Ep 652: NotebookLM: 8 New Updates for November that you should be using

Topics Covered in This Episode:

1. NotebookLM Eight November Updates Overview
2. Custom Prompt Viewing for Deep Dive Reports
3. Chat History Defaults On in NotebookLM
4. Goal-Based Chat Customization for Users
5. Enhanced Privacy Controls in Shared Notebooks
6. Google Sheets Import in NotebookLM
7. Gemini 1,000,000 Token Context Window Integration
8. Mobile App Quizzes and Flashcards Release
9. Nano Banana AI Visuals in Video Overviews
10. Practical Use Cases for New NotebookLM Features

Keywords:

notebook lm, NotebookLM updates, Google NotebookLM, Gemini 2.5, AI grounding, custom prompt, deep dive reports, chat history, goal based customization, privacy controls, Google Sheets integration, context window, 1,000,000 token context, mobile app updates, quizzes and flashcards, nano banana visuals, video overview, mind maps, AI reports, AI-powered audio overview, dynamic templates, learning guide conversational style, Google Drive search, source discovery, custom reports, multimodal AI features, artifact generation, infographic feature, slides generation, multi-turn conversation, ChatGPT comparison, AI chatbot, team collaboration, executive assistant AI, sales deal AI, product manager interview analysis, proposal customization, secure sandbox environment, model agnostic platform, Aria platform, API integration, personalized AI, deep research integration, AI for education, Ceo board packet AI, SME onboarding AI, marketing team customization, user interview analysis, mobile flashcard generation, visual learning AI, AI image generation, nano banana image model, Claude, Copilot, Large Language Model updates, real-world AI use cases, AI privacy, admin workspace settings, AI hallucination prevention, team privacy enhancement, artifact creation AI

Podcast Transcript

 Jordan Wilson [00:00:14]:
I talk to hundreds of enterprise leaders a year, and do you know what kills most AI projects? Teams can't experiment without IT freaking out about production risks. That's where Aria comes in. They built a secure sandbox environment where your teams can prototype, test different models, and even run AB tests between agents all before anything touches production. Drag and drop interface works with any AI model you choose, and when you're ready, you move to production on the same platform. So check out today's show notes or see our website for a free trial of Aria. Go to airia.com because innovation needs a safe place to fail fast. Google's notebook l m has quietly turned into a legit juggernaut. Yes.

Jordan Wilson [00:01:04]:
It was a viral and fun tool in 2024 when Google rolled out the deep dive audio overview podcast feature. But notebook LM has actually been one of Google's most updated platforms over the past year. And, yeah, they obviously have dozens. And I think that these newest features that we're gonna be going over today are starting to push notebook l m over the edge from personal productivity second brain to absolute necessity for growing teams. So on today's shows, we're bringing you the eight new notebook l m updates from November that you should be using. Alright. I'm excited for today's show. I hope you are too.

Jordan Wilson [00:01:46]:
Let's get into it. Welcome to Everyday AI. My name is Jordan Wilson. I'm the host, and while we do this thing for you, you actually voted for this episode, not me. But everyday AI, if you're new here, this is a daily live stream podcast and free daily newsletter helping everyday business leaders like you and me, not just keep up with what's happening in the world of AI, but how we can use all this to grow our companies and our careers. So, if you are new here, starts here with the unedited, unscripted livestream podcast. But take it to the next level. Our website is where it's at, youreverydayai.com.

Jordan Wilson [00:02:18]:
We're gonna be highlighting the, main points from today's episode as well as all of the other AI news that you need to know to be the smartest person in your company when it comes to AI. So let's get straight to it. Here's what we're gonna go over on today's show. We're gonna quickly recap the eight notebook l m features from, well, late October and early November that you need to be paying attention to. I'm gonna show you a demo of some of our newest or some of the newest features that I'm really personally enjoying. And then at the very end, I'm gonna share five new notebook l m use cases that weren't even possible before. So whether you're a student or sit in the C suite, there's gonna be some use cases that are now available that weren't previously. Alright.

Jordan Wilson [00:03:04]:
So, let me start here. You need to repost this show. I'm just gonna say this y'all. If you didn't get our everyday AI notebook l m cookbook the last time, you missed out. The people that I shared this with, they were like, wait. This is absolutely changing how I do work. So, if you are listening on the podcast, check the show notes. We always put a link to the LinkedIn live stream.

Jordan Wilson [00:03:27]:
So go repost today's show on LinkedIn, and I will share with you the everyday AI notebook LM cookbook. It is literally the complete guide. I don't know probably many people in the world who spend more time on notebook LM aside from me. I'm constantly chatting with the Google team, with with feedback suggestions going back and forth. I use it all the time, and this is the one thing that is gonna help you get started. We're not gonna do a basic overview today of notebook LM, but you're just gonna wanna go repost that show. Let's get straight to the eight updates. Alright.

Jordan Wilson [00:04:01]:
Number eight, the ability to view the custom prompt for deep dive reports anything custom. Number seven, chat history on by default. That's big. Number six, having goal based customization available to all users where you can set a specific goal, voice, or role for the chat. Then we have number five, privacy controls. This is great for team, for teams. Chat history can be deleted And in shared notebooks, the chat view is only visible to each individual user. Number four, you can import Google Sheets inside of notebook l m.

Jordan Wilson [00:04:38]:
This is what I've been asking for for a long time, so I'm glad the team finally made this available. Number three, NotebookLM now uses Gemini's full 1,000,000 token context. That is big. Right? Number two, the mobile app got a ton of new updates that just finished rolling out to a 100% of new users yesterday. So these are hot off the presses. So quizzes and flashcards are available on mobile. That's big. And then last but not least, Nano Banana.

Jordan Wilson [00:05:09]:
The visuals are here, in the video overview. So we're gonna be going over those six a little bit more talking about what they mean, how they work, all that good stuff, but this is Wednesday. Our Wednesday show is putting AI to work on Wednesday. So, I'm gonna be going over some practical use cases at the very end of the show, but, also, I'm gonna talk a little bit more about each of these features. And this fall has been a straight up whirlwind for notebook l m. So let me just say this. Maybe if you just use it, I don't know, once or twice a month or maybe you haven't used notebook l m in six months, you need to go back and use it. So aside from the eight features that I just talked about, there's actually October and September.

Jordan Wilson [00:05:57]:
We did dedicated shows because there were so many good ones. So I'm just gonna bullet point some of the highlights. So last month, the ability to customize chat responses and set the tone or style. There's also a new learning guide conversational style that asks users clarifying questions and kind of test your understanding. There's a new feature to discover sources via Google Drive search. And we went over those and more in episode six twenty seven, and then there's the updates from September. So there we saw custom reports, which was a huge one, right? So you can set this structure, tone and language. There's different dynamic templates.

Jordan Wilson [00:06:37]:
So, yeah, reports are a big part of notebook l m. Flash it, sorry, flash cards and quizzes debuted in September on desktop. And like I said, as of yesterday, they're now a 100% rolled out to mobile as well. That's great. You can, kind of, you know, generate these great quizzes to kind of drill yourself with feedback, from your sources. And then the audio overview new formats, which are great. So up until September, there was only the deep dive. Now there's the brief, the critique, and the debate, and also customizable length and tone for the, standard deep dive.

Jordan Wilson [00:07:14]:
So, yeah, all the, the AI, podcast that, you know, went super, super viral. Now more than a year ago, now there's a lot different formats as well as customization for the deep dive, kind of the OG of the, notebook l m audio overviews. Alright. And we went over those updates in 06/2008. So if you wanna know more about that, especially the reports, so much new and so much, so many new capabilities from being honest that are possible now, with the custom reports that weren't, possible before. Alright. So let's look live. Like I said, if you're new here, most Wednesdays, we do what's called putting AI to work at Wednesday, which is usually going over a new update or feature or a new mode, right, from either, ChatGPT, Google, Microsoft Copilot, or Claude.

Jordan Wilson [00:08:07]:
We kinda stick to the big four. Every once in a while, we'll venture off and do one other thing. But on Wednesdays, it is practical getting to work hands on doing demos. So, things go wrong in demos sometimes, just FYI. So I'm gonna be sharing my screen here in a second, but I do want to tell people if you are absolutely brand new, to notebook l m, make sure you actually go go watch our last episode because we also did a complete walk through. So, episode six twenty seven, we did a complete walk through. I'm not gonna do that today. But what I will tell you, maybe you're a first time notebook l m user.

Jordan Wilson [00:08:43]:
You might be saying like, okay. What's the big deal aside from this audio overview thing? One word, grounding. Okay? So, right now, I'm sharing in live stream audience. If you could let me know. If you can, see my screen, that would be great. But what I'm sharing right now is a notebook that I used. So for, the show on, Tuesday, yesterday, our hot take Tuesday show, I put together a notebook LM notebook as I do for almost all of my episodes. It helps me better prep, helps me better prep, prepare, get my notes together.

Jordan Wilson [00:09:17]:
Right? Just a way for me to interact and and learn a little bit better. But grounding, here's what's very important. Right? So, right now, this is about the show from yesterday. The Apple, partnering with Google. And by partnering, paying them a billion dollars to use their AI. Right? So I have all these sources here on the left hand side all about Apple and Google's partnership. Right? So if I go ask, this, notebook l m in the middle, and I say, you know, tell me about five features of JetGPT, and I hit enter. What's probably gonna happen, here as I give it a second to respond, it's looking through all my sources on the left hand side that I add, individually.

Jordan Wilson [00:10:06]:
Okay. This maybe wasn't the best example because there's actually, some some, in those sources, it's comparing, Gemini and Chad GPT on a couple of things. So not the best example. Let me do this. Let me say, you know, when was the last time the Cubs won the World Series? Alright. So now it's gonna come back and probably say, yo, can't help you with that. There we go. So it says the sources provided focus exclusively on the reported partnership between Apple and Google.

Jordan Wilson [00:10:39]:
So this is an example, the world's simplest and most basic example of what grounding is. Right? So it's always notebook l m is going to ground its answers in my sources. So when you go and start a new notebook, you can't even talk with notebook l m. And notebook l m is powered, by Gemini 2.5. Alright. So you you don't get the full right features, benefits, but also sometimes downsides of Gemini 2.5. Right? Hallucinations. Hallucinations happen in every single large language model.

Jordan Wilson [00:11:12]:
They are very, very less likely inside of notebook l m because it grounds everything in your sources. Right? Hallucinations can still happen, but, right, that's the big benefit. And I I always like to start there whenever I'm going over notebook l m because it is unique in that way. There are some ways that you can get some grounding capabilities now in Google Gemini, especially on the business side, ChatGPT on their business plan. But for the most part, it's not always that easy and you have to really know what you're doing. By default, notebook l m only works with what you give it. So, you know, when you do add a source, you can do that in the upper left hand corner. So you can add, you can upload files, you can upload, you know, your company's PDF documents, your SOPs.

Jordan Wilson [00:11:57]:
You can upload, you know, call recordings, m p threes, documents. Right? You can also connect Google workspace files. You can bring in website pages directly, YouTube videos, or just copy and paste text. Right? So you are essentially building the foundation, for notebook l m. And this is why you create many different notebooks. Right? Whereas, you know, in Chat GPT or Gemini or Claude or Copilot or whatever, you create new chats, but it's using essentially the same knowledge. It's the training data. It, you know, it goes off and it queries the web and sometimes that can be a bad thing.

Jordan Wilson [00:12:32]:
Alright. So let's go over some of the new features from November. One that I didn't even mention, very small one, but I really like it. So all of the panels are, resizable. So in notebook l m, if you're listening on the podcast, this might be one of those. Go watch the video version on our website, youreverydayai.com. Alright. So the cool the good thing I like, the the panels have always been collapsible, but now they're resizable, which is really nice.

Jordan Wilson [00:13:04]:
So small quality of life thing, but you can drag the sources panel on the left, and then the studio panel on the right. And then in theory, when you do that, it also changes the middle panel, which is the chat panel. And that is where you talk with notebook l m. Alright? So you have your sources on the left, your chat panel in the middle where you are chatting with notebook l m powered by Gemini 2.5. And then on the right hand side, you have your studio. That's where you create your audio overview, video overview, mind maps, reports, flashcards, quizzes, and more things coming soon. Alright. So let's go over a couple of the new things.

Jordan Wilson [00:13:40]:
One is just the, ability to resize columns, something simple. One I've been loving since it dropped, the ability to add in spreadsheets. Alright. So, to do that, very simple. In sources, you just go to add, then you select Google Drive. Alright. And then I'll just go click this. This is a spreadsheet that I have just for YouTube stats.

Jordan Wilson [00:14:06]:
I click enter and it brings it in automatically. And then the great thing is with any source, but it also works with spreadsheets, which is really nice. I can click it. It's gonna automatically resize it a little bit and I can actually see it converts it to kinda like plain text here. So I can make sure and understand that it brought everything in correctly. The columns, and the rows are all matched up. I can see it right within notebook l m. So it's not like you, you know, are gonna enter in, you know, 50, a 100 spreadsheets and then be like, okay.

Jordan Wilson [00:14:35]:
Hopefully, it's reading it right. Hope right. Because large language models can get things wrong. So you can actually click on the spreadsheet and see that it brought in everything correctly. Alright. So that is one of the new features for November. The other one is being able to set the goals. So how you do that is in the middle column.

Jordan Wilson [00:14:52]:
You go to the chat column and then there is the, configure notebook option. So in the middle, it's kind of the, the toggle or the option slider. And where that is now, you'll see it says notebooks can be customized to help you achieve different goals. I can click custom right there, and then, you know, give it a goal or say, hey. My goal in this notebook is to a b c. Then I can also tell it how I want to, respond as well as set the, response length. Alright. Another one here, is the which is great for me.

Jordan Wilson [00:15:26]:
Being able to view the custom prompts. So let me tell you what I mean. So as an example, if I wanna create a report, I can click on report and then I can click create your own, and I can create a great report. So let's just say as an example, think with me here. Let's say you work in HR and you have a bunch of onboarding documents. Right? Like 20 onboarding documents, hundreds of pages. You can go in and create a custom report for maybe marketing team in North America. Right? And it turned out really, really well.

Jordan Wilson [00:15:55]:
Oh, but then the marketing team in Europe, they want something, but there's some different things. Right? There's some privacy rules, that are different. You know, the team reporting structure is a little different. You're like, oh, what did I use for that prompt to get the one? Well, before you were kinda screwed unless you've saved it. But now it's very easy. So both in anything that you're using a custom prompt in, whether that's reports, you can do it in quizzes. You can do it in flashcards. You can do it in audio overview or video overview.

Jordan Wilson [00:16:28]:
So now on the right hand side, if you, so on the studio at the bottom, you'll see every single every single, kind of, piece of media that you've created. So as an example, this was a podcast that I created with my source material before I did my podcast. Right? So I can go here and click the three dots on the right hand corner and then click view custom prompt. So this is huge, especially if you have a notebook that you go back to often. If you're using notebook LM to create educational resources for your team, or even if you're like, oh, wow. You know, I remember creating, you know, an audio overview a couple of weeks ago that worked really well, and now I can't get a new topic to produce, an audio overview that well. Well, you can now, go back and see your custom prompt, and then I can go and just click the copy button and reuse it. Alright.

Jordan Wilson [00:17:21]:
So small thing, but big benefits. Alright. And then last but not least, the nano banana visuals. Alright. So, let's go ahead. I did already generate a video. I wasn't gonna make any everyone wait because, the videos can, now that they're powered by nano banana. Downside, they can take a little longer.

Jordan Wilson [00:17:41]:
Upside, they are bonkers good. Alright. So I'm gonna play, just a couple portions of this one. So this is, an explainer video, that I created. So I'm gonna go ahead. It's a problem I hear all the time. The gap between the AI champions and everyone else in your organization is sizable. You might have half a team that wants to fine tune models by hand, and the other half doesn't know what an API is.

Jordan Wilson [00:18:09]:
How do you get them working together on AI that moves the needle without creating a security nightmare? That's where Aria really shines. They built one platform with three ways to work. Your developers can go full pro code and build custom agents with Python. Your business analyst can use the low code tools. Or your domain experts who've never coded, they can use the drag and drop no code builder. Everyone's building in the same secure governed environment. No shadow IT, no security gaps, and because they're model agnostic, you're not locked into one vendor's ecosystem with Aria. You can even a b test different agents against each other.

Jordan Wilson [00:18:45]:
Try different models, and when you're ready, deploy to production on the same platform. Your AI strategy should unite your team, not divide them. Check out Aria in today's show notes or on our website for a free trial. Go to airia.com. Get rid of the AI gap and move forward with a more resilient AI ecosystem. So our live stream audience can see just the cover is so good. Right? It says Apple's 1 b, $1,000,000,000 AI gamble, and it has this nice illustration. It's the Apple logo.

Jordan Wilson [00:19:26]:
Right? There's this kind of arrow with an x over it, you know, this little chip icon. So essentially saying like, hey, Apple couldn't get it done, and then there's an arrow. You know, the Apple icon, you you know, has a thinking bubble, and it's like, oh, I have an idea. Let me hire Google. Let me give Google $1,000,000,000. And and then there's the Google logo with a brain over it in Gemini AI. Such a good visual. Right? So I'm gonna play and Alright.

Jordan Wilson [00:19:54]:
Let's dive right in. Yeah. And if you haven't done, if you haven't used these video overviews, you should. Alright. I'm gonna scroll through, some of these. I mean, look at this. So this is, a nice visual here. It says, why is Apple paying its biggest rival with biggest rival highlighted in yellow? $1,000,000,000 to fix Siri.

Jordan Wilson [00:20:12]:
Again, a lot of, corresponding visuals. There's a couple others. I have a screenshot here I'm gonna share with you guys in a little bit. I mean, but here we go. Here's another one. I mean, it made charts, you know, charting Google Gemini's parameters, 1,200,000,000,000 versus Apple's model, which was a 120,000,000,000 to, 120,000,000,000 parameters. Right? So it literally pulled different elements, from, my notes, from other sources, and it's creating literal labeled visuals. Right? So so good.

Jordan Wilson [00:20:47]:
So, nano banana is, Google's if you haven't heard. That is their Gemini 2.5 flash image model, also just now known as Nano Banana. And it is the leading image editing AI tool in the world according to LM Arena. So it is extremely powerful. And just the capabilities. Right? I use these, these AI videos a ton, and I have since, so originally, they were being powered by, I believe Google's imagine, AI model. And it's not like they were bad, but sometimes I would get, you know, certain slides and I'm like, this doesn't really make sense, but it's like, okay. Who am I? Right? Like, the fact that this technology even exists, it's like beggars can't be choosers, but now it's yeah.

Jordan Wilson [00:21:34]:
You can, because this is number one free. Right? But it just makes for me, it makes learning so much more impactful when each visual inside of this video is just on point like a freaking decimal. It is so so good. Right? That's why, hey. You you just might wanna go check the video out on this one, and, I'll probably share the actual video that this created, in today's newsletter. So make sure you go check that out as well. Alright. So, let's get back and go over, a couple more things here.

Jordan Wilson [00:22:12]:
Actually, let's first take a quick break for me to take a sip and for a quick word from our sponsors. It's a problem I hear all the time. The gap between the AI champions and everyone else in your organization is sizable. You might have half a team that wants to fine tune models by hand, and the other half doesn't know what an API is. How do you get them working together on AI that moves the needle without creating a security nightmare? That's where Aria really shines. They built one platform with three ways to work. Your developers can go full pro code and build custom agents with Python. Your business analyst can use the low code tools.

Jordan Wilson [00:22:48]:
Or your domain experts who've never coded, they can use the drag and drop no code builder. Everyone's building in the same secure governed environment. No shadow IT, no security gaps. And because they're model agnostic, you're not locked into one vendor's ecosystem with Aria. You can even a b test different agents against each other. Try different models, and when you're ready, deploy to production on the same platform. Your AI strategy should unite your team, not divide them. Check out Aria in today's show notes or on our website for a free trial.

Jordan Wilson [00:23:20]:
Go to airia.com. Get rid of the AI gap and move forward with a more resilient AI ecosystem. Alright. So let's quickly, dive into a little bit more depth, on these eight features. If I didn't already go over them, if if I did go over them, I'm not gonna go into them in too much more depth. But the first one here is the ability to, view the custom prompt. So like I said, the the where you're gonna get this is if you go to your studio for something that you've already, created, all you do is you find it. You find the three little dots, and then that's gonna bring a drop down menu and then the view custom prompt.

Jordan Wilson [00:24:02]:
And, again, this is big because if you're not super organized, that's me sometimes. Right? I actually use notebook l m to be organized, but sometimes I'm not very organized within notebook l m. This is a great way to go back on, you know, some of your reports, deep dives, videos, etcetera, that you've created custom. See what worked well. Go grab that custom prompt and reuse it. 7, chat, sorry. That was number 8. So then number 7, the chat history on by default.

Jordan Wilson [00:24:32]:
Small thing. Huge. Right? And this is something that a lot of people didn't understand at first about notebook l m. Right? You add in all your sources. You know, on Monday, you go in and you're like, oh, this is amazing. I love the grounding of notebook l m. And then you exit out. And then Tuesday, you go back and you're like, wait.

Jordan Wilson [00:24:49]:
Everything's gone. Right? That's how it worked before. You had to save any conversation. Each individual response from NotebookLM, you had to save it as a note. Alright? And then you could also save the note as a source. Right? But, it essentially put it on your studio on the right hand side. So it worked a little different than a traditional AI chatbot. Right? Normally, you're like, oh, okay.

Jordan Wilson [00:25:12]:
Well, if I chatted with Chad GBT or Gemini or Claude or Copilot yesterday, right, it should be there today. That's not how notebook LN worked. Now it does. It sounds simple. Right? Although I on all I don't see this on all of my workspace accounts. So this might be something at the admin level for workspace, but on my personal accounts, I do see this, enabled by default. So it might be a setting kind of, buried somewhere, in the, admin settings, inside Google. But just chat history on my default, it seems like, oh, okay.

Jordan Wilson [00:25:47]:
Duh. But, y'all, like, notebook l m was not created to be an all encompassing AI chatbot juggernaut, but now it kind of is. Right? So I like kind of these slight pivots maybe away from the original vision of what the team wanted to use notebook l m for, and they're probably saying like, wait, everyone wants this. So, you know, it's great. And it just improves, obviously, the multi turn performance. Number six, already went over this, but the goal based customization, this this is this is great. Right? Yes. It's kind of like having custom instructions inside every chat in chat g p t, which you don't have.

Jordan Wilson [00:26:28]:
Right? You do you can set that at the project level, but share more and more context. Use this. I think a lot of people are just using this, to tell notebook l m how to respond. Right? Either be long and funny, be short and serious. Right? But give it a goal. Tell it who you are and what you're trying to do. So this is essentially notebook l m's version of custom instructions. Number five, this is big for teams.

Jordan Wilson [00:26:53]:
Right? That's the other thing. Notebook l m can be shared across your organization. Just such. Right? When you talk about the lowest hanging fruit in generative AI, that's it right there. Right? Nope. Being able to share notebook across your organization, my gosh. Like, hang up on this podcast right now and go do that. But before, privacy controls weren't that great.

Jordan Wilson [00:27:16]:
And it seemed like sometimes the chat history could be shared even if you maybe didn't want it to. Right? So now the chat history can be deleted. And in shared notebooks, the chat is only, visible to the individual user who was using it that way. So it seemed like before, maybe it was supposed to be a feature and maybe it kind of turned out to be a bug. But regardless, some new privacy controls that just rolled out. Number four, already showed this live being able to import Google Sheets inside notebook l m. Love this. Downside though, it seems like there's a strict file limit.

Jordan Wilson [00:27:53]:
I didn't test it, very, in a detailed way, but I had a spreadsheet that was 1.3 megabytes, so not huge. Right? I have spreadsheets that are hundreds of megabytes, and it couldn't bring in one that was 1.3. So I'm guessing the limit is probably a a megabyte or under, to work, which for most people, right, it's not gonna be a problem. But if you have heavy spreadsheets, heavy Google Sheets, it might be too big. So I am gonna be reaching out to the team because I actually just found that, limitation, which I think actually might be a bug. Because one megabyte is actually kinda small. So we'll see if that, is improved. I'm sure it will.

Jordan Wilson [00:28:33]:
Number three, the 1,000,000 token context. This is big. Right? So, I'm gonna read this from, Google's blog post here announcing these features. So it says more seamless and natural conversations. We have significantly expanded notebook l m's processing capabilities, conversation context, and history. Starting today, we're in we're enabling the full 1,000,000 token context window of Gemini in notebook l m chat across all plans, significantly improving our performance when analyzing large document collections. Plus, we've increased our capacity for multi turn conversation more than six fold. So you can get more coherent and relevant results over extended interactions.

Jordan Wilson [00:29:19]:
So, yeah, I was actually number one, great. Number two, I was kinda confused by this because I was under the assumption that notebook l m had that level, of context window previously because it was powered by Gemini 2.5. But it seems like it it defaulted to a lower, context window, but now it's good to know that it does have the full 1,000,000 token context window. In a chat program, I don't know if anyone else aside from now Google has that. Right? People see these, oh, yeah, million token context window, for, you know, Claude or whatever. Well, no. That's usually in the API. Never in the chat.

Jordan Wilson [00:29:58]:
Right? I I mean, you can't even use Claude chat. I did demos on here before two weeks ago. I tried to do a single prompt. It was, you know, multi step agentic, but a single prompt, and it, tore through the chat window. Right? A million token context window inside of a free tool that's grounded? Y'all, this is so, like, this is so good and so powerful. It's silly. So, I I I am glad that Google clarified that and put it out there in the wild for everyone to know. Number two, the mobile app.

Jordan Wilson [00:30:36]:
This is big. Here's a little secret into my life. Sometimes my brain won't turn off. People are always like, Jordan, how do you do a daily podcast? It seems like you're well researched. Right? Seems like you're on your toes. You can answer questions. How do you do it? Well, I number one, I should sleep more. Number two, I mean, notebook online.

Jordan Wilson [00:31:00]:
Right? I'd say it's like one of my secrets, but I talk about it all the time. Right? They're one of the advertisers for this podcast. Right? You hear it all the time. But one thing that I was kinda like, man, I wish it was better, is the mobile capabilities were kinda not that great up until, like, September. But this most recent one, which again just dropped to all users this week, having the quizzes and flashcards available on mobile is big because a lot of times I'm up at night and I'm like, oh, man. I gotta prepare or, you know, oh, did do I actually know this piece on the show well enough for tomorrow? Or if I'm interviewing. Right? A lot of times I'm interviewing, you know, like CEOs of public companies, And I have to be able to ask them very relevant and hopefully into halfway intelligent questions. Right? I love using the flashcard in quizzes just like I did back in the day.

Jordan Wilson [00:31:57]:
Right? Like, eight year old Jordan, literally, I would just make flashcards by probably when I was younger. I was a dork. Right? I love flashcards. I would make them all the time. I think even for, like, basketball stats. Right? I would just make flashcards. I love, memorizing facts. It's a little harder now because I feel I learn so much new every day because of AI.

Jordan Wilson [00:32:20]:
I forget more than ever. But this is great. Having that on mobile because sometimes that's when I really do my best work is like, alright. Well, I'm in bed. I can't sleep, but I have no other distractions. Right? Throughout the day, I have distractions all the time. When I'm in bed, if I can't sleep and I look at my phone, there's no distractions. I'm zoned in.

Jordan Wilson [00:32:40]:
So now I love having the quizzes and flashcards available on mobile. Have a little screenshot there. Really clean. Looks nice. The answer to that is 1000000000, by the way. Right? The Apple AI quiz. And then last but not least, the nano banana visuals. Alright.

Jordan Wilson [00:32:57]:
They're already rolled out to the video overviews, and there's also six different, preset styles, right, that they all use nano banana. So it's not like, oh, you're looking for nano banana as a preset. Right? There's whiteboard. There's anime. There's, you know, all these different, styles that you can select, but the actual visuals are built with nano banana. And I already showed you guys a couple. Here's one that I really liked, from the, the Apple and, Google Gemini, Siri, paying $1,000,000,000 show from yesterday. This one's great.

Jordan Wilson [00:33:36]:
So, it's it's kinda like a medieval esque, kind of style to it, but it has, Apple. In Apple, you know, there's a a gap. There's a cliff. Right? There's a big drop off, and it's scary. It can't get across, but there's a bridge. Don't worry. But the bridge is Google logos. Right? So if Apple needs to get to the other side, which is a castle with an Apple logo logo on it, the only way they can do it is the bridge of Google Gemini.

Jordan Wilson [00:34:06]:
Such a good high quality visual that I, you know, I kinda like chuckled because I'm like, You know, that's funny. Right? It's it's it's funny, but it's just highly relevant. Right? So, being able Nanobana is so good at being able to, contextually grab the meaning behind your words. Right? So things that you might not even know, even if it's something you write by hand. Right? You might not even be able to create certain connections that Nano Banana is just fantastic at. So I can't underestimate how big of a level up that is for everyone. You should be using these video overviews. They are rich in context.

Jordan Wilson [00:34:45]:
And if you are a visual learner like me, it's it's gonna be hard to go back. Alright. Here's what's coming next, and then we're gonna wrap with our use cases. So there is an infographic feature that is gonna be powered by Nano Banana that will be released sometime soon. The API, notebook LM has confirmed that. We don't know if that's gonna come this year, but like I said, there's gonna be, I think, multiple million dollar companies that literally are just using notebook LM's API, and that's it. Also some new updates. Some of these are rumored, some are confirmed, but custom video style.

Jordan Wilson [00:35:23]:
So you'll be able to just describe it, not just having to choose from one of the six. Deep research integration. Yes. I did confirm that directly with the, notebook l m lead, but they are bringing, Gemini deep research into notebook l m, as well as tables, artifacts, slides generation, and more. Alright. So let's wrap with five new notebook l m use cases that are available today that weren't available before some of these late October, early November updates. Ready? Here we go. And here's a timely one.

Jordan Wilson [00:36:01]:
College student, your midterm rescue. Alright. So you can upload an entire semester of notes, documents. Right? If you have your book and PDF form, and be and work with that 1,000,000 context window and essentially set a goal. You know, say, you're a Socratic tutor, you ask questions, but you don't give answers. Right? Be creative with how you use that goal section. Then you can generate mobile flashcards. Right? So you can get it all set up on your desktop, and then you can generate mobile flashcards for your commute.

Jordan Wilson [00:36:30]:
And then you can, you know, resume your chat history at the library. Those things were not possible before. And this takes, maybe dozens of hours of work that you would have to do otherwise into, like, thirty minutes. Next use case, executives assistant, the CEO brain. So putting together board packet, agenda sheet, past decisions, you know, and again, tapping into that 1,000,000 context window and as many Google Sheets as possible. Same thing, being able to generate mobile flashcards, CEO reviews between meetings. Right? I think a lot of CEOs are always between meetings on their phone. That's a great thing.

Jordan Wilson [00:37:07]:
Right? So if you're an executive assistant, if you work directly with a CEO or if you are a CEO, you need to be doing this. Right? Even for me, even though I'm on the computer a lot, I sometimes do my best work on the phone. So load everything in there and then set the goal. Right? Hey. This is a board member asking tough tough questions for scenario prep. Again, hours of prep down in minutes. Next one, this is my salespeople. This is for you.

Jordan Wilson [00:37:32]:
Import your actual deal data. Right? So what if if you're in Salesforce, whatever your CRM is, HubSpot, you can usually export it to a spreadsheet, bring those spreadsheets into Google Sheets, import those and then set the goal. You know, skeptical CFO asking hard budget questions, as an example. And then the AI can role play your specific deal with real numbers that you import. So just new capacity right there, you know, being able to practice on actual accounts, not just generic scenarios. Next, consultant proposal customization engine. So same thing here, import client RFPs, budget sheet, past work, anything. Right? So many different modes, that you can import, and then you can generate a deep dive report for each client.

Jordan Wilson [00:38:22]:
And then you can use, that copy prompt. Right? So, if you're working on this over the course of three weeks as an example, you can use the new chat history. You can use the, view and copy custom prompt, and then you can, you know, spit out, different deep dive reports for all different clients. Alright. And then we have our product manager interview analysis at scale. So let's just say that you're having to go over 200 user interviews. Well, whatever program you're using to collect all those applications, you can export it to spreadsheets. You can import all those spreadsheets, work with the new 1,000,000 token context window, and then have multi turn chats.

Jordan Wilson [00:39:01]:
Whenever you wanna go in there, ask questions, about which, which one is best, which user did best on this. And you can also do something like, you know, now show enterprise versus, small business patterns, and it will remember the entire context. And then you can generate mobile flashcards. And, again, cut that time in half, maybe down to 20%. Alright. So I hope this episode was helpful, putting AI to work on Wednesdays. And I will say this, you all wanted this. I put, I I put a poll in the, show notes for the podcast.

Jordan Wilson [00:39:39]:
I put a poll on, in our newsletter, and you all said you wanted to go over these new notebook l m updates. So if you want if if I should be doing these updates for every single large language model, go ahead, leave a comment on the, on this Spotify episode or on the live stream and just say l l m. Right? If you want a monthly episode where I do this for all, you know, at least the big four. Right? Copilot, Gemini, Chad GPT, and Claude. Let me know. I offered this up, like, six months ago. I always have an arbitrary number in my head, and we didn't hit it. Right? A little short.

Jordan Wilson [00:40:14]:
So if you want that, let me know. Make your voice heard. I work for you. If it's not helpful, that's fine. But I hope today's show was helpful as we went over those eight new updates in November that you need to be using. Like I said, I think that Google's notebook l m is turning into a fully featured AI chatbot and all the things that are coming along with it. Right? All these rumors and, you you know, leaks and also confirmed plans for the future of notebook l m. It is much more than just a tool to help you learn.

Jordan Wilson [00:40:51]:
Yes. It helps you learn better than any tool. The grounding is fantastic, but even just the features that we went over today, these are great for teams. These are great for, you know, CEOs, board members, whatever it is. It is becoming more and more useful for more and more people and for teams. So you can't not pay attention to notebook l m anymore. It's not just a cutesy little thing to generate AI podcast. Alright.

Jordan Wilson [00:41:20]:
And make sure if you haven't already, repost this show on LinkedIn. Trust me. You are gonna want that every bit, everyday AI notebook l m cookbook. We've literally put all of our knowledge, all of our information into one helpful guide. So go repost this on LinkedIn. I'll share it. Literally, the feedback that I've gotten for people are like, you're stupid for giving this away for free. You should be charging a lot of money for this.

Jordan Wilson [00:41:45]:
But I wanna keep free unbiased information available to everyone for as long as I can, but I need your help. I need you to share about this, tell people about this because if you just keep everyday AI your little secret, we die. Right? The only thing we can keep this thing going is if you share with people. So make sure you go share this episode, then make sure you go to youreverydayai.com. Sign up for the free daily newsletter. I hope you are now putting AI to work more on Wednesdays, and I hope to see you tomorrow and every day for more everyday AI. Thanks y'all. As someone that covers AI everyday, no one knows which AI model will be best in six months.

Jordan Wilson [00:42:29]:
That's why betting everything on one vendor is dangerous, and that's why Aria can solve the LLM FOMO issue. They're completely model agnostic. Use GPT for one agent, Claude for another, your own fine tune model for something else. Switch anytime without rewriting code. Their intelligent routing automatically sends requests to the right model based on your rules. Check out today's show notes or our website for a free trial of Aria. Go to airia.com because vendor lock in is a terrible long term bet.