Ep 514: Google’s AI Studio – 5 time-consuming tasks you didn’t know you can automate

Topics Covered in This Episode:

1. Google AI Studio Overview & Hidden Benefits
2. Google AI Studio vs. Google Gemini
3. Google AI Studio: Long Context Window
4. Google AI Studio Video Creation
5. Parsing PDFs with Google AI Studio
6. Multimedia Content Creation via Google AI
7. Learn New Skills with Google AI Stream
8. YouTube Learning Enhancement with Google AI

Keywords:

Google AI Studio, AI automation, time-consuming tasks, interface update, user experience, nontechnical users, structured prompts, Google's API, Gemini models, multimodal tools, AI playground, developer tools, OpenAI comparison, Claude comparison, time saver, advanced settings, thinking models, video creation, VideoGen, VO2 model, AI video generation, PDF parsing, OCR technology, NotebookLM, image generation, multimedia content creation, Gemini advanced, grounded search, screen stream, learning new skills, YouTube learning, video content analysis, visual recognition, AI-driven creativity, AI-generated images, content strategy, percentage calculations, screen interaction, data privacy, cloud billing, AI chatbot, generative AI, personalization, long context window, last seven days data

Podcast Transcript

Jordan Wilson [00:00:17]:
You probably know a lot of Google's AI products and offerings. Right? Maybe you use Google Gemini as a chatbot Like you would ChatGPT. Maybe you use Google Gemini inside, your workspace apps like Google docs and Google sheets, or maybe you use one of my favorite tools from Google powered by Google Gemini, Nopogalem. But there is a legit hidden gem that I think most people don't know about. And that is Google's AI Studio. And I think for a lot of use cases, it actually might be Google's best AI. And I don't think many people know, and most people aren't using it. And there's been a lot of recent updates just in the last few weeks that I think make Google AI Studio even better.

Jordan Wilson [00:01:19]:
Alright. So, we're gonna be going over that today and talking about, inside Google AI Studio, five time consuming tasks that you probably didn't know you could automate. Alright. I'm excited for this one. I hope you are too. If you're new here, what's going on y'all? My name is Jordan Wilson, and I'm the host of Everyday AI. We're a daily livestream podcast and free daily newsletter, helping us all not just learn AI, but how we can leverage it to grow our companies and grow our careers. Is that what you're trying to do? If so, it starts here.

Jordan Wilson [00:01:51]:
This is where you learn with the livestream, with the podcast, but where you leverage it and where you actually put it to work, that's on our website. Number one, on our free email, newsletter that we put out every single day, we're gonna be recapping the highlights, of today's show. So maybe you're driving or walking your dog and you're like, oh, what was that? It's gonna be in the newsletter. But also while you're there, we have more than 500 episodes. We've interviewed hundreds of the world's leading experts on AI across a variety of topics. So no matter what you're trying to learn, our website is where you go and make that happen. It is a free generative AI university. Alright.

Jordan Wilson [00:02:29]:
Normally, most days we go over the AI news. There's actually a ton going on, but, I didn't want this one to turn into too long of a show. Wanted to keep it very factual, you you know, hard hitting. So if you want the AI news, that's gonna be in our newsletter. Alright. Here we go. Let's just jump into well, no. I gotta shout out all my people here at McDonald joining from Chicago.

Jordan Wilson [00:02:50]:
Yeah. We're doing this live y'all. I I I like to say, you know, at everyday AI, we're the realest thing in artificial intelligence. Right? So much of what you see online or listen to or or or watch. Right? It's it's very fabricated. It's very scripted. That's not what we're gonna do here. We're gonna be trying to do a lot of this stuff live.

Jordan Wilson [00:03:07]:
There's gonna be some bugs, I'm sure. So thanks for joining us, McDonald. Kelly joining from Syracuse. Dennis joining on LinkedIn from New York City. Love to see it. Noel joining from Chester, England. Aiden, not too far away from Indiana. Jackie, happy Tuesday.

Jordan Wilson [00:03:27]:
I'll be seeing Jackie tomorrow at DePaul. That'll be fun. Lot of lot of people. Gotta shout out doctor Harvey Castro joining us from, Berlin, Germany. Alright. Well, let's get into the use cases y'all. And and and it is Tuesday. So here's my my my hot take for Tuesday.

Jordan Wilson [00:03:44]:
Google AI Studio is the best AI tool you've probably never heard of. Right? If you're if if you're an avid AI user, right, you're using large language models hours a day, You've probably heard of AI Studio. But if you're more casual, you probably haven't, or you probably at least don't know what it's capable of. You know? I'm curious, livestream audience. We got a ton of people in the house today. How often do you use AI Studio, or have you never used it? I wanna know. I'm also kinda curious because I think most people either haven't heard of it or they don't know what it's capable of. And we're gonna be going over those five, time consuming tasks that we can do, that we can, you know, automate.

Jordan Wilson [00:04:32]:
So, let's start at the top. What the heck is Google AI Studio? Well, number one, it looks a lot cleaner than it did a month ago. Right? So, shout out to the Google team. They really cleaned, cleaned up the, user interface and the user experience. And, well, why am I mentioning the user interface and user experience, for an AI tool? Well, it is more for developers. Right? So, at least initially, Google AI Studio was really made for developers. It's a place where, you know, people who are a little more technical, can go in. They can, you you know, work on some of their code.

Jordan Wilson [00:05:08]:
They can work on, structured prompts. They can work on, you know, how they're using Google's API on the back end. Right? So, you know, let's say that your company is is maybe fine tuning one of Google's models or you're using, their new, you know, Gemma three, which I think is an amazing, small model. Right? So maybe you're using that, you know, on device, on prem, you're fine tuning it, whatever it may be. But, you know, I think Google AI Studio was originally just created, to make developers' lives easier, right, in in the same way that OpenAI has their playground. But the difference is AI Studio is, like, legit, a full fledged working product, and it's for much more than developers. I actually think the everyday nontechnical person such as myself, I'm not super technical. Right? I'm not fine tuning models aside from just testing it out inside of AI Studio.

Jordan Wilson [00:06:02]:
But I think for nontechnical everyday people, there's so much to explore, so much you probably don't know, in Google AI Studio. So, yes, originally kind of set up for AI developers over the last, I'd say, six months, it's really grown into so much more. And I think that there's, a lot of tools and features that a lot of other companies have kind of promised but maybe haven't fully delivered on yet. And, Google AI Studio has delivered. So does anyone is anyone using this? Alright. So Allison says a handful of times. Heather says heard of, haven't used. Angie says barely.

Jordan Wilson [00:06:42]:
Alright. Kelly hasn't used it. Jay hasn't used it. Alright. A lot of people haven't. Noel says just heard of it. Dennis is using it weekly. Alright.

Jordan Wilson [00:06:50]:
So some of you are using it. Some of you have never heard of it. So buckle up. We're gonna we're gonna go into it. But at its core, originally, kind of made to help developers, make better apps with Google's API. Right? Because there's so many, tools and services out there. Tens of thousands that you use that are powered by, you know, either Google Gemini on the back end, OpenAI, Claude, etcetera. Right? So developers usually have kind of like a sandbox or a playground that they can go experiment and make their products better before releasing it to us all in the world.

Jordan Wilson [00:07:24]:
Right? So think of those, you know, all these AI tools, you're like, wow. How do they work? Well, generally, they're running on, you know, Google, OpenAI, or Claude, and developers need a spot to go and play around with it and make it better. And that's why, you know, talking about the UI, UX, there's a lot more. Right? So if you just log on to gemini.google.com, it's an AI chatbot. Right? You're just chatting with Google Gemini. You can still select your model, but for the most part, you don't have a lot of controls. Inside Google's AI Studio, there's a lot of controls. So you can control the temperature, change your model, toggle certain tools on or off for structured output code execution, function calling to bring in, kind of third party APIs, grounding with Google search, which is new and amazing.

Jordan Wilson [00:08:09]:
My gosh. It is actually it got the, the the top spot on the LMA Marina board for Internet connected search inside Google AI Studio. It's so good. Okay? So that's kind of a a a the the gist of it. And here's the other thing. It's free. Yeah. It's free.

Jordan Wilson [00:08:26]:
Some more updates here, but let me put out, kind of, let me read first what Google says about this, kind of unpaid services versus paid services because there's an update here that I think people are gonna like. Because previously, you know, Google AI Studio, it just anything that you put in there, it used that information to train its models. Right? So and that is still the case for, free. So if you are on a free Gemini account, this is what Google says and how they use your data. So it says when you use unpaid services, including, for example, Google AI Studio and the unpaid quota on on Gemini API, Google uses the content you submit to the services and any generated responses to provide, improve, and develop Google products and services and machine learning technologies. Alright. So if you are on a free, Google plan, you probably shouldn't be uploading confidential proprietary, data from your company, because Google, if you are on the free plan, it does use that to train its model inside AI Studio. However, and this was, just updated, I believe, in April.

Jordan Wilson [00:09:35]:
So just like this month, this was updated. So now if you are paying for Google Gemini and you have a cloud billing account set up, not technically, you know, it's not hard. Took me, like, thirty seconds when I originally set up, you you know, this, I don't know, a year or so ago. But here's what it says now. So it says now when you use paid services, including, for example, the paid quota of the Gemini API, Google doesn't use your prompt or responses to improve our products. So that's an update. I don't even know if Google really announced this, and I didn't really see anyone talking about this. But y'all, I always do my homework before I do these shows.

Jordan Wilson [00:10:13]:
I don't just randomly jump into something. I I care about, data privacy, security, how, you you know, hallucinations, truthfulness, how the model works. Right? So, good thing Google updated this. So if you're on a paid plan and you set up that cloud billing, Google's AI Studio does not use anything that you input, to train its model. If you're on the free plan, it does. But, y'all, let me be honest. So much of the information that you're probably gonna put into any chatbot, it's already on the Internet. It's already public information.

Jordan Wilson [00:10:40]:
Right? Let's just put that out there. Alright. A lot of people don't understand how much of, you know, your company's data is already, in large language models. If it's been posted on the Internet ever before, it's in the models. Alright. So if you are brand new and feel free to livestream audience to follow along as we go, the first time you go into Google's AI Studio, you're gonna get an option. Okay? And just just so you know, it is a iStudio.google.com. Okay? So it's gonna say it's time to build, and you can either use Google AI Studio and click that try Gemini.

Jordan Wilson [00:11:16]:
So, yes, it is Gemini inside of AI Studio, or you can do, build with Gemini API. So if you do, want to, you know, you can actually use Google's API key, which a lot of people didn't know you could do. So you can, you know, try it out that way. Alright. A couple housekeeping things to keep in mind. One, if you go up to settings, you know, you can do light mode, dark mode. But, yeah, like I said, the user interface used to be a lot more geared toward highly technical people. Now it's easy to, follow.

Jordan Wilson [00:11:46]:
It's it's so much cleaner now, but you're gonna wanna turn on the auto save option. So go up to your settings, toggle that auto save on. Otherwise, by default, Google's AI Studio does not save your chats. Okay. Now let's go into, use case number one, long context window. Alright. Here's where we're gonna get, a little tricky, and apologies y'all, for, probably jumping around a lot of, a lot of tabs here. So what what I have, is I went through, and I'm gonna share this with our livestream audience, podcast audience.

Jordan Wilson [00:12:25]:
This is one of those you might, you might want to, watch the video on this. So if you're listening, on the podcast, we always, leave a link. You can go watch this video, whether it's on, YouTube, LinkedIn, whatever. Okay? So I pulled about 50 episodes transcripts. Alright? So from our AI news that matters. Alright. It is nearly a 400 page document. Alright.

Jordan Wilson [00:12:55]:
So I'm gonna copy this right here. Alright. It might literally crash my computer just from copying so much information. So why does long context window matter, and why is that my number one, use case for Google's AI Studio? Well, you'll see here even with, OpenAI's new o3 model, it can't handle this much context. Right? So, I'm telling it to at the very top of this prompt, I am saying, please carefully analyze this content and find 10 underlying trends that indicate, trends from AI companies, large language models, generated AI, etcetera. So, again, I have the transcript of our AI news that matters, shows. I think there's probably, like, 50 episode transcripts. So that's about forty hours of transcripts content.

Jordan Wilson [00:13:43]:
So if I go into, OpenAI's new model, their o3 model, I love it. I think it's one of the most, capable models in the world. I think Gemini 2.5 Pro is probably a little more, useful right now, but I think o3 is probably more capable. And I did full shows on each of those in the last two weeks, but I can't even put this full, context in here, even with the extended context window of, Chatt GPT's o3 model. Right? You might be saying, oh, okay, Jordan. What about Claude? Claude has a long context model. Can't handle this. Can't handle this.

Jordan Wilson [00:14:18]:
So you'll see from a context, this is 250,000 tokens. Alright? So more than a quarter million tokens. It's a lot of information, right, on nearly 400 pages of transcripts. So Claude can't handle it. It says it's 40 over the leg length limit, so I can't do anything. Even Google Gemini, right, on their front end. Because this is one of those reasons you might be thinking, okay. Well, why would I ever use AI Studio? Can't I just use all the features and functionality inside Google's front end chatbot at gemini, .google.com.

Jordan Wilson [00:14:51]:
Well, no. Here's one use case already. I can't paste in all that information, into, into Google Gemini. It just cuts it off. But I can, obviously, in, Google's AI Studio. Alright. So, let's see let's see if I can do this live. If not, I do I do have a screenshot, but let's see.

Jordan Wilson [00:15:13]:
Alright. So I am going to copy and paste literally 400, 400 pages worth of context. So now I am in Google AI Studio. I'm not gonna go over the entire interface now because we're gonna be doing some of these things later. So I'm going to choose just so it's a little faster. I'm gonna choose Gemini 2.5 flash preview, which was just released about twelve days ago. So you do have on the right hand side, you have these different models that you can choose from. And the good thing I love about this inside Google's AI Studio, it gives you so if you are a developer and you wanna care, oh, how much might this cost if I put something like this out into production, for each model, you can just hover, and it gives you, you know, thinking input tokens, non thinking input tokens, what it's best for, use cases, the knowledge cutoff.

Jordan Wilson [00:16:07]:
I wish every single model had this. Alright. So I'm just gonna go to Gemini 2.5 flash flash preview. I'm literally just pasting in, 400 pages of content. Alright. I'm gonna scroll to the top. So, again, all I'm saying here at the top is please carefully analyze this content and find 10 underlying trends that indicate trends from AI companies, large language models, generative AI, etcetera. So I wanna know, essentially, over the last eight months, everything that's been happening in the world of AI news, what are the trends? I might know some of these things.

Jordan Wilson [00:16:37]:
I might not. And I am using, Gemini 2.5 flash preview, which is a thinking model. But I did use the flash version, which is the smaller version versus the pro because I'm guessing the pro one would have taken longer. And my gosh, this is done. That was, like, no time at all. Twenty six seconds. It went through and it used reasoning. My gosh, if you're listening on the podcast, this is one of those ones where I'm just like smiling and I'm like, I can't believe this technology exists.

Jordan Wilson [00:17:10]:
Number one, I can't believe this technology is free. Insane. My gosh. Okay. So and it did find, 10 different trends. I'm just gonna read, just the the the headings, but it gave me, it gave me details. Right? And the crazy thing is people are always like, oh, Jordan, how do you remember so much on AI? Well, number one, I forget a lot. Right? I forgot most of this stuff even though it came from my lips.

Jordan Wilson [00:17:34]:
Right? But so many of these things were back in, like, eight months ago. So I forget things. I use Google AI Studio every single day to remember and recall information. So let's just, for fun, go over the 10 trends. Number one, escalating competition in rapid model responses, and it's some very good, details there. Number two, the rise of agentic AI and task automation. Again, we're we're looking at October 2024 through April 2025. So, yeah, back in, you know, October, there really wasn't a lot of talk on agentic AI or even task automation inside large language models.

Jordan Wilson [00:18:11]:
Now there is. Number three, advancement in specialization in multimodal AI. Four, heavy investment in innovation in AI hardware and infrastructure. Five, diversification and experimentation with pricing in business models. That's a good one. Right? Talking about, like, as an example, OpenAI's pro tiers. Anthropic just came out with some new tiers. So, yeah, there's details supporting all of this, as well.

Jordan Wilson [00:18:34]:
Six, increasing strategic partnerships, investments, and acquisitions. Seven, growing focus on AI safety, ethics, and governments, in governance. Eight, rising regulatory scrutiny and geopolitical tensions. That's a huge one. Right? And to be able to know, just over the course of five to six months, here's what's happening there. That's huge. Nine, transformation of user experience and accessibility. And then 10, significant impact on the workforce and industry structure.

Jordan Wilson [00:19:01]:
This is so good. And because I used a thinking model, I can go in inside Google AI Studio and look and see how it went through all of this information. So extremely, impressive. I can go see how the model thinks, see how it planned, and see how it's, identified these 10 different trends. And, yes, it would have been better if I use, Gemini 2.5 Pro, but it probably would have taken another minute or two. And I'm trying to get the, through these different use cases a little quicker. Alright. Yeah.

Jordan Wilson [00:19:35]:
Angie just says, woah. Yeah. I agree. Curtis from YouTube says, those little model cards are so helpful. Yes. I agree. It's I wish number one, I wish that that was also in the front end of Google Gemini, but I wish everyone did that. Right? Those model cards are so so helpful.

Jordan Wilson [00:19:55]:
Right? Especially if you're a beginner. Right? And you go down to, Gemini two point o. Right? Because there's actually some features that are only available in Gemini two point o inside Google AI Studio, not in the newer Gemini 2.5. You have your Gemma models. So extremely, I think, probably still the world's best small language model in Gemma three. But then you can also go and play with some of these preview models, which is the learn l m models. Alright. So that's the number one you'll see already.

Jordan Wilson [00:20:26]:
That's something that no no other platform could take a million tokens, right, in the front end. It just that's that's that's nutty. So think of all the use cases, and I'll tell you what I do for this all the time. So, yes, you can do something very similar in NotebookLM. Right? You you know, dump a bunch of context in there, and and this could fit inside NotebookLM. But one of the reasons is I still like sometimes having flexibility, outside of your grounded information. So as an example and let me just do this quick. Alright.

Jordan Wilson [00:21:00]:
So, alright. We're still on use case number one. But there is this new thing grounding with AI search. So now I can use information that's not in that 400 pages. Right? Whereas on Google's NotebookLM, as powerful as it is and it literally won our twenty twenty four AI tool of the year, but now I can click this new option grounding with Google search. Right? And I can say something like, you you know, based on April, 2025, movements in the AI space, please bullet point, what's new for the above 10 trends. So, like, as an example, if I just wanna see what's happened this month with those 10 trends and to see where they're at in this current day because some of them are reflecting back six months or more, I can, ground this in Google search and then I can go see exactly what it's doing. So now it's just gonna get information, from April, 2025 only, and it can go out and search and use the web.

Jordan Wilson [00:22:03]:
So very cool. Alright. Use case number two, video creation. Alright. I'm gonna try to do this, try to do this live. Let's see how it goes. Alright. So people don't know.

Jordan Wilson [00:22:18]:
You can create videos inside of Google AI Studio. So, one thing I'm technically now starting inside of Gemini advanced because I wanna get a photo first. So I'm going to, unfortunately, I don't think right now inside AI Studio you can, create images, but you can create videos with their new VO two model. So I am in Gemini right now, and I'm saying create an overhead aerial photo, realistic shot on full frame DSLR from above a commercial airplane flying over the Chicago skyline. Alright. So now, I, again, I am in the front end of Gemini. I don't necessarily like this. This isn't what I was going for.

Jordan Wilson [00:23:01]:
It only, it only got the the wing there. I wanted to be able to see, the entire, the entire plane. So I just click the redo. I already did this once. It was actually a really good photo if I'm being honest. But I wanted to be able to see, the, the full airplane overhead. If I didn't if if if I can't get exactly, what I'm looking for, I did, run this once this morning and I'll use that image, but I was trying to see if I could get a nice one. Alright.

Jordan Wilson [00:23:31]:
It did the same thing, but that's fine. So anyways, you know, you can pull this into Google AI Studio. Alright. So now I'm jumping back into Google AI Studio, and I'm going to go on the left hand side. You have this new video gen. Alright. So v o two is so good. Right? I'd still say even though we have some new updates as an example, runway gen four, we've had some very impressive offerings, from some of the, Chinese companies, Cling, as as an example, all the different AI video companies.

Jordan Wilson [00:24:05]:
I still think v o two is ahead. It's ahead of Sora. It's ahead of everyone else. Alright. So, Google FYI, Google is bringing v o two if you have a paid version of Google Gemini. And it's a slow rollout because you'll see right now, on my different I have, you know, four different paid Google accounts. I don't have v o two access inside of Google Gemini right now. So the Google Gemini chatbot, gemini.google.com.

Jordan Wilson [00:24:29]:
But if I go into Google AI Studio, I do have it. So on the left hand side there, you'll see I have VideoGen. Okay? And the good thing is inside, Google's AI Studio, there's a ton more options. So on the right hand side, you have all these different settings. So I can create a 16 by nine video. I can create a vertical video nine by 16, you know, anywhere from five seconds to eight seconds. I can change the frame rate. I can have a a set the resolution or run a negative prompt, which is if something keeps popping up in my AI video generation and I don't want it to, I can write it in the negative prompt box.

Jordan Wilson [00:25:05]:
But the good thing with, Google's AI Studio and using v o two there versus, yeah, you can use it in the more enterprise vertex and get even more options. But the thing I like inside Google AI Studio is you can start with an image, because, unfortunately, if you're using this inside Google Gemini, the last I checked, you aren't able to, start with an image. So this is great. So I uploaded, the previous image that I had, and I have a little, little prompt here, so I'll read it out. So all I'm saying is cinematic panning shot showing the airplane slowly moving from right to left across the Chicago skyline. Alright. And here is the image that I ultimately used. So, I don't know.

Jordan Wilson [00:25:51]:
Live stream audience, does this look does this look like a real image? Right? Google's imagine, Google's imagine three AI photo generator is really, really good. Right? If you look at, like, LM Arena, which, you know, you know, we might as well just do that now because it's gonna be a second for this to generate. But if you look at LM Arena and if you go to, the leaderboards and you go to, let's see, text to image. So this is the different, text to image. Like, imagine three from Google is the top, AI image generator, at least, that they have access to inside this program. Alright. So, let's see here. Hey.

Jordan Wilson [00:26:34]:
This wasn't too bad. Michael said video generating on a live demo. Jordan is brave. Yeah. I know. Right? Alright. But it's it looks like it's already done. Alright.

Jordan Wilson [00:26:43]:
So I'm gonna go ahead, put this full screen. So we have an eight second video here. Live stream audience, let me know how does this look. Again, so we started with the image in, Google Gemini, brought it over to Google AI Studio using the video gen on the left hand side, inside Google, Google AI Studio. And this is all for free. Oh, this is wild. This is wild. Alright.

Jordan Wilson [00:27:03]:
Here we go. Here's the photo, or the video. Not bad. Not bad. So pretty good. There were some some some, like, artifacts right here. There's there's, like, some little blur here. But, again, you can just, you you know, you can just regenerate, you know, and the good thing is is just using natural language.

Jordan Wilson [00:27:27]:
Right? I just said cinematic panning shot showing the airplane slowly moving from right to left across Chicago skylight. So, like, what could you use this for? I mean, my gosh. Your company's marketing is probably still stuck in the nineteen nineties. It's old. It's dry. It's dull. So let's say, as an example, your big annual conference this year is in Chicago. Right? If it is in Chicago, by the way, reach out to me.

Jordan Wilson [00:27:48]:
I'll come I'll come, keynote, your your conference and run a workshop. But, you know, maybe you're trying to put together a nice looking, you you know, landing page, for for your, annual conference, for your big company's annual conference in Chicago. This would be a great, I think, you you know, get this, like, three seconds, video and put that as a as a background, on the website. Right? It's great. You can tell if you're from Chicago. You can tell it's Chicago. Right? For our podcast audience, it looks really cool. I mean, to be able to get a shot like this, right, it you would have to be in another, like, airplane because you can see the entire airplane flying, over the Chicago skyline.

Jordan Wilson [00:28:31]:
So very cool. Right? Is this going to, you know, be in the next Netflix documentary? No. But, again, I essentially just, you know, two shot at this. Right? I took two attempts at it. It's it's really good. It's really good. Yeah. Live stream audience.

Jordan Wilson [00:28:50]:
What do you think of this video? I think it's like in terms of being be like, putting up on your website as a background video, you know, putting it on social media. Right? You could throw it in Canva, something like that. Add some effects, add some words. In terms of you now have this used to take so much time. Right? To get a video like this five years ago would be nearly impossible and extremely expensive. Now in terms of your marketing, your comms, your advertising, using Google's v o two, especially if it's just gonna end up, like, as a smaller something on on your website, social media, etcetera. Again, I don't think you would wanna use this at least right now, right, in a feature film or something like that, but it looks extremely realistic, especially on a smaller screen. If you're only doing a couple of seconds, it's very good.

Jordan Wilson [00:29:40]:
And where this takes your creativity, like, next level. Next level. Yeah. Angie just says, I can't believe it's free. Jay says, actually, an annual oh, Jay, I suck. I know you texted me. I gotta get back to you. Alright.

Jordan Wilson [00:29:54]:
So Sandra says, I'm actually doing it on my computer as we're speaking, and it's super amazing. Yeah. It's it's so so good. I think the physics and the realism, specifically the physics, is what separates v o two from Google ahead of Sora. Sora is great, but it struggles with physics. I think there's some, creative tools inside Sora, from OpenAI that I really like, but it struggles with physics. It struggles with realism. Google VO two crushes it.

Jordan Wilson [00:30:21]:
It is absolutely so good. Yeah. Denny says good for background image that might have an overlay. Exactly. I would put this if I was having a big conference in Chicago, right, and you're selling tickets or whatever it is. You know, you're trying to bring thousands of employees together for whatever. Right? Or just, you know, maybe your your your website needs a refresh. Go go do it like this.

Jordan Wilson [00:30:42]:
Right? It's really good. Alright. So that is use case number two. Let's go to use case number three. I've done this before, but parsing PDFs. Okay? And I know this might sound like a boring one and not super impressive. Alright? But it is, because, again, up until, the most recent line of models from both Google, and from OpenAI, this was something that large language models really struggled with. Right? You know, using a combination of OCR.

Jordan Wilson [00:31:17]:
Alright? So that is, OCR is optical character recognition. So, you know, these models would use a combination of OCR and computer vision, and it wouldn't always work. Alright? So, let's go again. We're doing this live. I did do this one other time, but I want to include this, on today's show because I think it's extremely impressive. Alright? So let's jump over. We're doing this live. We are in Google's AI Studio.

Jordan Wilson [00:31:46]:
Alright. There we go. And all I'm going to say is transcribe this PDF word for word. Alright. And for this one, I am going to go with Gemini 2.5 pro, the most powerful model. Alright? I'm gonna click run, and we'll see how long this takes. And first of all, you might be thinking, okay. Why why might I wanna use this? Alright? How many times have you gotten a super long PDF, and maybe you have to make updates? Or you're like, my gosh.

Jordan Wilson [00:32:17]:
I have to read through this entire thing, and it's it's it's gonna take forever, and maybe I just need a little bit of information out of here. So in this case and a lot of times, different tools struggle reading PDFs. Right? Especially, you you know, I'll show you all an example of of of what, this PDF is going through, and you'll see why this could be extremely helpful. Right? So this is going through, this is kind of our sponsorship opportunities deck. So if you look through this, it's images. Right? Any tool would struggle to read this. I created this in Canva. There's a bunch of images, a lot of this stuff that looks like text isn't even text.

Jordan Wilson [00:33:01]:
Right? It's it's literally a bunch of images. Any program would struggle. So, you know, when companies reach out and they wanna advertise with us, you know, I send them this little deck over. So I wanna pull up this page. So at the bottom, it says trusted by leaders from. Right? So we have, you know, hundreds of, you know, subscribers from big companies like, you know, Google, Amazon, NVIDIA, Microsoft, IBM, Intel, etcetera. So we have their logos, at the bottom of this deck to tell people, yeah, if you wanna reach our audience. We have a lot of, you you know, very reputable people who are building the future of AI, you you know, reading our, platform.

Jordan Wilson [00:33:38]:
Alright. So that's a logo. Okay. So now it's done. Alright. So let's see how long that took. Didn't take long. So, again, you can go in if you're using these thinking models, these reasoning models you can go through.

Jordan Wilson [00:33:52]:
It took fifty three seconds. Alright? And here's the thing. It got it done perfectly perfectly. It got all those stats. It pulled all this information. It pulled all this information from, you know, images that would be very hard for any, OCR or computer vision, to do. Right? So in a lot of these pages, it's just like 10 images and maybe a little bit of text. So right here, it even pulled the logos.

Jordan Wilson [00:34:21]:
These logos are not labeled. Let me repeat that these logos are not labeled. So, you know, as an example, you know, the, Amazon logo, it's just an aid. It's just an a with the little, you know, smiley face. Right? If if you if you know Amazon's logo, you probably do. It literally knows that that's Amazon's logo even though you it the word Amazon isn't on there. So do you see the utility and how this can be a huge time saver? So maybe you have to up update a PDF and you're like, oh my gosh, who has that original file? I'm gonna have to redo all of this. Maybe you need to read information from a PDF and it's a long, you know, 100 page, you know, industry white paper, but you only care about 10% of this.

Jordan Wilson [00:35:03]:
Well, Google AI Studio is a great place to do that. Because when you combine this very large context window with the fact that it is one of the smartest and most capable models in the world, I mean, you have a tool here that is almost unfair. Right? And I'm not even going to get into into the more technical aspects of what you can do, but you can even if you wanted to, you could create, like, a version of Google Gems. Right? Or, you know, if you've used custom GPTs inside of ChatGPT. So I could save, let's let's take that industry white paper example. Let's say every single week, there's a huge industry PDF that comes out. It may be a big part of your job is reading through it, pulling out some of the key insights, and then briefing your team, and maybe only 10% of it pertains to you. Right? It's probably something a lot of you do.

Jordan Wilson [00:35:53]:
But you could essentially go in here. You could create essentially a version of a Google gem. It wouldn't be called that, but you can put in custom instructions. You can also, go in here if, you know, if you wanted to get a little more, technical. You could even, turn on the structured output. So maybe, hey. In each week, there's always a a table or a chart, and maybe there's eight columns, but you only want three of the columns because that's all that matters. You could go in.

Jordan Wilson [00:36:21]:
It's very easy. Right? You could essentially give examples, to Google AI Studio and then create that. And then, you know, it it would save because you can save it with the system prompts and then you can toggle, the the, option on, for structured output. Right? So I can go in here. I can go into this visual editor and I can add a property. So, you know, and then you can export this as what's called the JSON. Alright? I know that sounds a little technical, but essentially, you can, you know, kind of, save different types of prompts and train it on input outputs, but you can just do it in natural language. Alright? What do you guys think about use case two? Richard says, how about had that been written text in a PDF? It it it it would have been done much faster much faster.

Jordan Wilson [00:37:15]:
Yeah. Curtis says it'll even accurately extract text from a PDF that has wonky OCR text in it. Yes. It is so good. Allison says, I pay for Acrobat Pro and still receive this error every time I have I haven't used OCR if there's a single rasterized image. Yes. Exactly. It says, oh, yeah.

Jordan Wilson [00:37:36]:
Acrobat cannot run OCR as the page contains renderable text. And then she says AI Studio just did this successfully in five seconds. Yeah. It's it's it's nutty, y'all. This is so good. Are you guys again, this is free. In fact, this is free, and we're only halfway through our use cases. That was number three.

Jordan Wilson [00:37:53]:
Alright. Number four, multimedia content creation. Okay? So this is one of those. I'm gonna go ahead and jump over, into my screen. Again, podcast audience, we're doing this live if you wanna see. Alright. So for this, for this example, I'm actually going to use an older model. Alright? And I do think and hope, that they're going to update, which models have this capability.

Jordan Wilson [00:38:21]:
So for right now, I'm gonna go to my model selector. I'm gonna go to Gemini two point o, and then I'm going to go to this flash image generation. Alright. So there's actually a lot of things that I wasn't gonna do this, but I saw someone in the comments had asked for it. So I'm I'm just gonna do an example of this. This isn't even one of my use cases, but let me see here. I'm gonna try to give me a second here. Alright.

Jordan Wilson [00:38:47]:
I'm gonna try to upload, an image. Let's see. Give me a second y'all. I know this is, doing these things live. Never fun. Never fun. All right. Let me.

Jordan Wilson [00:39:04]:
Okay. So I'm going to pull in this same photo that we used. Okay? So this new, you know, and it has the word hot on it. Right? If you hover over, this is essentially, you you know, we've we've been hearing a lot about the g p t four o ImageGen. Amazing. Right. So, Gemini two point o Flash, the experimental version, and it has image generation. This isn't my use case, but someone asked for it.

Jordan Wilson [00:39:30]:
So I'm gonna see if I can do it here live on the fly. So I I uploaded that same Google Gemini image of the, the the plane flying over, the Chicago skyline. So let's just say, I'm gonna try this. I'm gonna say, keep everything else the same and turn the, and I'm gonna say, but make the plane bright yellow with the words Jordan air on the side. All right. I don't know if this is where if this will work. Hopefully, it does. But, you know, I've been mentioning on this show with between what it's done already.

Jordan Wilson [00:40:09]:
Alright. It didn't do a great job. It actually added an additional plane. So I I probably should have done, I probably should have done this a little better. I'm gonna say, there should be only one plate. Alright. We'll see if that, if that works. So I've been talking about on the show between, GPT four o ImageGen, between this new thing from Gemini two point o Flash, whatever like, everything that, you know, Canva announced.

Jordan Wilson [00:40:40]:
I think there's gonna be a lot of pressure on, on, Adobe because this is like if you get it right, this is like Photoshop. This saves so so much time. Alright. So so there we go. It did it correctly. It changed the perspective a little bit. It made the plane slightly larger. So let's even say it that took five seconds.

Jordan Wilson [00:41:01]:
I'm gonna say, you know, the plane is too large. Make it more like the original image. Keep the one plane yellow with Jordan air on the side. Alright. If I was taking a little bit more time, I think I could get this really well, but y'all, I can't tell you. Right? I've been using Photoshop since, how old am I? I'm I'm a little old. I've been using Photoshop for twenty twenty three years, almost a quarter century. I've literally wasted thousands of hours, that now you can get a pretty good, job done inside Google's, AI Studio.

Jordan Wilson [00:41:41]:
Alright. So that one didn't work perfectly. It added some fragments of another image. That one was a little complicated, but, go in and play with that. That's not even the use case. Alright? So, I got distracted. So let's get back to the use case, which in this case, it is doing multimedia content creation. So again, I'm inside Google's, AI Studio.

Jordan Wilson [00:42:02]:
On the right hand side, I chose Gemini two point o Flash, and you'll see the big thing here is it has this image in text output. Alright. So all I'm gonna say is, you know, write a blog post on the top five tourist spots in Chicago and create photos for each of them. Alright? That probably just to type that FYI, probably took me twelve seconds. Let's see how quickly, Google Gemini can create this. So, alright. It's at it's oh, let's see. Is it done yet? Not yet.

Jordan Wilson [00:42:34]:
Okay. So you'll see. It's literally writing me a blog post, but it's giving me the top five must see spots in Chicago. But for all of those five in line, it's giving me photos. It is using, imagine, which I'm actually curious if this is using, imagine two or imagine three. My hunch is it's using imagine two, because I've run these exact same prompts inside, Google Gemini with the Imagine three and in the Imagine three interface. And it it's the quality is a little better. So I'm not sure.

Jordan Wilson [00:43:13]:
I'll try to get that verified, but I believe if you're using this, I think it's using Imagine two. But regardless, I mean, y'all look at these photos. Right? The fact that I just, quote, unquote, in twenty three seconds. Right? I have a blog post. Let's say you're you're you're a tourism company and you have a new tour here in Chicago with the five, you know, the five, you know, hottest spots in Chicago for tourism. The blog post is written. The images are there. Right? Are these the most high quality images? Absolutely not.

Jordan Wilson [00:43:46]:
But they're really good. Right? Hey. Another secret here. And and and what do you think? What do you guys think of this? This right here, I don't think any other large language model, any popular one by default anyways can do this. Right? Literally, I just, in theory, quote, unquote, wrote. I would wanna go through human in the loop, spend more time on the front end, spend more time on the back end, but I have a blog post here with five photos that Google Gemini generated. I used to do a lot of, you know, SEO content creation, and I've been doing that on the web probably since I don't know. I mean, I built my first website in the nineties.

Jordan Wilson [00:44:26]:
I was paid to build some of the first websites I did in, what, like, 2010. So I spent a good three, four, five years mainly doing this, blog posts with images for a lot of clients. It just did it in twenty some seconds, and it's really, really good. Alright. Here's here's a little cheat code. Right? Let's say you accidentally go into the wrong mode. So let's say you go into Gemini 2.5 pro and you run this exact same check. Okay? It's obviously not going to output images, But what's really cool because it's a thinking model and it's like, yo, I can't create images.

Jordan Wilson [00:45:07]:
You'll see this, because I I always like to test this. I'm like, okay. What happens if you, you know, ask a model inside, Google AI Studio to do something that it is not capable of? And I can obviously read its, kind of chain of thought, to see how it's processing this. Let's see if it did it. Here we go. So what it does is it's like, I can't generate an image, but it gives you a very detailed prompt. And then I can go into, and then I can go into Google Gemini and just run that prompt. Right? So I just said create an image for, and I copy and pasted, the image description, that it gave me.

Jordan Wilson [00:45:50]:
So Google Gemini 2.5 pro realized, hey. I can't create an image even though you asked me to. So instead, here's, an image description that you could put inside. And and, yeah, this one, again, this photo is much better, than the one that was generated, inside, the multimodal version inside, Gemini, Gemini two flash. So I I do think where I assume it's a better, image generation model. Alright. We got more y'all, but I made a mistake. So I made a mistake.

Jordan Wilson [00:46:32]:
There's actually an extra one that I wanted to do that I think is better than the rest of these. I know there's still a couple between all our different platforms. There's more than a hundred people that are still around. So if you want me to get to the sixth one, just say the word bonus. Alright? Sometimes I like to have fun, see who's, you know, still here paying attention. So if you want me to do the sixth one because actually the sixth one, initially, I said, oh, here's five time consuming tasks. And then this morning when I was going over my show, I'm like, wait. I didn't put the newest and most powerful one in this list.

Jordan Wilson [00:47:06]:
So if you want me to do the sixth one, just type the word bonus. If we get 10 people, I'll do it. If not, maybe I'll share about it in the newsletter. Alright. So just put in the word bonus if I get 10 people. Alright. So here we go for number five. This one might get a little tricky, so I'm sorry.

Jordan Wilson [00:47:21]:
Also, livestream audience, aside from typing in the word bonus, if you want to see this, I'm gonna need some help, on this because I want you all to hear this one. Because number five is learning any new skill via share screen stream. Okay? And this is this is one of those this is one of those that, you know, OpenAI previewed this almost a year ago, and we still don't have it, on desktop. But right now, Google Gemini again for free can see your screen and you can interact with it. Let me repeat that for free Google Gemini's AI Studio can see your screen and you can interact with it. Alright? Yes or no. Be honest y'all. How many of you knew that? How many of you all knew that? Alright.

Jordan Wilson [00:48:15]:
So, I'm gonna get something going here. I hope that you're you can hear it. I I'm gonna have to move my mic. I've done some testing with this, and even when I share, even when I share, the audio, you you can't always hear it. So, number one, live stream audience, can you still hear me? Alright. Because I moved my mic away. Alright. And then I'm gonna go ahead and, stop sharing this, and I'm gonna go over, I'm gonna go over this use case, which I think is amazing.

Jordan Wilson [00:48:52]:
All right. So give me a second. Y'all doing this live. It's dangerous. It's dangerous here. Okay. So let me first describe what I have. Okay? I have a simple spreadsheet from my Google search council data.

Jordan Wilson [00:49:09]:
And of the 10 pages, with the most, clicks, I exported that and put it into a Google Sheet. Okay? And what I wanna know is I wanna know the difference in impressions over the course of the last seven days. Alright? So, did this go up 10%? Did did it go, you know, down 30%, right, in terms of impressions? So these are some stats that I'm pulling in. And so, essentially, what I wanna do is I need to write a formula. Okay? And as much as I love Google Sheets and Excel and everything else, does anyone struggle with formulas? Just me, anyone else? Alright. So now I'm going to go into, Google AI Studio. Alright. So that is the sheet I am going to share.

Jordan Wilson [00:50:00]:
Alright? And hopefully, you can hear this. So you might not be able to. I apologize. I'm cranking my volume all the way up. So here we go. So on the left hand side of the screen, I'm clicking the stream icon. So this, I can just talk to, Gemini live. I can show it my webcam so it can see me, or if I was trying to explain something because this also works on mobile, which is really really cool.

Jordan Wilson [00:50:27]:
Or I can click share screen. So this is what I'm gonna try to do. And again, this is something that, OpenAI demoed, they I think May of twenty twenty four, and we still don't have it on desktop. Alright. So I'm gonna click share screen. Hopefully, you can hear. So I'm clicking share screen and then I have to choose, I have to choose which one we're gonna do. Hey Gemini, can you, hear me?

Google Gemini [00:50:56]:
Yes. I can hear you. How can I help you today? Cool.

Jordan Wilson [00:50:59]:
Can you tell me what's on my screen? On your screen,

Google Gemini [00:51:05]:
I see a Google Sheets spreadsheet titled e d a I last seven. The spreadsheet contains data organized in columns, such as top pages, clicks last seven days, impressions last seven days, and difference. Do you want me to describe any of the data in more detail?

Jordan Wilson [00:51:22]:
No. So I understand the data. So in this column here, h two, I want to, write a formula that shows me the percentage change in this impressions difference, between the, you know, column, e two and f two. So g two gives me the number, but I wanna turn that into a percentage, and I'm not sure the formula that I need to write in h two. So can you tell me the formula?

Google Gemini [00:51:59]:
To calculate the percentage change in cell h two, you can use the formula equals g two e two. After entering the formula, format the cell as a percentage to display the result as a percentage value. Will that work for you?

Jordan Wilson [00:52:14]:
Alright. Yeah. Cool. Give me a second. So I'm gonna highlight, so you just gave me this formula here inside the Google AI Studio chat. So I'm gonna copy that. Give me a second here, and I'm gonna go over, I'm gonna insert it into the formula bar, click enter, and there we go. Okay.

Jordan Wilson [00:52:31]:
Cool. So, now it gave me, like, a fraction. So, that's fine, but I want it to show up as a percentage. How can I change this new column, the h column to a percentage?

Google Gemini [00:52:49]:
I understand that you wanna convert the values in the age column to percentages. To do that, select the entire column by clicking on the column header. Then in the toolbar, find the format menu. Within that menu, there should be an option for number or format as. Choose the percent option from the dropdown menu. This should format all the numbers in column h as percentages. Does that make sense?

Jordan Wilson [00:53:15]:
Cool. Alright. Did did I do that right? Can you look? Is did I get it correct?

Google Gemini [00:53:21]:
Yes. The h column now displays the values as percentages. You did it correctly. Is there anything else I can help you with?

Jordan Wilson [00:53:28]:
Yeah. Maybe just out of curiosity, and if you could be, just very direct and blunt and act as kind of an SEO strategist. So, you know, these are all website pages, from my, my website and some, Google Search Council data. What should be some of the first things if I want to increase, traffic to my website by looking at this, screen? Where do you think my best opportunity is, or what should I go do right now?

Google Gemini [00:54:03]:
From the data, it appears that the web page free ChatGPT versus ChatGPT plus what's the difference, is experiencing a significant decrease in impressions and clicks. To increase traffic, you should investigate why that page is experiencing such a large drop. Could you tell me about any changes you've made to this page recently?

Jordan Wilson [00:54:25]:
Alright. So now what I'm doing is I stopped, I stopped that. That's what do you guys think? Was that was that pretty impressive? Alright. Angie just said mic clone. And the good thing is, which I didn't have this enabled, I could have done grounding with Google search. Right? And then it could have planned that episode, for me. Right? Which is really, really cool. So do you guys understand the magnitude of that? I just gave a simple example.

Jordan Wilson [00:54:59]:
Right? Okay. I would have probably, you know, that that that was a very easy, you know, formula to write. Like, let me be honest. It wouldn't take me that long. But maybe if I was trying to do more something more advanced, probably would have taken me, I don't know, five, ten, fifteen, twenty minutes to go find something. Right? When I can give Google's AI Studio and Google Gemini, access to my screen, I can become an expert in anything, especially with this new option that no one's talking about that you can ground with Google search. Because at the end, it correctly identified, that one of my, articles on my website, which brings in the majority of the traffic, it's losing ground. And the reason why is, well, that article is a little old.

Jordan Wilson [00:55:47]:
So it's, probably about six months old, and there's a lot of things in the new ChatGPT free versus, free versus paid that have changed. So it's losing ground. So if I would have had grounding enabled, I I could have talked with Gemini to help me plan, that, update. It could have looked at that web page, said, okay. Here's some new updates that have happened with ChatGPT that are not in your article yet. So, all of a sudden, if you use this correctly, think of it. Think of, like, you now have the smartest person in the world over your shoulder. You can ask them anything Anything, and they're gonna get it.

Jordan Wilson [00:56:29]:
So, you know, you might be trying to learn a new piece of software. Right? Maybe it's something like I showed you, an Excel sheet. Maybe you're coding something. Maybe you just want feedback on a design. Right? And it's actually really good. So you do need to do a little bit of prompting. Sometimes the, the live talking models are a little verbose. So I always like to tell it to be direct, you know, to never be wishy washy or politically correct.

Jordan Wilson [00:56:53]:
Always, you know, give me hard hitting, and and actionable advice because sometimes and that's all large language models. They might give you a bunch of fluff. So you can still do a little bit of best practice prompt engineering, and really kind of, you you know, give it a role, give it a task, you know, have a conversation with it, iterate, evaluate, etcetera, and you're gonna get great results. But you can literally learn anything. Anything new that you're trying to learn, you can do it. This I don't know why more people aren't talking about this and using it, especially the fact that you can now, combine it with this grounding with Google search. Y'all. Y'all.

Jordan Wilson [00:57:33]:
Angie says, I'm gonna spend all day doing this. McDonald said, I did not know that. Fred, good question. Fred says, can it make the changes you requested to the spreadsheet without you having to do them? So I don't think so. Although, Fred, strangely enough, I I ran this, simulation a couple of times. Now one time, Google Gemini did say, hey. Do you want me to put that formula in there? And I said, yeah. Sure.

Jordan Wilson [00:57:59]:
It didn't do it, but, you know, maybe. Monica said, I I fought with a spreadsheet for hours, last week. So, yeah, maybe now you can go, fight less. Big Bogey says, how is this free? Yeah. Good good stuff. So yeah. Alright. Let's see.

Jordan Wilson [00:58:15]:
Did enough people want the bonus one, or should I end this? Let me see. How many people said bonus? One, two, three, four, five. I don't know. Maybe let's see. All right. Well, at least let me, stop sharing, this screen. Take a drink. We gotta go.

Jordan Wilson [00:58:35]:
Angie Angie says next prime prompt polish with Gemini. Maybe. Alright. I think, I think we got 10. I was trying to count. I won't be I I won't be a Strickler, but okay. Yeah. We got okay.

Jordan Wilson [00:58:51]:
Now that I'm scrolling up, it looks like the word bonus showed up way more than 10 times. Alright. I know it's already been an hour, but let's let's do it. Here's number six in this one. Y'all is even crazier. Alright. I am not kidding. Alright.

Jordan Wilson [00:59:10]:
Let me get my, gosh, where's my, link there. There it is. Okay. Alright. So give me a second. Number six is better YouTube learning. Stick with me here. It's more than you think.

Jordan Wilson [00:59:26]:
Alright. So what I'm going to do. Alright. So I had this video. When was this video? Give me a second. Okay. This video was from seven months ago, so it's a little old. It is a nine minute video, and it's going over, oh, gosh.

Jordan Wilson [00:59:46]:
Looking looking at my hair on this video, I need a haircut right now. Looks like I just got a haircut there. So it's a nine minute video, and the video is Google's NotebookLM, the AI tool you can't ignore. So I think this was my second, video that I did on, NotebookLM. Okay? So all I'm doing here is I'm copying the URL. This is a nine minute video. K? So now I have my screen sharing going on here. Okay? So this is new.

Jordan Wilson [01:00:18]:
This is new. So at least using it in the Gemini 2.5 pro. So, one thing I didn't talk about is, there is this little plus button, if you go over in the middle, by the run button. K. So if I click the plus button inside Google AI Studio, there's different options where I can start with different media. So the other amazing thing, about Google AI Studio, it's multimodal by default, but it can ingest video, but not in the way that you think. And let me show you that and let me prove that. So, again, when you think of this large context window and the fact that Google's AI Studio can technically see this.

Jordan Wilson [01:01:07]:
Let me not exaggerate here. Actually, I'm not gonna say anything. I want you all to see it live first. So I can, click when I click that plus button, I can click my drive, upload file, record audio, camera, YouTube video, sample media. Okay? So all I'm gonna do here is I'm gonna click YouTube. I hope this works. And then a box pops up. It says YouTube video URL.

Jordan Wilson [01:01:27]:
I'm gonna paste it in there. It loads the thumbnail, which these thumbnails are silly, but, someone from NVIDIA told me that, my, my YouTube was lame, and I had to make it better. So, there's a thumbnail, I guess. So all I'm gonna say is, what do we wanna say here? Give me a second. So I'm just gonna type in. So this is a a a video about NotebookLM. So I'm gonna say, bullet point, bullet point the steps on how to use NotebookLM. Okay.

Jordan Wilson [01:02:01]:
And then I'm gonna click run. And you'll see right here, it gives me a token count. So this nine minute video is a 57,000 tokens. So I'm gonna click run prompt. Okay. And, again, I'm using Gemini 2.5 pro. So presumably, this is going to take a little longer. All right.

Jordan Wilson [01:02:21]:
So, Jackie says Google owns YouTube. So this makes sense. Will it work with other video channels? Great question as we wait, Jackie. So yes. You can also just upload a file if you have a video file. Now, as we wait for this, and I'm gonna go ahead and click this and you can see in the chain of thoughts, Gemini 2.5 pro is thinking it's it's going through, it's crunching this video. And it's almost already done. Okay.

Jordan Wilson [01:02:54]:
This is good. Okay. So yeah. It's already done. So it took forty two seconds, and it gave me bullet points on what I talked about in this video. So number one, access NotebookLM. Go to the NotebookLM interface. Create a new notebook.

Jordan Wilson [01:03:10]:
Add your sources. Process the source. Locate audio overview. Generate the conversation. Okay. So pretty cool. So it just broke down a nine minute video, into bullet points. Alright? And I probably get what you're saying like, okay, Jordan.

Jordan Wilson [01:03:25]:
What's the big deal? Why is this changing how we work? Okay. Let me, let me do something else. So I'm typing, describe the person in the video. Because there's so many AI tools that you can throw in a YouTube link and, you know, what it essentially does is it goes through the transcript. Okay? And then it's like, hey. According to the transcript, here's here's what, here's oh, gosh. Hey. At least this.

Jordan Wilson [01:04:02]:
Okay. Alright. That's that's good. So, y'all, look at this. Based on the video, here's a description of the person. Appearance. He is an adult male, appearing to be Caucasian, likely in his thirties or early forties. Ouch, Google.

Jordan Wilson [01:04:20]:
Ouch. Hair. Let's see. Alright. Hair. He has dark brown or black hair. My wife will love that one. We always argue about my my my hair color.

Jordan Wilson [01:04:33]:
I like to pretend that my hair is is brown, but it's probably black. Hey. And at least Google was a little nicer here, and it didn't mention all of my gray hair. But, facial features, clean shaven, attire. Look at this. Attire. He is wearing a dark color, likely black or dark navy, short sleeve polo shirt. The shirt has thin white stripes along the edge of the collar.

Jordan Wilson [01:04:59]:
A small white colored logo appears to be c k, visible on the left side of his chest. Y'all look at this. You can barely even see that. Right? So, apparently, I have a looks like a Calvin Klein polo right there. That little c k is tiny, but do you understand and realize what is going on here? Okay. Think of how this can change the work that you do. Let's say, I don't know, for for for an easy, an easy example. Let's say you work in a factory.

Jordan Wilson [01:05:38]:
Okay? And, you you know, whatever it is you process, let's say you make, these mugs. Okay? I have a glass mug here from, Nespresso. Come like Nespresso. I've I've name dropped you, like, 50 times. Why do I not yet have a lifetime subscription to Nespresso? Right. Anyways, let's say your company makes these Nespresso mugs. Alright? And you have video, that is monitoring, and let's just say it's a thirty minute video. Alright? And a lot of things go wrong during this thirty minutes.

Jordan Wilson [01:06:13]:
Right? You're doing a tour. Some things knock off. One of the pieces of the machine malfunctions. Right? A couple of the glasses come out wrong. Whatever. I'm trying to give you an easy example on something that I saw. Google Gemini can go through and do all of this and say, hey, how many glasses fell off the conveyor belt? Give me the time and then give me a classification on what caused it, to fail. Right? And then remember, you can have these structured outputs, as well as system prompts.

Jordan Wilson [01:06:46]:
So let's say during that thirty minutes, a hundred glasses fell off and, you know, a thousand went through successfully. So, you know, it was a ten percent failure rate. So you could go in there, create a a a system prompt, using structured outputs where it essentially, kicks out, you know, a spreadsheet looking, output that gives you the timestamp, what happens, and it can classify it as well. Was it human error? Was it machine error? Was it, you know, faulty glass? Whatever. You can create those classifications. Google's AI Studio can go in and essentially watch thirty minutes of, you know, let's say, security video you uploaded there. My gosh. Live stream audience is no one's, is no one's mind blown? Anyone else? You know, we just have some people saying, this is crazy.

Jordan Wilson [01:07:48]:
Y'all think of the new possibilities and just how this changes the future of work. Right? A lot of people, if you are in a role where you're observing something all day and you have to report back, you have to classify this information. Y'all. Google AI Studio does that. Right? Can you upload an eight hour file right now? Probably not, but it's getting, it's getting there. Right. So it's even describing my demeanor in this video. It says he appears engaged and expressive as he talks, looking directly toward the camera slash viewer.

Jordan Wilson [01:08:26]:
He smiles and shows enthusiasm while discussing the topic. My gosh, like the fact that this technology is available today, it's available for free and it can completely change the way you do business period. That's a wrap y'all. Alright. Let me quickly recap our six, time consuming tasks that you didn't know you could automate or run inside Google AI Studio. Number one, long context window. Number two, video creation. Number three, parsing information from PDFs.

Jordan Wilson [01:09:09]:
Number four, multimedia content creation. Number five, learning any new skill via screen, share screen stream. And our last bonus one, better YouTube learning and just being able, to literally have a large language model, be eyes for any video and to be able to classify information much more than a transcript. It can see and use a brain. It's wild. That was a wrap, y'all. I hope this was helpful. Alright.

Jordan Wilson [01:09:43]:
But there you have it. If this was helpful, could please share this. Alright. I would appreciate if you share this, if you tag someone that needs to know this. I think Google's AI Studio is getting absolutely slapped on. Like I said, a couple of these updates, I I don't think what I just showed you, the ability to upload, a YouTube video in Gemini 2.5 pro. I I I was using prior models before this. I think that's brand new.

Jordan Wilson [01:10:12]:
Right? And again, it's not like the thousands of other AI tools that do that that just look at the text. They look at the transcript. They look at what was said. They look at the words. No. This can see. It can use its brain, and it can use the Gemini 2.5, pro model. So if this was helpful, please let me know.

Jordan Wilson [01:10:29]:
Repost this. Share someone. Tag someone that needs to know this in the comments y'all. I I'd like to make everyday AI a place where we can learn together, where we can share, but, you know, you gotta do your part too. You gotta share. You gotta give me feedback, on on what's working and what's not. So I appreciate you listening. I know this was a long one.

Jordan Wilson [01:10:45]:
If you're on the podcast, thank you for sticking with us. Like I said, this might be one of those ones where you need to go, click the show notes. Go watch this video. It'll hopefully explain things a little better. So thank you for tuning in. Go to your everydayai.com. If you haven't already, sign up for the free daily newsletter. We're gonna be recapping this one.

Jordan Wilson [01:11:03]:
It's not gonna take you an hour plus to get through, the newsletter. It'll be about seven minutes for you to become the smartest person in AI at your company. Thanks for tuning in. Hope to see you tomorrow in everyday for more everyday AI. Thanks, y'all.