and you can tell
it to stop at any point, but it's it's tracking you.
Text as the form factor is, is something that I'm like overly.
(30:06):
I'm overly excited and bullish. On 100 percent 100% I don't want
more notifications but I can handle it if it's all within my
messages out. And like you're travelling with
your friends and like all of a sudden now it's multiplayer in
the conversation. Like I want to put my sort of
travel companion into the group chat.
And like I'm I'm travelling withmy family in a few in a few
weeks. So like, I would love to be able
to like just not have to be the arbiter of information about
(30:30):
like what's our plan and our like all this like conversation
toil that you have to have like put my companion in there, drop
the little thing. And then whoever forgets to
check the Google Sheet that has all the list of the itinerary,
just text in the group chat and like the companion is going to
answer like technologically likeit's actually not that hard to
build that, which is awesome. Yeah, it's a Twilio integration.
(30:51):
What other cool things like are you?
Like, did we not get to that? You're just excited like a proud
parent to show me. Yeah, that's a good question.
So there's two that are top of mind and I'll show one of them
and the other one we're working on like a great showcase for I
think like voice AI agents and like computer use agents, I
think are two things that are really exciting.
(31:14):
Computer use agents. We just launched the time of
this recording like literally yesterday, a state-of-the-art
model that's able to sort of like navigate browsers and do
all this stuff for you. And it's like a really helpful
if you if you're somebody who's like thinking about building
agents, it's really helpful. It's like a supplemental
mechanism to let go and gather information or to do like
automate repetitive like UI tasks that you're potentially
(31:36):
doing. So really excited about that.
The other one, which is like adjacent to this is like voice
agents. I think there's a huge amount of
alpha in this. Like if folks have like tracked
the voice AI market, the like amount of companies, the model
quality, the like investment, the use cases are all like up
and to the right. There's like a huge amount of
potential impact and like it's actually not that hard to build.
(31:57):
And the fun thing is like you can literally go and vibe code
voice AI experiences inside of AI studio, which is really cool.
So I'm going to tell you this demo and then we'll I'm trying
to think of like what do? What do we want to build that's
like? Voice AI powered.
I will say I had this lead magnet that was just a form for
this initiative I have and I just swapped it out with a voice
(32:19):
AI agent. And I'm upfront that it's a
voice AI agent. And I see everyday like the
transcripts of whoever having a conversation with my agent and
I've talked to them like afterwards and they love it.
Like they know it's AI. It's a great experience.
I think we have this perception that a voice AI agent is taking
over and people aren't going to like it.
(32:39):
And it's more frustrating than being on hold with AT&T.
But it's a better experience. And if you know it's AI and you
don't feel tricked, it's just superior.
Extremely bullish on that. Yeah, yeah.
Well, that's actually a great thing.
Let me try vibe coding this. So I'll, I'll describe what I
understand and what this is doing and we'll see if the model
can, we'll see if AI Studio can actually build me an app that
(32:59):
does this out-of-the-box. OK.
All right. I want a landing page for my
website where we sell, we actually sell AI services and I
want the product experience whenyou land on my website to be an
AI voice agent powered by the live API.
And basically basically the whole experience is going to be
(33:20):
a it's, you know, it's a veneer on top of a lead Gen. form
behind. So the user will talk to the
live API and behind the scenes, the model will actually just be
filling out a form. And then once the model has the
information that it needs, whichlet's say that it's like the
name and the e-mail address and the company that the the person
works at, the model will say thanks, it'll end the
(33:41):
conversation. And then it'll kick off a
workflow behind the scenes to e-mail that person and like
create a lead Gen. and and database.
So let's do all that. Let's powered by the live API
and let's make the website look futuristic.
I want a little bit of I want tofeel like I'm in the future for
this. And my nickname for this is Yap
Yap to app. So we'll see if I like the how
(34:05):
good it is. This is a fairly involved.
So like this might be an exampleto, you know, level set my own
expectations. This might be an example where
like it doesn't work the first time because we're actually, I
didn't think deeply about my prompt and I was truly just
yapping. But we'll see whether or not we
get anything interesting from this.
But yeah, I'm I'm not surprised there's that like not you as you
were describing, Chris, that like experience that a lot of
(34:27):
the users have. I also think there's this like
novelty effect where like you might be able to like it's
people are surprised and interested in this because they
don't see that experience everywhere.
And like I do, maybe there's a, there's a time window of like
when that's true. But like it feels like it's
right now we're like people are open and willing to try because
they know how AI is changing. Stuff well, and the bar is
(34:50):
pretty low. Like if I need to call customer
support for anything, my day is ruined.
I'm I'm yelling at my kids, it'sI'm on hold.
I'm going to get hung up on likethat's what AI has to be.
We will never be on hold ever again, right?
It's either that or I'm calling a restaurant to make a
reservation and they don't answer, right?
Like, that's kind of what we're up against here.
(35:11):
Yeah, all right. It looks like it's done 66
seconds. I have low confidence it's going
to work, but let's try it. Hey, how's it going?
It's going well. Thanks for asking.
I'm here to help you with Stellar AI.
Could I get your full name, e-mail address, and company
name? Yes.
My name's Logan Kilpatrick. My e-mail is email@xyz.com and I
(35:33):
work for Google. Thank you Logan Fitzpatrick for
providing your full name, e-mailaddress, and company.
I have noted that you work for Google.
Is there anything else I can help you with today?
Nope, I'm all good. Can you contact Stellar AI and
let them know that I'm interested?
We're so close. Almost almost zero shot
experience accepted. That's amazing.
(35:55):
Yeah, well, I'm curious, but I think it you sort of close like
I'm like 2 prompts away from this thing, what I need.
Is it like a walled garden like if you said what's the capital
of of Kansas, would it answer you or would it be like I'm not
trained on that that's. A good question.
So I think my my hypothesis is like the guard actually.
So this is where looking at the code is actually helpful.
(36:16):
So if I go to code and then I goto see not voice agent dot TSX
here it is. Yeah, actually system
instructions. You are a helpful, friendly, and
personal AI agent. For Seller AI, your primary goal
is to collect the user's full name, e-mail, and company name.
Be conversational and be conversational and engaging.
(36:36):
Once you successfully collect all the pieces of information,
you must call the submit leads form function.
Do not ask for other personal information.
Give the user an introduction toyourself before starting.
So my guess is like this system instruction doesn't say anything
about like don't answer other questions.
My so my guess is it'll answer right now we can try and then we
could try adding in like only talk about stellar AI do not
(36:57):
talk about anything else and seehow much it works.
But my assumption is that works out-of-the-box as well the.
Pause. The latency is so much better
than even a year ago, right? It was.
It was awkwardly long, I didn't notice it at all there.
Yeah, you don't. It feels, it feels extremely
natural. It is actually always surprising
to me how quick it is. But yeah, it is.
It's it's very fast. So I'm going to keep playing
(37:19):
around this. I might, maybe I'll add a voice
AI agent to my personal website and see if people want to talk
to my voice AI agent. And I'll just have it make up
random stuff and confuse people just to throw them off my trail.
Oh man, that is really cool. What are some things that you're
excited about that it feels likestill very underexplored, like
(37:40):
unexploited by the everyday person?
Yeah, that's a good question. Let.
Me ask a follow up, which is related.
How big is the opportunity to have like an AI automation and
or implementation business or agency that helps implement
these tools into small businesses?
Because you and I toy around with them and it's easy.
(38:01):
You one shot prompted Cool. It doesn't matter how easy it
is, right? It doesn't matter how easy
Google ads or Facebook ads or building websites are like there
will always be business owners that just want someone to do it
for them. It's not about the the
complexity, it's about the brainspace and like the the
perception of difficulty. Do you see that as being a a big
(38:22):
opportunity? Well, so I'll, I'll give my
bias, which is like, I don't know what the actual numbers
look like, my intuition and likemy personal experience engaging
with people and I'll share. I was at a was an event in Santa
Barbara last week and it was like some of the top executives
in the world from like all the like Fortune 200 companies and
even these top executives who I think are like obviously
(38:45):
extremely smart, like in the know, they, they're, they have
teams that are telling them how important AI is.
If you like actually get into the nitty gritty, like a lot of
folks don't know how to use AI tools and like they would need
to go and delegate to like go and do a bunch of these things
and they're like extremely well paid, like at the frontier of
sort of knowledge. They can talk the talk, but
(39:06):
that's about it. Yeah, exactly.
And they're like, and it's like really interesting to see this
and then they actually like needa lot of hand holding and it
will make progress on this stuff.
So I think like you take small businesses that are like just
trying to get by and like go andmake, you know, move the needle
on, you know, their family business or some small business
with only a few people. Like I think there's just not
(39:28):
enough time in the day to be deeply embedded.
And like you show them these three experiences.
Like I was on a call with a clothing brand and they were
talking about how they, like, want to do all these ideas with
mood boarding and like using AI and virtual try on.
And I was literally on this calljust like vibe coding the things
that they're saying. I was like, yeah.
And like, we're just like, here,here's the app that actually
(39:49):
does that. And they're like, how is that
possible that you already have this thing ready?
And like you can give people like the timeline, the like fact
that it took 66 seconds to buildthis thing.
And again, it wasn't perfect, but like you get the point
across of like this is within reach, which I think is a lot of
the cognitive dissonance that folks have right now is like
they don't actually believe thatit's in reach.
(40:09):
And I think there's a world where like you can actually just
go and the experience sells itself so much because you can
go and take this vibe coded experience.
You can go find this company, the company website that you
want to work with. You can take their products or
their website Reimagine. Imagine it with AI and like
that's your lead Gen. and like the cost to you is like
basically 0, but you can do thatoutreach and instead of being
(40:30):
like, hey, I'm blah, blah, blah,and I do AI stuff, you can be
like, hey, I redesigned your website using AI.
Here it is. If this seems interesting to
you, let me know. If not, like your marginal cost
was basically nothing. So it's like on both ends of the
spectrum of building this type of like AI agency, you can do
really targeted, really rich, really deep outreach.
(40:50):
And at the same time, like you have a customer base that's like
potentially really excited and interested.
And again, all my caveat to this, I don't know how big the
actual market is, but like I would imagine it's large and
there's a lot of people who wantthis as a as a service, so.
Well, I mean, there's, there's 400 million small businesses
around the world. All of them need AI to some
extent. Maybe not all of them can afford
(41:11):
$1000 a month, but I'm insanely bullish about that.
What do you think VO 3 is going to look like in five years?
I think it'll look like a toy, but also like an important like
to me, VO3, and this is from, from conversations that I've
seen, like VO 3 was the GBT 4 moment for generative media.
I think there's like all of these companies that are engaged
in that space have now realized like, Oh no, this technology is
(41:34):
actually possible and going to be good enough.
And like it's basically here right now.
The exponential increase in likesort of maybe not exponential,
but the increase in like capabilities and how good the
models are becoming, I think hasmade like lots of folks across
the ecosystem aware. So I think they'll be like a
huge amount of investment over the next three years.
And it will be like a massive accelerant of like the media and
(41:56):
entertainment industry, which is, which is exciting and sort
of like the outcome that you would want as yeah, as a as a
fan of the space. Will we be in a in a Cinemark
theater in five years watching aa Tom Cruise movie that cost
500,000 to produce with VO3? Is that realistic?
It's a good. Question.
I don't know, my my sense is like actually, what's more
(42:16):
realistic to me is that there's this like infinite canvas of
media that I think is really interesting.
So I think I think my my expectation is like the Tom
Cruise movie will still have a high, you know, maybe something
like roughly the production costwill go down, but it'll still be
expensive. It'll still, you know, they'll
still really deeply like art andcraft put into making this an
(42:39):
experience that both like the people producing it and also the
audience is going to love. The thing that will be net new
is the the content lifespan withthis like infinite repurposing,
an adventure is going to dramatically change.
So the way you experience content is like they'll have a
base video and you'll be able tobe like, wait, this is fat.
I love this story. But what would happen if, you
(43:03):
know, Tom Cruise decided not to hang out on the side of an
airplane and to do something else instead?
And like you can go and see whatwhat's possible.
So I think there's the and I don't know, it'll be interesting
to see how like the platforms adopt this.
But like, I think this infinite content remixing and like
exploration is going to be very much much possible, which is
exciting. I completely agree and I'm not
(43:25):
of the mindset that like VO 3 isgoing to replace Hollywood,
right? The Kindle didn't replace books.
There's going to be a world for both.
But I just think it's going to look so different and what we
see on VO3 today is going to look laughable in a few years,
and it today it looks amazing. It's pretty good today.
What? What's like a Google product
(43:45):
that you wish everyone knew existed that is just completely
slept on and ignored and underrated?
It'll sound counterintuitive, but AI mode and Google search,
despite it being such a big product surface, like has
actually gotten like the, the user journey of like I ask a
query, it's sort of I get an AI overview.
I want to sort of go deeper and like look at the, you know, look
(44:06):
at the links and have a deeper conversation.
One click into AI mode. The AI mode experience is like
so fast. They're like constantly rolling
it out into new countries and languages and all that stuff.
So I think also specifically like the US for like the
prevalence of like all of these AI tools so large, like we don't
think about AI mode that much inthe US, but actually like it is
(44:26):
likely the first experience thatbillions of people are going to
have using AI. And it's actually like
comparable against the rest of the AI ecosystem.
Like it's a frontier AI experience.
It's like the quality is really great.
It's super fast. I'm proud for the Google search
team who was able to build that because like, I think they've
actually built like a really toptier experience.
(44:48):
And it's great that that also gets to be the experience that,
like billions of people who haven't used AI before, will
will get to feel. Yeah, I feel like those that are
on like the online tech bubble or the Twitter bubble think that
Chad GPD is king and then that is secondary.
But when I talk to my friends that are not on Twitter, which
is honestly most of them, like my real world friends, they're
not on Twitter. They're using Gemini and they're
(45:09):
using AI search through Google as they should.
Like we're millennials and we'vebeen using Google our whole
lives. It's the it's the most
frictionless way to experience it.
With that in mind, and this is, I don't know, this is kind of a
different question, but what is your bowl thesis for Google as a
company in an age of, you know, Google's Google ads being eaten
by other LL Ms. Yeah, it's an interesting question.
(45:32):
I think my world view is everywhere I look, I get excited
about Google and there's there'sso many interesting places where
like Google has built and like search I think is one of these
where like Google has this like steward responsibility in the
ecosystem. And like if you look at what
that means from a product perspective, it means that like
our obligation to the world is to not like snap our fingers and
(45:53):
then all of a sudden everything changes inside of Google because
actually in a lot of ways Googleis the front door to the
Internet and the Internet economy.
So I think like how you approachbuilding that product in the
response that Google has to build that product looks very
different than in other domains where like it's a complete
completely Greenfield. Like Google's basically
competing against, you know, allof these like other top
(46:16):
companies and like it's super competitive and like it's a, you
know, no, there's no clear winner yet.
And so I think it's been interesting to see us make
that's across the board. I think the thing that gets me
like I'll make 2 like small comments about what gets me most
excited. I think DeepMind helping solve
all of these scientific problemsis like a very real potential
(46:40):
positive outcome for the world. And I don't know if you saw
this, but sort of folks at Google, we just got our third
Nobel Prize in in two years, which is awesome.
So like Google really was this like home of frontier science
that's taking place. Demas and John John John Jumper
won last year and then we just won one for a bunch of the, the
guy who runs our, our, the Google AI quantum lab.
(47:02):
And so there's like so much frontier science work that's
happening is really exciting. The other angle is
infrastructure. And I think Google builds the
world's best infrastructure. So for me as like somebody who,
if you think about the future, like ultimately dependent on
this AI infrastructure that's being built out, Google is like
well integrated in that world. And we have our TP us, which are
(47:23):
sort of on the frontier of what's possible with, with
computing hardware. And like, I actually have two TP
us behind me, if you can see, which is really fun.
So, yeah, I, I think there's everywhere I look, there's
reasons to be bullish in addition to, you know, Waymo and
all these other experiences. Like it's just, yeah, it's a ton
of fun to be at Google these days.
And I think it's we're just getting started, which is funny
(47:44):
to say given how how great things have gone for Google.
You only realize how early you are decades later, right?
It's easy to feel that you're late at anything, but usually
when you look back on it, you are early, like most of the
time, right? And we're very early.
Is there anything that I should have asked you that you just
find super interesting that people would find helpful before
we go? I'll make one last pitch that AI
(48:06):
dot studio slash build get started vibe coding for free.
If folks have product feedback or questions or need us to build
things for you, let me know. We're we're very much like
building AI Studio in public, which is what I'd love to do.
So you're on the Internet, on e-mail, Twitter, whatever, send
us feedbacks. Had a suggestion suggestions and
Chris thank you for for having me on and for taking the time to
(48:28):
chat. I would love to we got to vibe
code some stuff together and would love.
Feedback, I would love that. And where can we find you,
Logan, if anyone wants to reach out?
Yeah, I'm on Twitter, LinkedIn, Logan Patrick, you can find me,
find me all over the Internet where people are talking about
AI. OK.
Well, thanks, Logan. Thank you.
Hey, guys, If you're still listening to this, it's probably
because you haven't had a chanceto take your Airpods out.
(48:49):
You're still mowing the lawn, you're still driving, what have
you. If you're still here with me, I
would really, really love and appreciate a five star review on
Spotify, Apple, or wherever you get your podcast.
It would mean a lot. If you want to go the extra
mile, share this episode with a friend that might have an
interest in starting a business.It would mean a ton.
Hope you have the best day of your life today.
I want the product experience when you land on my website to
be an AI voice agent. All right, it looks like it's
done 66 seconds. Let's try it.
Hey, how's it going? It's going well.
Thanks for asking. Could I get your full name,
e-mail address and company name?OK, my mind is buzzing with the
possibilities. How big is the opportunity to
have like an agency that helps implement these tools into small
(00:21):
businesses? I was at a an event in Santa
Barbara last week. The top executives in the world
from Fortune 200 companies and even these top executives.
Don't know how to use AI tools? You're 10 prompts away from the
home run. Could you imagine how arrogant
that advice would sound? Three years ago just launched 50
different things. Now it's like, no, that's 50
prompts. You can do that.
(00:41):
You're literally going from likeI have that idea to deploying
the thing into literally 90 seconds and like the cost and
barrier to entry is literally free.
All right guys, I just recorded a banger of an episode and I
feel the need to issue a public apology.
What apology? Well in the past I've talked a
little bit of crap about Gemini and or Google's AI products.
(01:04):
I'm a changed man. Today I chat with Logan
Kilpatrick. He is from Google's Deep mind
team. He knows a ton about all of
Google's AI products and about what ideas you should vibe code,
what AI tools you should use to vibe code, what types of ideas.
He shared a screen and we vibe coded 2 different apps with one
prompt each. This is not a sponsored episode,
Google paid me $0.00 to publish this.
(01:25):
But I am a shareholder of Googleand a personal fan of their
company, and I think there's a lot that we can learn and a lot
that we can build on top of Google's AI products.
So today we covered VO3, Nano, Banana, Gemini, AI Search and
more. So if you are here for ideas and
tactics and tools, this is the episode for you.
Please share with a friend and enjoy.
(01:46):
My name is Logan Kilpatrick. I lead the developer product
team for AI Studio and the Gemini API at Google DeepMind.
And we're really focused on how do we take the latest AI
capabilities coming from Google and coming out of DeepMind and
put those in the hands of peoplewho want to build stuff.
And the whole sort of spectrum of builders these days from
everyone from, you know, developers and enterprises who
(02:07):
are like building massive companies and products to like,
hey, I just have this idea and Iwant to build my first AI app or
build my first app at all and, you know, share with a friend or
someone in my family. So we're building for all of
those people, which is challenging, but also a lot of.
Of fun. That's exciting.
What of like all the products within Google's AI Studio?
What are like the main ones? Why don't you just list them
(02:29):
off? The fun part about Google is we
have a massive spectrum of products.
You get everything from if folkshave heard of of the Gemini
apps. So the Gemini app is like
Google's personal assistant powered by Gemini to you know
all of the Gemini integrations that you might find in like
other Google product services. So that's everything like Google
Docs and Sheets and Drive, etcetera, all have Gemini
(02:52):
integrations to search with AIO reviews and AI mode folks
haven't tried is like an awesomeexperience inside of search to,
as you mentioned, like actually custom built a like almost like
AI native products. And that's notebook LM, which is
sort of like a research assistant that takes all this
like content that you have and makes it infinitely repurposable
(03:14):
to AI Studio, which is a sort ofAI builder platform.
If you want to create software and you want to build something
powered by AI and put it in the hands of users, the platform for
you to Google Labs, which has all these like early stage bats
and things like Opal and and others.
So there's, there's a huge spectrum.
The simple answer to your question, Chris, is you can go
to Google dot AI and it has sortof like the suite of all of
(03:36):
these different products that are available and you can sort
of look through and find what maybe is most exciting to you.
OK, so you've got a really unique insight into all of
Google's AI products. If you were forced, heaven
forbid, to have to pick one of them to build a business with,
or to start a business with onlyone of them, what would you
choose and why? Yeah, it's a good question.
I'm biased because I spend my time thinking about AI Studio.
(03:58):
So probably AI Studio if you want to build a product and
build a business. I think the my pitch to you
would be build AI products. And the reason for this is like
AI is both extremely monetizable.
There's edges everywhere you look like there's all of these
emerging interesting product experiences that you could
potentially build. And actually the barrier to
entry is pretty, pretty minimal.The beauty is you don't need to
(04:21):
be an AI expert to go and like build AI products.
You just need to have some problem that you're trying to
solve. And like, there's a probably a
good chance if it's at least a digital problem that AI can help
solve that for you. It is this like unique
combination of all these things plus like consumer interest is
increasing, consumer willingnessto pay for AI products is
increasing, costs are going down, the technology is
(04:42):
improving. So there's like all of these
very unique tailwinds that are happening at the same time,
which I think makes this like such a exciting moment to build
AI products in AI. Studio, You've probably seen a
lot of people building cool stuff with Google products.
What are like some interesting stories or case studies of
people that have used your products to build something
awesome or something simple or something profitable or any and
(05:05):
all of the above? I'll give sort of 2 ends of the
spectrum from it from an answer perspective.
So on one hand, like in AI Studio today, teams across
Google are like prototyping the next versions of a flow, which
is our video editing creation product for creatives, like
experiences around Google searchand YouTube and other things
(05:26):
like that. So it is really like becoming
sort of the engine room for Google to prototype and like
build next Gen. AI experiences.
So I I see like one end of like,you know, these experiences
might end up impacting billions of users too.
With the nano Banana launch a few weeks ago, on day one of the
nano Banana launch, users insideof AI Studio were vibe coding
(05:46):
literally 10s of thousands of AIpowered apps using that new
model and like much thinner experiences, things that are
like kind of goofy, but also like interesting, like haircut
AI and like all these like photorestoration products.
These like very, very vertical use cases.
But like you're literally going from like, I have that idea.
I could see why people would want that to deploying the thing
(06:08):
into production and like puttingin front of users and literally
90 seconds and like the cost andbarrier to entry is is literally
free. It's paid when you deploy and
you have to like, you know, service external users and
stuff. But to actually build the thing
doesn't cost anything, which is just such a unique moment that I
don't think like if you look at the arc of what's happened in AI
historically, there's this lag of like new capabilities
(06:32):
relative to products on the market actually being available.
And I think what Vibe Coding is enabling is this like
compression of like new capability to there's 1000 new
products built on top of that capability on day one literally
being deployed, which is a really unique combination.
Now, if someone's hearing that, you know, 10s of thousands of
products being tested or deployed on day one or week 1,
(06:54):
give me reasons why. And I'm I'm in your camp here.
Give me reasons why people should not feel discouraged by
that. Like, oh, it's I'm already too
late. Oh, there's haircut.
AII had that idea. Like what are you seeing out
there? Yeah, that's such a great
question. I think a couple of things, like
1, the thing that gets me excited about this experience
that we're building in AI studiois how easy it is to go and
(07:17):
remix. So again, maybe somebody has
like generally the same idea, but like you're like like, oh,
actually, you know, I am a hair stylist and like I have some
unique insight or like I get my haircut and I hate these four
things about that experience. And like, therefore I'm going to
put a unique twist and a unique spin and like that's literally
like one that's a prompt away. So you're a prompt away from
(07:39):
like, yeah, maybe like roughly there's other people doing the
same thing, but like you have some unique differentiated
perspective. So I think even if you take like
all of those like very basic verticals, there's like this
massive like tree explosion at the bottom end of like how to
make it different and how to keep adding features and like
discoverability and how you position and how you make the
(08:00):
experience fun. So I really think it's like
every at every one of those different thousand 10,000
things, there's, you know, maybe1000 other additional options
that like could be interesting and fun and exciting.
Products. Yeah.
And I think it's important that people start with what they
know. Let's say you're a hairdresser,
right? And you just hear anecdotally,
(08:21):
you know, what's that going to look like?
What's it going to do? You want your hair like this.
What is it going to look like? You have a unique insight into
the market that makes you want to do haircut AI, right?
But if you're just listening to this and you have no background
in in working in a salon, you'reprobably not the person to do
this. But if you do a quick audit of
your own life and experience, you could have ideas that are 10
(08:41):
times more valuable than that, right?
Like when we solve our own problems with these vibe coding
tools, it has the greatest likelihood of succeeding because
we know it more intimately than anyone else.
Yeah, it is also fun. I I think while at the same time
that that's true, Chris, it is also fun to just like take
random shots at things that I know nothing about.
I'm like. I do it all the time.
(09:01):
Yeah, it's. All the time that it's like both
things are true at the same timethat like while the value of
your expertise and your edge is like very real, it's like also
so much more approachable to like go into domains in which
you're not an expert. And like, maybe you actually
just get lucky and stumble upon the thing that's like really
interesting or you have some like random unique site that
(09:22):
actually is super valuable. So it is just another another
plus in my book for this vibe coding moment being like such an
interesting experience. Have you ever read the book
Range? Yes, Yeah, yeah, yeah.
That's what I'm thinking of as we talk about this, because they
did a study and a lot of times the experts have like the worst
insight because they're so biased and they look at
something a very specific and narrow way.
(09:43):
Whereas in quote, UN quote, ignorant outsider comes in and
they, you know, it's like the Midwest meme.
They look at it like a caveman and they have this big unlock
because they're not biased by their previous history.
So I do think there's, there's arange there right between like
what you know what you recognizeyou being able to see
opportunities more clearly than others and like you being way
(10:04):
too biased, right? You being like the old fogey in
the room. That's like all that would never
work because I've been in that business for 10 years.
Like I've had people tell me that and I've launched anyway
and it's gone great, right? So I think it's a matter of like
finding where your place is on that spectrum and just taking
wild home run shots on goal justbecause you either win or you
learn, you know? I think you're 100% right and
(10:26):
it's also because of how accessible this is now.
Literally you could be doing andtaking a shot at building
something every single day, which is awesome.
And like, that's how I feel. Like I, I wish I had more time
in the day, but like there's 1000 things I want to build.
And like you actually could be building 1 AI app every day with
like probably 30 minutes of workor something like that.
(10:46):
And like again, maybe the 1st 50things you build aren't
interesting and no one cares. But like the 51st might be.
And like again, you spend $0.00 in that whole process to get to
the point where like you actually built something that
you're really excited about. So such a special moment again
from that perspective. Well, and could you imagine how
arrogant that advice would soundthree years ago?
Like just launched 50 different things.
It's like what? Like I don't have unlimited time
(11:09):
and money, and now it's like, no, that's 50 prompts.
Like you can do that. Yeah, there's something
interesting about if folks follow like levels IO and some
of these like people online who talk about like, you know, they
had like 20 ideas and only threeof them worked.
And the three that worked are now like, you know, $100,000 a
month businesses or whatever. Like that experience probably
(11:30):
doesn't perfectly generalize across everyone who tries to do
this. But like that is now like more
in reach than it's ever been. You can literally take a hundred
shots at it. And like, yeah, you should be
thoughtful and deliberate about what shots you want to take.
But like the barrier is like basically non existent, which is
really exciting. Like it really is just like, do
you have agency? You know, are you interested?
(11:50):
Are you spending your time doingthis?
Or is like there's something that's more high value in the
world that you're spending your time on instead?
Yeah, that's beautifully said. And I ask you this next question
more as like someone who I know is a student of the game and
like in the startup community ecosystem, seeing what's
happening, how are you seeing people find success at actually
marketing these apps that they vibe coded and not just building
(12:12):
them? Yeah.
One of the interesting things isthis goes back to like what is
the edge that you have? Like I'm somewhat biased because
I spend a lot of time on like seeing what people are building
on social, which I think is like1 version of this, of this like
flywheel of like how people are coming to market these days is
like you could basically for free social first engage and go
(12:32):
and do that. I think there's another angle of
this, which I've seen more and more startups and this is like
more in like the indie hacker bootstrapped space.
But people are building these like packages of not just a
single tool, but it's like, Hey,you're a student or hey, you are
XY and Z persona. Here's the package of like 10 AI
tools that you need. So it's not like I, I'm trying
(12:54):
to make the tool to rule all tools.
It's like actually, no, you have10 different needs as a student
or as a, as a lawyer or as a whatever your, your persona is.
And like I'm going to package all these things up.
I think some of the challenges like like how you go to market
with that package looks very different than how you would go
to market with one of those individual tools.
Like the search volume, for example, for like, you know,
(13:15):
haircut AI might be extremely thin, but you sort of package
together the like 7 different tools and some specific domain.
And then all of a sudden like you've actually reached a
critical mass where there might be a business that you can
build. So I think that's one of the
things that I've been most interested in.
And I, I don't know if like I haven't seen a lot of people
doing this and could be an interesting edge to like try to,
(13:38):
to try to come up with what thatpackage would look like for like
a getting to a wider audience. Well, I just interviewed a guy,
John Rush. Do you follow him at all?
I don't know. I'm not sure.
It was episode 228 and he he makes 3,000,000 bucks a year
from a dozen AI tools, maybe like 20 AI tools and it's
definitely 8020, right? Like most of them don't make
(13:58):
much money, but he has like an an AISEO tool and a marketing
tool and all these other tools and it's all like he's selling
them to start up guys to indie hackers, etcetera.
But he's able to cross sell and cross promote between all of his
e-mail lists and he's able to triple down on his same like
meta ad accounts and he's able to, you know, share all these
resources, his AWS account and all these things.
(14:21):
He just has a lot of surface area for learning what people
want and what they're asking foror not asking for.
And he's able to take all these shots on goal.
And you know, if I might have signed up for this, you know,
AISEO tool for 100 bucks a month, It never actually paid
for it or I turned out, but thenI end up spending $200 a month
for this other tool that he offered me.
(14:42):
I think that's a really smart idea.
Like there's no point in building something and not
hitting publish on it, right? Or telling people how or why
you're building it. Like it's very little
incremental friction to publish what what you're doing compared
to actually doing the thing. Right?
Yeah. I think there's also something
which is an interesting point that you're making, Chris, which
is I also think there's just like a level of complexity in
(15:05):
what you have to build. And if you think about like if
you're just getting started doing this stuff, like again,
building the like full end to end AI marketer that does SEO
and outbound and ads and five ofit's just like really daunting.
And I think for a lot of people like your experience is like
probably not broad enough that you would have enough domain
expertise to like really have a point of view on like what's the
(15:27):
right product experience for allthose things.
But like you can maybe build thelike sliver again, like thin
version of like three of those products pretty easily.
It makes me ponder what the future is going to look like as
as people sort of, you know, there maybe will be these like
all the like big companies or maybe not all of them, but like
all these companies are trying to build the everything app.
I mean, at the same time that everyone's trying to build the
everything app, like it's now becoming easier and easier to
(15:49):
also build the like just one thing app.
And I think users actually appreciate that sometimes.
Like, I don't want all this complexity.
I just want to take a picture ofmyself into an app and like see
what I look like with different haircuts.
I don't need a bunch of other stuff.
Like, I mean, Elon Musk isn't even really finding success at
building and everything out, butyou're you're out there trying
to build the next HubSpot, you know, Like what what do you just
(16:11):
build a tool that puts furniturein people's empty rooms and go
from there? There's like very specific
niches of this, like I love the furniture one, but like I was
helping my girlfriend with this.She wanted curtains.
That was the only thing that shecared about.
She was like, I don't need to redesign my whole room with AII
just want to see seven differenttypes of curtains and like going
deep on that experience. Like again, it's maybe it's
(16:31):
maybe the funnel to your, you know, furniture AI business.
But like really the thing that people are trying to solve is
like some very specific problem and you can win on the niche and
like. Then get people back into the
larger funnel. I love that.
Like I just wish people had moreof a bias towards like that's
not niche enough as opposed to that's too niche AI curtains,
(16:51):
you know? Like that's not too niche.
It's not too niche, but I do think, and it's interesting, I
think this like bias comes from like the historical cognitive
dissonance of like the cost to build software being high.
So like all the conventionalism,the way that humanity has been
programmed is like you have to take a big enough swing for it
to be worth it to build softwarebecause the cost of building
(17:12):
software is high. And I think it is like not
trivial. I think for a lot of people to
go through the like flipping theswitch that like actually the
cost of building software is nowtrivial.
And like the strategy in which you should employ in that world
looks very different than the conventional wisdom.
I genuinely think the way that the flip happens is you like
experience at first hand. Like you go build 15 different
furniture apps powered by AI in a single day and you're like,
(17:35):
wait, holy crap. The limitations are all
different than what I thought they were.
Yeah, you spoke on a different interview about I forget which
product it was that watched likea 30 minute museum video and
pulled out a list of exhibits. What what are you seeing with AI
tools that can quote UN quote watch video even if it's just
frame by frame? And what applications do you
(17:56):
think are exciting around that technology?
Yeah, that's a great question. Do you want to build stuff or I
can I can answer this question, but we should also I'm happy to
all sort of give vibe coded answers to all of these
questions. And then and then we'll try and
I'll also talk while it while itwrites the app, so.
This is a fairly selfish question because this is
something that I've been trying to do personally.
(18:18):
Like I want a tool that can likewatch short form videos for me
and like extract interesting points from it where I can ask
it questions that can go out agentically and find interesting
short form videos that I might be able to post content about,
right? Yeah, I love that.
So I'll kick off building something and then I'll give you
my answer. So we want to build.
(18:38):
Let's do, and then maybe I'll try.
I'll see if it's speech to text on a podcast doesn't work.
Let's see. Build me an app that takes in a
video and then parses out perhaps the most interesting
stuff from the video, picks up on the trends, gives me sort of
maybe an entire analysis of whathappened, what the gist of the
(18:59):
video is, what the take away should be. 10 insights, but make
it so that I can actually use AIto customize that report that's
being generated, in addition to using AI to analyze the video as
it's processed. What a prompt.
It's like watching Picasso in his prime.
Yeah, my my word vomit of watching that, doing that prompt
(19:21):
live without being more thoughtful about it, but.
No, that's great. Yeah.
So what to answer the question, like that example that I was
referring to about a tool that can like take videos and and you
know, in the example I was giving, it was a museum and you
can sort of extract all of the exhibits in the museum.
The beauty is it's just Gemini, like literally that is just like
(19:41):
the Gemini model out-of-the-box.So you can actually do this in
AI Studios. If you just go to AI dot studio,
you upload a video, you ask, theprompt is like extract all of
the different scenes from this video.
It will literally go and do thatfor you.
So it's like very simple, that works out-of-the-box.
The question then is like, what is the product experience that
you sort of build around that model?
(20:04):
And I think that's where the magic is.
I've just seen. Like Gemini has state-of-the-art
image and video understanding. It's it's one of the only models
that has native video understanding as well.
And it's more than just like theframe.
Like it's not just if you were to like pull sample a specific
frame, it's more than that. It's like the interleaved frame
and audio coming together and like the context that it's
(20:26):
shared on a like a frame and audio by audio basis.
So it's a little bit more complicated.
Than that. Oh man, all right, I've got a
video. Analysis Engine.
Now I need to see, do I actuallyhave a video on my desktop that
I can use for this? All right, 270 megabytes.
Let's see if it says I can do supposedly up to 1 GB.
(20:47):
So let me drag this in and analyze video.
Let's see and so just to give context on this, you know, the
prompt was build an application that takes a video, parses it
application should identify the most interesting etcetera,
etcetera. You can see it in the top left
hand corner. Gemini 2.5 Pro went and you
know, did a plan, wrote all the code for this and actually made
(21:08):
me an AI video analysis engine. I just copy and dragged this and
was able to get an analysis, wasable to get 10 key takeaways.
And then the cool thing is we can actually again, and this is
powered by AI in real time, we could to change what we want
from this analysis. So Chris, I don't know if you if
you have suggestions of like howwe would potentially change this
(21:30):
analysis, but we can change it if you want.
Yeah, what about videos that have no text or no audio?
It's just just just like pure video.
Yeah, Yeah, we can also do that.So I think it's it has, this
goes to like Gemini has like native image understanding and
video understanding. So it can, if there's no audio,
like it's perfectly fine. We could find a video that has
(21:51):
no audio and it'll actually likelook.
OK, my mind is just like buzzingwith the possibilities.
I don't know why I've never had much success with like an AI
watching videos but I just haven't but this.
Is I think it works really, really well.
So this is, we have like tons ofcustomers who are super
successfully doing like AI watching videos.
And there's this interesting loop now where it's like AI
(22:13):
watching video that is then AI generating video with VO3, which
is then like using nano banana to do something.
Like I've seen a lot more of this activity where you can sort
of take this full suite of models, stitch them all up
together. And we have some examples of
this where it's like, can you, yeah, can you stitch all these
things up together? And these are just a bunch of
the like random examples in our in our gallery right now.
(22:35):
But yeah, lots of cool stuff. And like, I genuinely think
you're probably 3 prompts away from something that works really
well. And again, it's like critically
the Gemini model that's enablingthat analysis.
What are some other use cases for watching videos that you've
seen people use? That's a good question.
I think one of the one of the most interesting ones is like
there's all of this intelligenceand videos and it's just like,
(22:56):
how do you extract intelligence from videos?
Like I talked to a lot of companies that just like have
lots of video data internally inside of the company and
they're like, yeah, wouldn't it be nice?
And I think like content creators actually is like
another great example where likeI, you know, very inactively do
my own podcast and like for that, I'm like, you know, if I
wanted some montage, I did this in the past where like I
(23:17):
basically uploaded all of the data and I built this pipeline
that would just like go through the video and I would ask a
question and I would like searchacross all of my videos
completely vibe coded and like pull out interesting insights
that like, I didn't even know that I talked about that on one
of my podcasts. It was super cool.
What are? Mistakes that you're seeing
people make that when it comes to prompting and or vibe coding
(23:39):
that are easily fixed. Yeah, I think the big one is
like people. And I actually think like
building software is very much like this as well.
It requires persistence. In this example of that, we were
just looking at it kind of worked.
It kind of didn't like maybe it kind of like missed the point of
like the second part of what I wanted.
But like the beauty is the cost to continue to iterate is
(24:00):
literally just like putting something in the prompt box.
And we even added a bunch of, you know, suggested downloading
the report as text or clearing error messages or refining
report sections. A bunch of pre made prompts that
will like show up here based on the context of what you're
building. So I think people often times if
that first one doesn't just likehit the home run.
They're like, this thing doesn'twork, but I think it's like
(24:23):
really, you know, you're 10 prompts away from the home run
and the important part is that you do the 10 prompts to get
there. I think that's the biggest
mistake right now. With everything changing so
fast, what skills or habits do you think will stay valuable
throughout all these changes that we're seeing with AI?
Yeah, it's funny. And like back to the a similar
thread of the last question you asked, I think everyone talks
(24:44):
about like building soft, you know, being a software engineer
is this like diminishing thing that you should be doing.
And it's, it's funny because I think about the skills that I
learned as somebody who's like traditionally trained in
building software as a, you know, a computer science
undergrad and someone who's formerly a software engineer, I
think about almost none of that,of what I learned having to be
(25:07):
like typing, typing letters intoa key into a keyboard that then
translates into code. And like, I think almost all of
it is like how to think about solving problems, how to be
resilient. And I don't know about you all
or other folks who have built software, but like my
experience, experience of building software is error
messages. And I think that's like spending
(25:29):
years of your life just seeing error messages.
I think like things basically not working, I think trains you
in a very different way of like how to be resilient.
And I think the reality is like how to be resilient and how to
have agency and like go and takeinitiative.
I think are like the two determining factors and all of
this and just life in general. The challenge is like, how do
you put yourself into an environment where you can do
(25:51):
both of those things? The nice thing is like for AI is
sort of enabling you to be have more agency.
Like you now have all these tools at your disposable.
The floor is sort of is leveled up so that you don't have to
worry about like the drudgery ofa lot of the tasks that you were
doing before. I think it's a beautiful moment
from that. Perspective.
Yeah. I mean, more agency can make or
(26:12):
break people depending on the person, right?
It could drive us to be our bestselves or more of our worst
selves. But I think the people listening
to and or watching this are are in the the former category.
What are some overhyped like AI use cases that you're seeing
right now that you're you're notbullish on travel?
I hate the idea that I'm going to be booking my flights with
(26:32):
and this is somebody who travelstoo much.
We were talking before this off camera.
I travel too much. I wish I wasn't traveling, but I
just think it's like the most quintessential like demo use
case that is like not actually valuable that much.
I think it's also because not the form factor that I've seen.
Like I do think there's something interesting and AI,
you know, enabled travel planning, but I think the
(26:54):
product experience that most people are building is like AI
to book your flight ticket. I'm like, I don't know about
you, but the United website is like pretty simple to use.
Like I don't actually have AI tobook my flight.
I need AI to like orchestrate the like actual complexity of
travelling. And like the most of the
products are not doing that. So it's just like the easy thing
(27:15):
they're actually helping me solve.
And I'm like, I don't need the easy thing to be solved.
I need the hard thing to be solved.
Yeah, people are trying to to solve a problem that's not a
problem. And the the cost of AI getting
it wrong is quite high. If I have AI book me a flight to
Vegas with a layover anywhere, you know, it's really messed up.
There's like 50 non-stop flightsfrom DFW to Vegas every day.
(27:35):
But that would happen like something in the logic would
happen to save me $3. It would, it would have me lay
over in Miami or something and that's to save me 3 minutes.
What are some travel AI use cases that you think could be
useful, if any? There's something interesting
about like, how do you bring together all of these like
disparate sources across the Internet?
Like, you know, I think there's some amount of useful signal
(27:58):
that you get from like main travel websites as an example,
but there's also like you kind of want to discount the opinions
that you get, like depending on what experience you're looking
for. If you want like a nuanced
travel experience, choose your favorite like rating websites
that that rates like places on travel.
Like oftentimes you might actually get like, you know,
it's 4 1/2 stars, but it's like very biased because it's like a
(28:21):
bunch of, you know, US travelersor it's like some, you know,
specific persona that is like maybe not the persona that
you're looking for, even though you might be a US traveler
yourself, which is the irony. So I think there's something
that like, how do you sort of connect all of this stuff
together and have like real sortof like travel intelligence of
like where you're going and likethe places that you should be
(28:41):
going to that like maybe are haven't bubbled up to the top
level of like, you know, the thehottest place to be.
And also like discounting a lot of those places like if you want
to avoid those things. And also just like the
logistics. I think about this like
traveling places that have like public transportation systems
that are like new. I was in London a few weeks ago
(29:03):
and hadn't used the like London train system to get from the
airport before. And I was like halfway through
this process of like walking around the airport.
I was like, I sure hope I'm going the right way.
The information about how these systems work is like out there
on the Internet. You just need to like build an
experience that make if I'd gotten like a e-mail from my
travel agent saying like, hey, by the way, you're in London,
(29:24):
here are your three options for how to travel.
And like, here's literally the map of how to do that.
Like that wouldn't even be that hard.
I could have probably if I codedit beforehand, but I just didn't
send it set it up. What if it was like a travel
companion that texted you like it was it tracked you right,
like Uber might and texted you as you got to different spots
along your journey, like, hey, Isee, I see you landed.
(29:44):
You're going to Terminal 4 because that's where the new,
you know, subway is, right? Oh, cool, you found the subway
awesome. I know you love Lebanese food.
There's a five star rated place right at this stop, right?
Like just kind of like text along the way and you can tell
it to stop at any point, but it's it's tracking you.
Text as the form factor is, is something that I'm like overly.
(30:06):
I'm overly excited and bullish. On 100 percent 100% I don't want
more notifications but I can handle it if it's all within my
messages out. And like you're travelling with
your friends and like all of a sudden now it's multiplayer in
the conversation. Like I want to put my sort of
travel companion into the group chat.
And like I'm I'm travelling withmy family in a few in a few
weeks. So like, I would love to be able
to like just not have to be the arbiter of information about
(30:30):
like what's our plan and our like all this like conversation
toil that you have to have like put my companion in there, drop
the little thing. And then whoever forgets to
check the Google Sheet that has all the list of the itinerary,
just text in the group chat and like the companion is going to
answer like technologically likeit's actually not that hard to
build that, which is awesome. Yeah, it's a Twilio integration.
(30:51):
What other cool things like are you?
Like, did we not get to that? You're just excited like a proud
parent to show me. Yeah, that's a good question.
So there's two that are top of mind and I'll show one of them
and the other one we're working on like a great showcase for I
think like voice AI agents and like computer use agents, I
think are two things that are really exciting.
(31:14):
Computer use agents. We just launched the time of
this recording like literally yesterday, a state-of-the-art
model that's able to sort of like navigate browsers and do
all this stuff for you. And it's like a really helpful
if you if you're somebody who's like thinking about building
agents, it's really helpful. It's like a supplemental
mechanism to let go and gather information or to do like
automate repetitive like UI tasks that you're potentially
(31:36):
doing. So really excited about that.
The other one, which is like adjacent to this is like voice
agents. I think there's a huge amount of
alpha in this. Like if folks have like tracked
the voice AI market, the like amount of companies, the model
quality, the like investment, the use cases are all like up
and to the right. There's like a huge amount of
potential impact and like it's actually not that hard to build.
(31:57):
And the fun thing is like you can literally go and vibe code
voice AI experiences inside of AI studio, which is really cool.
So I'm going to tell you this demo and then we'll I'm trying
to think of like what do? What do we want to build that's
like? Voice AI powered.
I will say I had this lead magnet that was just a form for
this initiative I have and I just swapped it out with a voice
(32:19):
AI agent. And I'm upfront that it's a
voice AI agent. And I see everyday like the
transcripts of whoever having a conversation with my agent and
I've talked to them like afterwards and they love it.
Like they know it's AI. It's a great experience.
I think we have this perception that a voice AI agent is taking
over and people aren't going to like it.
(32:39):
And it's more frustrating than being on hold with AT&T.
But it's a better experience. And if you know it's AI and you
don't feel tricked, it's just superior.
Extremely bullish on that. Yeah, yeah.
Well, that's actually a great thing.
Let me try vibe coding this. So I'll, I'll describe what I
understand and what this is doing and we'll see if the model
can, we'll see if AI Studio can actually build me an app that
(32:59):
does this out-of-the-box. OK.
All right. I want a landing page for my
website where we sell, we actually sell AI services and I
want the product experience whenyou land on my website to be an
AI voice agent powered by the live API.
And basically basically the whole experience is going to be
(33:20):
a it's, you know, it's a veneer on top of a lead Gen. form
behind. So the user will talk to the
live API and behind the scenes, the model will actually just be
filling out a form. And then once the model has the
information that it needs, whichlet's say that it's like the
name and the e-mail address and the company that the the person
works at, the model will say thanks, it'll end the
(33:41):
conversation. And then it'll kick off a
workflow behind the scenes to e-mail that person and like
create a lead Gen. and and database.
So let's do all that. Let's powered by the live API
and let's make the website look futuristic.
I want a little bit of I want tofeel like I'm in the future for
this. And my nickname for this is Yap
Yap to app. So we'll see if I like the how
(34:05):
good it is. This is a fairly involved.
So like this might be an exampleto, you know, level set my own
expectations. This might be an example where
like it doesn't work the first time because we're actually, I
didn't think deeply about my prompt and I was truly just
yapping. But we'll see whether or not we
get anything interesting from this.
But yeah, I'm I'm not surprised there's that like not you as you
were describing, Chris, that like experience that a lot of
(34:27):
the users have. I also think there's this like
novelty effect where like you might be able to like it's
people are surprised and interested in this because they
don't see that experience everywhere.
And like I do, maybe there's a, there's a time window of like
when that's true. But like it feels like it's
right now we're like people are open and willing to try because
they know how AI is changing. Stuff well, and the bar is
(34:50):
pretty low. Like if I need to call customer
support for anything, my day is ruined.
I'm I'm yelling at my kids, it'sI'm on hold.
I'm going to get hung up on likethat's what AI has to be.
We will never be on hold ever again, right?
It's either that or I'm calling a restaurant to make a
reservation and they don't answer, right?
Like, that's kind of what we're up against here.
(35:11):
Yeah, all right. It looks like it's done 66
seconds. I have low confidence it's going
to work, but let's try it. Hey, how's it going?
It's going well. Thanks for asking.
I'm here to help you with Stellar AI.
Could I get your full name, e-mail address, and company
name? Yes.
My name's Logan Kilpatrick. My e-mail is email@xyz.com and I
(35:33):
work for Google. Thank you Logan Fitzpatrick for
providing your full name, e-mailaddress, and company.
I have noted that you work for Google.
Is there anything else I can help you with today?
Nope, I'm all good. Can you contact Stellar AI and
let them know that I'm interested?
We're so close. Almost almost zero shot
experience accepted. That's amazing.
(35:55):
Yeah, well, I'm curious, but I think it you sort of close like
I'm like 2 prompts away from this thing, what I need.
Is it like a walled garden like if you said what's the capital
of of Kansas, would it answer you or would it be like I'm not
trained on that that's. A good question.
So I think my my hypothesis is like the guard actually.
So this is where looking at the code is actually helpful.
(36:16):
So if I go to code and then I goto see not voice agent dot TSX
here it is. Yeah, actually system
instructions. You are a helpful, friendly, and
personal AI agent. For Seller AI, your primary goal
is to collect the user's full name, e-mail, and company name.
Be conversational and be conversational and engaging.
(36:36):
Once you successfully collect all the pieces of information,
you must call the submit leads form function.
Do not ask for other personal information.
Give the user an introduction toyourself before starting.
So my guess is like this system instruction doesn't say anything
about like don't answer other questions.
My so my guess is it'll answer right now we can try and then we
could try adding in like only talk about stellar AI do not
(36:57):
talk about anything else and seehow much it works.
But my assumption is that works out-of-the-box as well the.
Pause. The latency is so much better
than even a year ago, right? It was.
It was awkwardly long, I didn't notice it at all there.
Yeah, you don't. It feels, it feels extremely
natural. It is actually always surprising
to me how quick it is. But yeah, it is.
It's it's very fast. So I'm going to keep playing
(37:19):
around this. I might, maybe I'll add a voice
AI agent to my personal website and see if people want to talk
to my voice AI agent. And I'll just have it make up
random stuff and confuse people just to throw them off my trail.
Oh man, that is really cool. What are some things that you're
excited about that it feels likestill very underexplored, like
(37:40):
unexploited by the everyday person?
Yeah, that's a good question. Let.
Me ask a follow up, which is related.
How big is the opportunity to have like an AI automation and
or implementation business or agency that helps implement
these tools into small businesses?
Because you and I toy around with them and it's easy.
(38:01):
You one shot prompted Cool. It doesn't matter how easy it
is, right? It doesn't matter how easy
Google ads or Facebook ads or building websites are like there
will always be business owners that just want someone to do it
for them. It's not about the the
complexity, it's about the brainspace and like the the
perception of difficulty. Do you see that as being a a big
(38:22):
opportunity? Well, so I'll, I'll give my
bias, which is like, I don't know what the actual numbers
look like, my intuition and likemy personal experience engaging
with people and I'll share. I was at a was an event in Santa
Barbara last week and it was like some of the top executives
in the world from like all the like Fortune 200 companies and
even these top executives who I think are like obviously
(38:45):
extremely smart, like in the know, they, they're, they have
teams that are telling them how important AI is.
If you like actually get into the nitty gritty, like a lot of
folks don't know how to use AI tools and like they would need
to go and delegate to like go and do a bunch of these things
and they're like extremely well paid, like at the frontier of
sort of knowledge. They can talk the talk, but
(39:06):
that's about it. Yeah, exactly.
And they're like, and it's like really interesting to see this
and then they actually like needa lot of hand holding and it
will make progress on this stuff.
So I think like you take small businesses that are like just
trying to get by and like go andmake, you know, move the needle
on, you know, their family business or some small business
with only a few people. Like I think there's just not
(39:28):
enough time in the day to be deeply embedded.
And like you show them these three experiences.
Like I was on a call with a clothing brand and they were
talking about how they, like, want to do all these ideas with
mood boarding and like using AI and virtual try on.
And I was literally on this calljust like vibe coding the things
that they're saying. I was like, yeah.
And like, we're just like, here,here's the app that actually
(39:49):
does that. And they're like, how is that
possible that you already have this thing ready?
And like you can give people like the timeline, the like fact
that it took 66 seconds to buildthis thing.
And again, it wasn't perfect, but like you get the point
across of like this is within reach, which I think is a lot of
the cognitive dissonance that folks have right now is like
they don't actually believe thatit's in reach.
(40:09):
And I think there's a world where like you can actually just
go and the experience sells itself so much because you can
go and take this vibe coded experience.
You can go find this company, the company website that you
want to work with. You can take their products or
their website Reimagine. Imagine it with AI and like
that's your lead Gen. and like the cost to you is like
basically 0, but you can do thatoutreach and instead of being
(40:30):
like, hey, I'm blah, blah, blah,and I do AI stuff, you can be
like, hey, I redesigned your website using AI.
Here it is. If this seems interesting to
you, let me know. If not, like your marginal cost
was basically nothing. So it's like on both ends of the
spectrum of building this type of like AI agency, you can do
really targeted, really rich, really deep outreach.
(40:50):
And at the same time, like you have a customer base that's like
potentially really excited and interested.
And again, all my caveat to this, I don't know how big the
actual market is, but like I would imagine it's large and
there's a lot of people who wantthis as a as a service, so.
Well, I mean, there's, there's 400 million small businesses
around the world. All of them need AI to some
extent. Maybe not all of them can afford
(41:11):
$1000 a month, but I'm insanely bullish about that.
What do you think VO 3 is going to look like in five years?
I think it'll look like a toy, but also like an important like
to me, VO3, and this is from, from conversations that I've
seen, like VO 3 was the GBT 4 moment for generative media.
I think there's like all of these companies that are engaged
in that space have now realized like, Oh no, this technology is
(41:34):
actually possible and going to be good enough.
And like it's basically here right now.
The exponential increase in likesort of maybe not exponential,
but the increase in like capabilities and how good the
models are becoming, I think hasmade like lots of folks across
the ecosystem aware. So I think they'll be like a
huge amount of investment over the next three years.
And it will be like a massive accelerant of like the media and
(41:56):
entertainment industry, which is, which is exciting and sort
of like the outcome that you would want as yeah, as a as a
fan of the space. Will we be in a in a Cinemark
theater in five years watching aa Tom Cruise movie that cost
500,000 to produce with VO3? Is that realistic?
It's a good. Question.
I don't know, my my sense is like actually, what's more
(42:16):
realistic to me is that there's this like infinite canvas of
media that I think is really interesting.
So I think I think my my expectation is like the Tom
Cruise movie will still have a high, you know, maybe something
like roughly the production costwill go down, but it'll still be
expensive. It'll still, you know, they'll
still really deeply like art andcraft put into making this an
(42:39):
experience that both like the people producing it and also the
audience is going to love. The thing that will be net new
is the the content lifespan withthis like infinite repurposing,
an adventure is going to dramatically change.
So the way you experience content is like they'll have a
base video and you'll be able tobe like, wait, this is fat.
I love this story. But what would happen if, you
(43:03):
know, Tom Cruise decided not to hang out on the side of an
airplane and to do something else instead?
And like you can go and see whatwhat's possible.
So I think there's the and I don't know, it'll be interesting
to see how like the platforms adopt this.
But like, I think this infinite content remixing and like
exploration is going to be very much much possible, which is
exciting. I completely agree and I'm not
(43:25):
of the mindset that like VO 3 isgoing to replace Hollywood,
right? The Kindle didn't replace books.
There's going to be a world for both.
But I just think it's going to look so different and what we
see on VO3 today is going to look laughable in a few years,
and it today it looks amazing. It's pretty good today.
What? What's like a Google product
(43:45):
that you wish everyone knew existed that is just completely
slept on and ignored and underrated?
It'll sound counterintuitive, but AI mode and Google search,
despite it being such a big product surface, like has
actually gotten like the, the user journey of like I ask a
query, it's sort of I get an AI overview.
I want to sort of go deeper and like look at the, you know, look
(44:06):
at the links and have a deeper conversation.
One click into AI mode. The AI mode experience is like
so fast. They're like constantly rolling
it out into new countries and languages and all that stuff.
So I think also specifically like the US for like the
prevalence of like all of these AI tools so large, like we don't
think about AI mode that much inthe US, but actually like it is
(44:26):
likely the first experience thatbillions of people are going to
have using AI. And it's actually like
comparable against the rest of the AI ecosystem.
Like it's a frontier AI experience.
It's like the quality is really great.
It's super fast. I'm proud for the Google search
team who was able to build that because like, I think they've
actually built like a really toptier experience.
(44:48):
And it's great that that also gets to be the experience that,
like billions of people who haven't used AI before, will
will get to feel. Yeah, I feel like those that are
on like the online tech bubble or the Twitter bubble think that
Chad GPD is king and then that is secondary.
But when I talk to my friends that are not on Twitter, which
is honestly most of them, like my real world friends, they're
not on Twitter. They're using Gemini and they're
(45:09):
using AI search through Google as they should.
Like we're millennials and we'vebeen using Google our whole
lives. It's the it's the most
frictionless way to experience it.
With that in mind, and this is, I don't know, this is kind of a
different question, but what is your bowl thesis for Google as a
company in an age of, you know, Google's Google ads being eaten
by other LL Ms. Yeah, it's an interesting question.
(45:32):
I think my world view is everywhere I look, I get excited
about Google and there's there'sso many interesting places where
like Google has built and like search I think is one of these
where like Google has this like steward responsibility in the
ecosystem. And like if you look at what
that means from a product perspective, it means that like
our obligation to the world is to not like snap our fingers and
(45:53):
then all of a sudden everything changes inside of Google because
actually in a lot of ways Googleis the front door to the
Internet and the Internet economy.
So I think like how you approachbuilding that product in the
response that Google has to build that product looks very
different than in other domains where like it's a complete
completely Greenfield. Like Google's basically
competing against, you know, allof these like other top
(46:16):
companies and like it's super competitive and like it's a, you
know, no, there's no clear winner yet.
And so I think it's been interesting to see us make
that's across the board. I think the thing that gets me
like I'll make 2 like small comments about what gets me most
excited. I think DeepMind helping solve
all of these scientific problemsis like a very real potential
(46:40):
positive outcome for the world. And I don't know if you saw
this, but sort of folks at Google, we just got our third
Nobel Prize in in two years, which is awesome.
So like Google really was this like home of frontier science
that's taking place. Demas and John John John Jumper
won last year and then we just won one for a bunch of the, the
guy who runs our, our, the Google AI quantum lab.
(47:02):
And so there's like so much frontier science work that's
happening is really exciting. The other angle is
infrastructure. And I think Google builds the
world's best infrastructure. So for me as like somebody who,
if you think about the future, like ultimately dependent on
this AI infrastructure that's being built out, Google is like
well integrated in that world. And we have our TP us, which are
(47:23):
sort of on the frontier of what's possible with, with
computing hardware. And like, I actually have two TP
us behind me, if you can see, which is really fun.
So, yeah, I, I think there's everywhere I look, there's
reasons to be bullish in addition to, you know, Waymo and
all these other experiences. Like it's just, yeah, it's a ton
of fun to be at Google these days.
And I think it's we're just getting started, which is funny
(47:44):
to say given how how great things have gone for Google.
You only realize how early you are decades later, right?
It's easy to feel that you're late at anything, but usually
when you look back on it, you are early, like most of the
time, right? And we're very early.
Is there anything that I should have asked you that you just
find super interesting that people would find helpful before
we go? I'll make one last pitch that AI
(48:06):
dot studio slash build get started vibe coding for free.
If folks have product feedback or questions or need us to build
things for you, let me know. We're we're very much like
building AI Studio in public, which is what I'd love to do.
So you're on the Internet, on e-mail, Twitter, whatever, send
us feedbacks. Had a suggestion suggestions and
Chris thank you for for having me on and for taking the time to
(48:28):
chat. I would love to we got to vibe
code some stuff together and would love.
Feedback, I would love that. And where can we find you,
Logan, if anyone wants to reach out?
Yeah, I'm on Twitter, LinkedIn, Logan Patrick, you can find me,
find me all over the Internet where people are talking about
AI. OK.
Well, thanks, Logan. Thank you.
Hey, guys, If you're still listening to this, it's probably
because you haven't had a chanceto take your Airpods out.
(48:49):
You're still mowing the lawn, you're still driving, what have
you. If you're still here with me, I
would really, really love and appreciate a five star review on
Spotify, Apple, or wherever you get your podcast.
It would mean a lot. If you want to go the extra
mile, share this episode with a friend that might have an
interest in starting a business.It would mean a ton.
Hope you have the best day of your life today.
Popular Podcasts
Stuff You Should Know
If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.
Dateline NBC
Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com
On Purpose with Jay Shetty
I’m Jay Shetty host of On Purpose the worlds #1 Mental Health podcast and I’m so grateful you found us. I started this podcast 5 years ago to invite you into conversations and workshops that are designed to help make you happier, healthier and more healed. I believe that when you (yes you) feel seen, heard and understood you’re able to deal with relationship struggles, work challenges and life’s ups and downs with more ease and grace. I interview experts, celebrities, thought leaders and athletes so that we can grow our mindset, build better habits and uncover a side of them we’ve never seen before. New episodes every Monday and Friday. Your support means the world to me and I don’t take it for granted — click the follow button and leave a review to help us spread the love with On Purpose. I can’t wait for you to listen to your first or 500th episode!