Everything Free You Can Do With Gemini

I tried all the free Google AI things

for you. So, here's the cliffnotes

version to save you the thousands of

hours that I have spent using Google AI

products and I got to say that I'm

genuinely really impressed by what

Google has done in the AI space,

especially since most of their products

have very generous free tiers. So, that

is why in this video I'm going to

challenge myself to show you all of the

free Google AI things and I have to get

on a fight in literally 3 hours. So,

yeah, without further ado, let's get

started. And of course, as per usual,

there will be little assessments

throughout this video to make sure that

you retain all of the information that I

talk about. Okay, let's go. A portion of

this video is sponsored by Warp. All

right, here's a list of all the Google

AI features and products that we're

going to be going over today. Starting

with the Gemini web app, Workspace

integrations, Google AI mode, AI Vids,

Google AI Studio, Notebook Outlet,

Firebase Studio, Opel, and some honory

mentions like Vert.ex Studio, and

YouTube Studio. But before we get

started, I do want to give you a crash

course on Google's ethos surrounding AI

as well as their core family of AI

models because I think if you understand

this, you're going to be able to use

their products and features a lot

better. So, their ethos, well, okay, I'm

going to say like what I think their

ethos is cuz not like I'm their

spokesperson or something, but what I

think their ethos is is two primary

things. The first one is to seamlessly

integrate AI into their existing

products to have a better experience.

And two is to create outstanding

standalone AI products for major nieces

and just like daily life stuff probably

to try to get mass adoption by making

them essentially free. This is a

blueprint that Google has done with many

other product launches before. So it

makes sense. Now let's talk about their

core families of AI models. Starting off

with the Gemini family. So these are

their advanced multi-purpose reasoning

models with different versions that are

optimized for different task like Pro

for complex problem solving, flash for

best price performance balance and

flashlight for fast throughput. These

models are multimodal in their input and

their output. Meaning that they can take

in and output and reason with a lot of

different modalities including text,

image, code, video, and audio. Then

there is the Gemma family. These are the

open source lightweight models that are

designed for efficient execution. It

also allows Google to have a place in

the open-source world. Then there's the

embeddings models. These are models that

are able to convert data including text

and images into vector representations

for these tasks. It gets a little bit

technical but generally used by

researchers and for developers to do

things like complex searches,

classifications clusterings things

like that. The imagine model family is

for text to image generation including

things like generating new images,

editing existing ones or creating

specialized images for different types

of task. And finally, there is the VO

family of models. These are video

generation models where you can input

using text or images or combination of

both to create really cool videos. Now,

how does this relate to the actual

consumer products and features

themselves? All of the Google AI

products and features are built on top

of and in combination with these

families of models. So next time when

there's like news that comes out, it's

like, oh, crazy new model came out. You

will have a better understanding of what

that actually means in terms of your

usage of them. All right, time for our

first little assessment. Please answer

the questions on screen by typing them

into the comments to make sure you are

following along. All right, let's jump

into using the AI products themselves.

Starting off with the Gemini web app. So

this Gemini web app with its chatbot

interface is the most accessible way to

access most of Google's models and

capabilities. I am using the free

version over here. So you can start off

with just directly chatting with a

chatbot. Like what are some fun ways to

celebrate a million subscriber live

stream that are octopus themed? That was

really poor grammar, but I just want to

say thank you so much for a million

subs. Um just thank you so much for

being here. And yeah, when I get back

home I want to do a live stream that is

octopus themed to celebrate. So, okay.

Well, a huge congratulations. Thank you

very much. Okay. So, some interactive

games and activities include Octo

Pictionary, creating a custom list of

octopus or sea themed words and phrases.

Tentacle Tycoon using a pointsbased

system or channel currency. Releasing

the Kraken, uh, Submarine Survival, so a

lot of game themes. That is their

cosplaying and maybe some special

edition merch drops. Cool. You know

what? That sounds like a good idea. So,

let's do it. I'll make a post about it

after filming this video. So, yeah. This

is how you can interact directly with

the chatbot, asking it to come up with

things with you, search different things

for you, and plan different things for

you. Now, let's try out some of the

other AI models. Here, we were using the

2.5 Flash from the Gemini family. And

you can also have access to the 2.5 Pro,

which is for reasoning, math, and code.

Uh, but you do need to upgrade to get

the other more fancy Gemini models. Uh,

since this is the free tier, however,

what is really cool is that you do have

access to the nano banana model for

images. Also under the Gemini family,

you can do things like generate a

picture of a girl wearing octopus merch.

Oh, and that's actually quite cute.

Let's now try now wearing a t-shirt and

standing up.

And you can see that this is pretty

good. What is really impressive about

the Nano Banana model is that it's able

to have character persistence, meaning

that this person um actually looks the

same throughout generating different

images, which is a really big struggle

for previous models. You can also do

things like take an image here. This is

a photo of me and the CEO of YouTube. So

cool, right? So star struck. Um but

there is a lady who is in the back over

here of the image. So, I'm going to say,

"Can you remove the lady

in the back?"

And there you have it. Lady in the back

now removed. Really, really good. What

the heck? I'm just going to show you one

more which I think is cool. You can have

like say an image of yourself and like

an image of Naruto. Paste that in and be

like, "Dress me in Naruto's

outfit." cuz you know I always wanted to

cosplay but I don't know I've just been

too lazy so I guess I can live

vicariously like this. Yay! Look at me

dressed as Naruto. I really think that's

really really good. You also have access

to the canvas which is used for code

generation and for writing things. So

you can try something like create a

small game where a banana is gathering

other fruits.

I don't know. I'm literally coming up

with this on the spot. I have no idea

why I thought of that. So, yeah, it can

actually make code and you end up with a

game. Start game.

Yay.

Yes, there's actually quite a lot of

things that you can do here uh in order

to like change the UI of it and also add

other functionalities as well, but don't

have time to go into too much of this

right now. You also have access,

although limited access to deep

research, which is when you give it a

query, it would go and make a plan and

more deeply actually search up what it

is that you're asking it to generate a

report for you. For example, maybe you

want to know what are the different AI

trends that have the highest return on

investment to learn if I want to become

an AI freelancer and you click enter.

It'll give you a research plan and you

can click start researching. This may

take a little bit of time since it's

researching so many different websites

and so many different sources. So,

expanding the hamburger menu thingy over

here, you can click into explore gems.

Gems are specialized like customized

versions of the Gemini chatbot that is

used for specific task and purposes.

There are some that are already pre-made

by Google like a story book, a chess

champ, brainstormer, career guide. So,

let's like click on story book for

example, and you can write create a

story book

of a sad watermelon. Don't comment on my

examples today. Right. All right. While

it's doing that, looks like the deep

research has come back. So it says

freelancers edge in the AI native

economy, a guide to high return

investment trends and skills. Gives you

an executive summary and different

chapters. Like chapter one is the AI

joint transformation to freelance labor

market, winners and losers. Uh there's

like table of contents as well. So you

have chapter one uh chapter 2 earning

potential, high return investment,

technic specializations, chapter 3 and

chapter 4. So etc etc. There is a lot

over here. You can they have like tables

and like text and a lot of other things.

And also the the great thing is that I

also list all the sources that it has

over here. So you can read through it,

try to understand more, follow up with

it if you want to and always make sure

to check the sources if you're using it

for any other purposes to make sure that

it's not hallucinating. Gemini tends to

be pretty good at not hallucinating. Uh

but still there are times in which it

does hallucinate. So just do double

check your sources. Okay, let's now look

at the story book of a sad watermelon of

Wall-E the watermelon by lonely free.

Wall-ally the watermelon was the saddest

fruit in the whole garden. He sat all

day big and brown and green. Feeling

quite glum, he watched the other fruits

and vegetables. The carrots were always

racing to see who had grown the tallest.

The strawberries were busy turning the

brightest shade of red.

Okay. Etc., etc. Oh, okay. Okay. I think

it meets like a little friend. and and

oh no and then he got eaten.

I guess that made him happy.

I have no idea what's happening over

here. Anyways, that's an example of a

gem. Little pop quiz, put in the

comments. What is the pop out thing that

we have over here that was able to

generate this story book feeling and

sliding effect? Put it in the comments.

I did cover this feature already.

Anyways, you can also make your own gems

like a interesting

ice cream flavors. You are an ice cream

crafter that comes up with the coolest

combinations for ice cream flavors. Make

sure that you give real rationale for

why it makes sense and site your sources

too. Yeah. And now you have your

interesting ice cream flavors gem. And

you can be like, "Make me ice cream

flavor that is very sour."

Yeah. And it says, "Black lime and

passion fruit with a hint of saffron."

Yes. A beautifully pale yellow ice

cream. Generate a picture.

And this is what it would look like.

Wonderful. Okay. So, forgive me, but I'm

going to cheat a tiny little bit. All

right. So, I really want to show you

guys the VO model for generating video,

but it is a paid feature. So, all I'm

going to say is Gemini does usually

offer um like a one month free trial

that you can actually try out so that

you can have access to premium features,

including the VO model. So, yeah, it

counts. All right, cuz I really want to

show you this. The video generation

model is really cool. All right. So,

assuming you're on the one month free

trial, then you would also have access

to creating videos with VO and you can

say something like

create

video with sound of a keyboard hovered

in honey. How many of you guys have seen

the viral AI honey keyboard trend on Tik

Tok? Can listen to it.

ASMR.

Pretty cool, isn't it? Oh, yeah. You can

generate videos now as well, and they're

really good. Okay, going back to free

model. I want to show you guys a Google

Workspace integration. How's my inbox

looking? It is going to connect to

Google Workspace. And then it will say

that your inbox contains a forwarded

email from Hong Kong hikers about a mood

tracker preparation hike and also an

email with facts about octopuses. Show

me the contents of the email of the

octopus facts.

Yeah. So, this is in fact what's drawn

out over here. So, you can do things

like summarizing different emails if you

actually have a lot of emails in your

inbox. Uh, this is something that I

really do a lot. Let me show you my

inbox. This one has 110,266

unread emails.

This one has 15,763

and this one has 29,924.

Put in the comments if you're worse than

me.

So, the workplace integration is pretty

limited on the free version, but if you

do get the paid version, it can also do

things like draft emails for you. And

within the Gmail itself, it has like an

Ask Gemini little button thingy, and it

can do things like write emails for you,

summarize things for you directly on the

app. app. It also works with Google

Sheets where you can ask it to calculate

different formulas for you, write things

for Google Doc, generate slides on

Google Slides. Uh, but this is not

available on the free version. So, just

FYI. But as you can see, just on the web

app alone, there's already so many

things that you have access to on the

free plan. And I'm going to list now a

bunch of other ones. I'm put them on

screen right now. Take a screenshot of

this of all the other really useful

things that you can do using the Gemini

web app. And with that, time for our

next little assessment. Please answer

the questions and put them in the

comments. Gemini and Google AI can help

with research and brainstorming and even

vibe coding apps which is pretty

amazing. But when it comes to building

truly scalable and customized software,

I've been using a new type of dev

environment called Warp. Warp code is

kind of like cloud code times cursor but

with better UX and code editing

abilities. It's an agentic development

environment where in ADE basically it's

like the HQ for your AI project. You can

work alongside your agents, oversee

everything that they're doing and stay

in control. They recently launched Warp

2.0 IO and what it stands out to me is

how natural it feels to collaborate with

these agents in warp. It shows me

exactly what an agent changed. And if I

want something tweaked, I can reprompt

without leaving the Warp terminal. Its

intuitive user experience makes coding

with agents a lot less overwhelming. For

our team of engineers, it's really

helpful to use Warp's environment to

test and build software for our cohorts

and for our clients. Warp is currently

number one on Terminal Bench and 75%

which is top three on Sweetbench

verified and it's already being used by

over 700,000 engineers in places like

Netflix, Slack and Amazon. So if you

want to try it out as well, you can

download it for free and with my code

Tina, you'll get Warp Pro for only a

dollar for your first month. That is a

very good deal. So do check it out at

this link over here, also linked in

description. Thank you so much Warp for

sponsoring this portion of the video.

Now, back to the video

cuz next up, I want to talk about Google

AI mode. So, if you go on just

google.com and you type in something

like takoyaki recipes and click search,

you will get your, you know, takoyaki

recipes. But there is a tab over here

called AI mode. And this is going to

give you a lot more information and

details about takoyaki recipes. And it's

also going to site all the sources. This

is basically Google's reimagination of

Google search integrating with AI. If

you've used Perplexity before, this is a

very similar product. You can continue

the conversation and ask it what is the

simplest recipe possible

in the least amount of time. Yeah. And

it would just go through like all the

searching and things like that uh and

tell you the results here. So a question

that you might be asking right now is

Tina, how is AI search mode different

than if I just directly ask this

question on the Gemini web app and that

is an excellent question. It is true

that there is overlap between the Gemini

chatbot and Google AI mode. But the

difference is that Gemini chatbot is

much more multifunctional and it has

different integrations with other

applications. It also has more

creativity that's involved. While for

Google AI search, it really emphasizes

the search functionality. So everything

that you're getting back is going to be

based upon the actual sources that it's

finding on Google search and then

summarizing everything to give you the

best results possible. It often pulls

directly from the source itself. So

you're much less likely to see

hallucinations. For example, when I was

doing research on the different Google

family of models, I used Google AI mode

because I wanted it pulled directly from

the Google website in order to get the

most accurate information from Google

itself. Google AI mode does have the

ability of searching using images as

well and also has deep search which is

very similar to deep research but again

more search based. I'm going to put on

screen now some use cases and examples

that Google AI search is really useful

to do. So definitely check those out

yourself.

Moving on to our next Google AI products

which is AI Vids. AI Vids is Google's AI

powered video creation app. It allows

you to do things like producing videos

from text prompts, um, editing videos

together, and then reimagining videos

that already exist. Through AI vids,

you'll be using a combination of like

the VO model, the Gemini model, as well

as the imagine models for image

generation. Unfortunately, you are a

little bit limited on the free version

here. Like you can't go and actually

generate like full videos. But some cool

things that you can do is go on

templates and click trip highlights. And

here you can upload some of the photos

and the clips that you have from your

trip. Like for example, I have been in

North America for the past 2 and a half

weeks. I was in San Francisco, then

Vancouver, and then New York. So, I do

have a lot of photos from my trip and

maybe I want to send a trips highlight

video to my mom. So, I'm going to upload

all of these different clips and photos

that I have. Insert all scenes. And

voila, here is a nice little highlight

reel. Here are some editing

functionalities. And when it looks like

that it's ready to go, I'm going to send

it and share it with my mom so she

thinks that I have friends and I have a

life and I'm living a good life. I'm

going to put on screen now some of the

other cool and useful things that you

can do using Google Vids. Now, I'm also

going to put on screen now the next

little assessment. Please answer the

questions and put it into the comments.

Moving on to now I want to say my second

favorite Google AI product which is

Google AI Studio. I'll cover my number

one favorite one in just a little bit.

All right, let's now talk about Google

AI Studio. So, do not be intimidated

that there is a lot that seems to be

going on in Google AI Studio. Um, it's

actually very useful and I will walk you

through it. So, the primary thing is

that Google AI Studio is kind of like

the counterpart to the Gemini web app.

Like you're able to have access to the

things on the Gemini web app and a lot

more as well. You also have a lot more

granularity and control. For example,

say I have like a chat that's going on

over here. You know, you have access to

different models and you can do

something like give me some slogans of

my Venus by trap company.

Run that. Um, and it's going to do the

same thing over here, but you also have

control over things like the

temperature, which allows your response

to have different levels of creativity.

So, the higher the temperature, the more

creative it is. You also have some

advanced settings where you can add like

stop sequences. You can limit the output

length. Uh top P which is like another

way of controlling like what kind of

results that you're going to be getting

as well. So a lot more granularity

that's here. You can also enable Google

Drive which will allow you to save your

responses into Google Drive which is

something that you can't do on the free

plan with the Gemini web app. You also

have stream real time where you can talk

to Gemini live.

>> Hello. How are you doing?

I'm doing well, thank you for asking.

How about you?

>> I'm good. So, I want you to help me out

um because I'm trying to figure out when

is it that I need to leave to the

airport because my flight um is at 2:50

p.m. and it's currently 11:00 a.m.

>> Okay, your flight is at 2:50 p.m. and

it's currently 11:00 a.m. To figure out

when to leave, we need to go. Basically,

I'm right now um I'm in the meat packing

district in New York uh in in New York

City and I got to go to JFK airport.

>> Okay. Traveling from the meat packing

district to JFK airport can vary

depending on traffic, but it usually

takes around an hour to 1.5 hours. So,

yeah, it has the audio functionality and

you can converse with it in real time.

So, you might be like, "Okay, whatever

Tina, it's just like a chatbot like, you

know, audio functionality." But what you

can do is that you can actually share

your screen and have it like direct you

in terms of what's happening. Like right

now you can see the map. Is that

correct?

>> Yes, that's correct. I can see a map on

your screen.

>> What about this area? Like what is this

area over here?

>> That area is Brooklyn, which is one of

the five burrows of New York City. It's

located southeast of Manhattan across

the East River.

>> Okay, cool. So, um, if I wanted I guess

I don't have time to eat, but anyways.

So, yeah. What's really cool here is

that it's actually able to see like

where it is that you're pointing when

you're sharing your screen. You can also

have like video feed and chat with it

like showing it different things as

well. Some of my favorite use cases like

say I'm using Photoshop and I want to

like erase the turtle in the back and I

don't know how to do that. I will ask it

like directly how do I erase the turtle

in the back of this image and stream

real time is going to be able to direct

me like on where I should be clicking on

the screen in order to get the right

things and get rid of the turtle in the

back.

>> Okay. to remove the turtle in the back.

You could use the lasso tool to select

it, then use the contentaware fill

option to fill in the space.

>> So, it's great for for like directions

like that. You can also use stream real

time in order to narrate what's

happening in a video. Like, for example,

if I'm interested in knowing what's

happening in this football game, I don't

know anything about football. I can ask

it to actually narrate what's happening

in the segment of the video. What is

happening in this clip right now?

>> Okay. In the video, the players are

moving around the field and a player in

black is on the ground having just been

tackled. It looks like the player in red

and white has gained possession of the

ball. Also, the score is now Arsenal

zero, West Ham 1.

>> There are some other things that are

here as well. Like if you click on the

generate media tab, you'll notice that

you have access to the models like Nano

Banana, but you also have the imagine

model, speech generation, LIA, real

time, and VO and VO. So, you can do

something like generate a video of

cutting glass.

So, as you can remember, we were not

able to have access to VO on the web app

directly when you're just doing a using

the free version. But on Google AI

Studio with the free version, you have

access to VO and also a lot of other

different models there as well. So, it's

a nice little hack if you want to try

out the models. There's a lot more like

you can build applications. There's the

dashboard. You can try out the different

APIs as well. There's a lot of different

things. And I'm not going to go into

this too much more because I actually

made an entire video on Google AI Studio

where I go into a lot of detail about

all the features that you can do. It

really is amazing and you can check out

the video which I'll link over here. I

also put on screen some of the use cases

I really love when it comes to Google AI

Studio.

Moving on to Notebook LM. Okay, notebook

LM is hands down my favorite Google AI

product. As this tagline says, learn

anything. Notebook LM is for learning

things. And if you've been following my

channel for a while, you know that I

love learning things. The workflow is

super intuitive. You add different

sources um whether from like your drive,

different links, websites and copied

text and then you are able to chat with

the sources and get to understand it

more and then also transform it into

different versions like audio overview

like podcast uh video overviews, mind

maps and different reports as well. So

this is a way for you to dig deeper into

information, combine them together,

synthesize them together and really

transform that information. For example,

say I'm interested in learning about AI

agents. Well, instead of having to like

go through all the sources about AI

agents myself, what I can do is start

adding sources into Notebook LM. Like

for example, this is my own YouTube

videos that I've done. So, I have a

bunch of different YouTube videos on AI

agents. So, you know, I'm going to add

those because I think that they're good

and I don't want to watch them again

because I think that I'm biased, but I

think they're pretty good. So, there's

the AI agents fundamentals. This one is

building AI agents and this other one is

like a practical guide for how to build

an AI agent using NA10 as the tool. I

can also click the discover feature in

order to add more sources to this. So

sources about how to build AI agents um

and how they are used in industry.

Right? So I'm going to find all these

sources and add them in as well. So, I'm

going to add in some sources like how to

build and sell AI agents, what are AI

agents from IBM, building autonomous

agents, blah blah blah from Reddit as

well. And I can decide to add the ones

that I think are good. Like I think most

of these are pretty good. I'm not going

to add some of these because I feel like

they're not as reputable. So, I'll add

like the ones that I like and then I'll

import the different sources over here.

One of my favorite hacks with Notebook

LM is that you can actually also combine

it with deep research. Like for example

like I go on deep research over here and

I ask it generate a report on how AI

agents are being used in industry and

what is worth learning. Let it do its

thing and when it's ready I can go and

copy paste the results from deep

research and add it as a source as well.

So now I have a bunch of different

sources that are here. I can start

asking questions like what are the core

components of AI agents.

It will draw from all that information

from the sources and I can go on and

have conversations and dig deeper into

all the different sources that are

available as well. So this is really

really powerful for digging into it. Uh

these are the core components that um

are part of an AI agent. So AI model

brain blah blah blah like all these

different things and I can go and like

ask him more questions specific to the

the sources here. I can also select

specific sources to be exploring. So,

it's really really powerful to dig into

this and be able to really like learn

from all these sources without having to

like go over through it all of it

yourself. But there's even more than

this that you can do. If you look at the

studio tab over here, there's things

like audio overview that we can generate

a full podcast. There's video overview,

you can generate a mind map, and then

you can also generate reports like a

briefing doc, a study guide, FAQ, or

timeline. These are so amazing because

you're able to transform that

information a different way and interact

it in a different way as well. Like some

people who are audio people like me, I

really like generating podcasts and

interacting it with like that. Um, if

you want to like have this information

and make it into a study guide, you can

click study guide over here and it would

actually like give you a study guide for

how it is that you should go about

learning about AI agents. We can

generate an audio overview as well. And

here is the study guide. So part one is

core concepts of AI agents. uh it goes

through all the information AI agent

architecture and components. So it lists

out all of the different um types of

things. So it's like arranged in a way

that is really conducive for studying

and even adds a little quiz at the end

which of course you know that I'm a very

big fan of quizzes. Uh it really helps

you retain all that information. Also

gives you the answer key as well. And

here's a glossery of key terms as well.

>> Term AI agent just about everywhere

these days. uh boardrooms, tech blogs,

even just casual chats.

>> Yeah, definitely.

>> But what does it really mean? I mean, is

it just a fancier chatbot or is there

something, you know, genuinely bigger

happening here? Something that could

>> pretty cool. Um, you can even interact

directly with it. So, yeah, there's like

a lot going on. I really hope you can

see how powerful Notebook LM is. Um, I

really wish I can go into more of this

right now, but this video is already

really, really, really long. And I do

also have a full video that I've

dedicated to Notebook LM, which I will

link over here. So, please do check it

out. It is literally my favorite Google

AI product. Just like the other

sections, I'm also going to put on

screen out some of the really cool

things that I love using Notebook LM

for. And since we are on the topic of

quizzes, let's now do our next little

quiz/assessment.

Answer all the questions that I have on

screen right now in the comments to make

sure that you're paying attention. All

right,

moving on to one of also my favorite

Google AI products. It's called Firebase

Studio. Firebase Studio is a vibe coding

tool for building apps. It lets you

build and prototype full stack

applications uh for both like mobile and

web apps. I'm so mind-b blown that a

product like Firebase Studio is free.

This is what Firebase Studio looks like.

You can just start prototyping an app

with AI by just typing in what it is

that you wanted to build. like an app

that creates recipes

from photos. You click prototype with

AI.

I'll start it off with a little plan

over here. You can click prototype this

app and it's going to generate the code

for the first version of it. This is a

oneshot prompt and it's able to generate

this and it works just like that. Uh

it's not always going to be like that.

You know, sometimes you need to tweak it

a little bit. There is like a whole art

and science to vibe coding. I've made

like several videos about how exactly to

do vibe coding to produce the apps that

you want to have and doing it properly.

Uh so I'm not going to go into too much

more detail about that either. I'll put

them I'll link them up top and also link

you in the description to all the I've

literally made like at least three

different videos on how to vibe code.

Here's an example of a productivity app

that's inspired by Pokemon. And here is

a language learning app where you can

chat with the AI and it will give you

feedback on your grammar and your

pronunciation and your sentence

structure and your vocab.

>> Hi there. Let's talk about food. What's

on your mind?

>> I like potato. Eating potato.

>> Potatoes are great. Do you have a

favorite way to prepare them?

>> I do have a full video that covers

Firebase Studio and all the details

about it. So do check it out if you're

interested in building apps linked over

here. You can use Firebase Studio even

if you have no idea how to code. But if

you do know how to code, there's also

this IDE view where you can actually go

into the code and add things yourself as

well. I'm going to put on screen now

some of the apps that you can vibe code

using Firebase Studio.

Next up is Opel. Opel is also an AI app

builder that lets you like build, edit,

and share many apps using natural

languages. The experience of using Opal

is pretty different from Firebase Studio

because it is like a visual builder and

you don't actually interact with the

code directly. It's also only available

for beta um in the US only. So, I'm not

sure if all of you guys have access to

it right now, but you should. They're

probably rolling it out to everybody

else as well, so don't worry. So, let me

explain what I mean by it's a visual

builder that's different from Firebase

Studio. So we you can check out some of

the mini apps available in the gallery

like a blog post writer, a book wreck,

business profiler, citybuilder, etc.,

etc. Uh let's say let's click on

learning with YouTube. Let's try this

out as a mini app. So you see that

instead of having the code that's there,

it shows you the workflow itself. So for

this mini app, it's learning with

YouTube, turn your YouTube videos into a

quiz to help you learn. So you can get

started and it tells you to enter the

YouTube video URL. But let's say that

I'm going to put a video here that is my

video about prompt engineering. So it

would go and extract a video transcript

and you can actually see exactly what

it's doing. So it will collect a URL and

it's showing you the flow. It's

extracting the video transcript. Um and

then after that it's going to it's going

to analyze the education content. Then

it's going to generate the quiz and then

finally it's going to display the

report. The final thing that you get

back you can also see the flow that's

happening from the console view too.

like it's calling Gemini 2.5 fashion

now. Now it's generating the quiz and

voila, here you go. It is able to show

you the quiz uh that is based upon this

video and you can test yourself using

this. So this is what is meant by a mini

app. You can of course also build your

own mini apps by clicking create new

generate a blog post and video based on

the topic that the user provides. So you

can see the workflow here is that the

user will enter the topic for the

content and then it will use that

content to generate a blog post and it

will also simultaneously send it over to

generate the video instructions. Then

here the blog post is going to go into

the generate video clip as well as the

generate video instruction is going to

go into general video clips. Combine

everything together to generate the

combined output. So you get the blog and

the clip. And the way that the mini app

looks like is like this. So you can

click start, enter the topic for your

content, how to make chocolate,

and it will generate this blog post as

well as a video clip. You can also click

share app in order to share the app with

other people to use. So yeah, pretty

nifty, right? Um I think actually really

cool. It's like this like product that

you can see it's definitely not as

powerful as Firebase Studio is. It's

limited in the kind of apps I can build,

only like these mini apps, but it is

really nice for people who don't want to

like directly go into building a full

product. also completely free as well,

which is pretty crazy. Those of you who

are based in the US and have the beta uh

available to really recommend that you

check it out. I'm going to put on screen

now some of the mini apps that you can

build yourself using Opal. And also time

for our next little quiz. As you know,

answer these questions and put them into

the comment section. All right, we are

almost done. We've covered a lot in this

video, but there are two other um Google

AI products that I do want to very very

briefly mention as honorable mentions.

I'm not going to cover them fully

because they are a little bit niche, but

I personally think they are really,

really powerful. The first one is the

Vert.ex AI platform. It contains a lot

of things that you can do, including

Vert.ex AI Studio, which is kind of like

the developer version of Google AI

Studio, and there's also agent builder

where you can build out agents as well.

So, Vertex AI is really, really

powerful. There's a lot of things that

you can access through here, but it is a

developer tool. So, you do need to know

how to code to be able to use it

properly. But if you do know how to

code, um it is extremely powerful and I

highly recommend that you check it out.

And the final honorable mention I want

to tell you guys about is in fact

YouTube Studio. So as a creator, I spend

massive amounts of time on YouTube

Studio. Uh and originally I wasn't

actually going to add this into this

video. It just so happens that I am in

New York right now to attend Made on

YouTube, which is a YouTube event. Uh

they get a lot of creators and press to

come in and tell and they told us all

about the new AI features that they're

developing for creators. and it is

pretty cool. So, it's not available even

like to me right now, but they did show

some demos. Some of the things that

really stood out to me include being

able to use the VO video models directly

through YouTube Studio to generate

YouTube shorts. Gemini is also going to

be integrated into YouTube Studio so

that you're able to look at the metrics

and the data directly through natural

language as opposed to going through the

data itself. Uh, for me personally, I

love going through the data. I was a

data scientist, but I do know that for a

lot of other creators, they don't really

like digging into the numbers. So, this

will be um really really useful for them

in order to analyze their YouTube

channel. It would also help you come up

with better videos based upon comments

that are being generated, for example.

So, overall really, really powerful tool

for creators. So, yeah. Oh my gosh.

Thank you so much for uh watching this

entire video. And I have like 5 minutes

to finish packing everything before I go

on my flight where I'm going to be late.

Fingers crossed. Ask me in the comments

if I actually managed to make it on this

flight. But here, here, here's this

final little assessment. Please answer

these questions and put it into the

comments. All right, and I will see you

guys in the next video or live stream.

Wish me luck.