Ep. 25 – The Best AI Tool You’ve Never Heard Of
Let’s get curious about Google Notebook LM! In this episode walk through what it is, how it works, what makes it different from ChatGPT, and how I’ve personally used it to create mind maps, slide decks, and one-sheets. We also talk about learning styles, hallucinations, citations, pricing, and why this tool feels especially aligned with how I believe AI should be used.
Welcome!
I realize today’s episode title is a little clickbaity, and I’m hoping it didn’t deter anyone from giving it a shot, but I choose it because it’s honestly 100% true.
BTW, welcome to 2026. I know last week’s episode technically kicked off the year, but it was also the very first day of 2026, which made it feel a bit premature. Now that we’re actually a week in, it finally feels appropriate to say: Welcome to 2026.
How I Found This Tool
The tool we’re talking about today is one I’ve used a bit, and it was first introduced to me by my good friends Tina Tang and Dr. Jackie Fenton. So no, it’s not brand new, but in my opinion, not nearly enough people know about it (so it’s basically brand new), and I would very much like to change that.
The tool is Google Notebook LM. If you’ve heard of it, or better yet if you’re already using it, congrats, you are ahead of like… everyone.
Quick side note: I know this podcast is called ChatGPT Curious, but I always planned on using it to talk about AI more broadly, not just one company or one tool, soooooo, thank you for being cool with that.
What Is Google Notebook LM?
Google Notebook LM is an AI learning app.
I’ll be honest, while putting this episode together, I tried really hard to find a clean, explicit definition of what it is on Google’s own website, and I honestly couldn’t find one anywhere.
If you go to notebooklm.google, or just Google “Google NotebookLM”, the header at the top of the page says:
“Your research and thinking partner, grounded in the information you trust, built with the latest Gemini models.”
Sounds nice, but still doesn’t really tell you what it is.
If you scroll down to the FAQ section, you’ll see it compared to other tools, and in one of the questions they use the phrase “AI learning app”, so that’s what we’re going with.
The “LM” in Google Notebook LM stands for language model, and the language model it uses is Gemini.
The information page itself is honestly pretty bare bones compared to other AI tools, and honestly, I don’t mind.
Understand Anything
The most telling part of the information page is the tagline, in HUGE letters at the top of the page: Understand Anything.
That right there is the heart of Google Notebook LM, and it’s why I think it’s the best AI tool you’ve never heard of.
Here’s how it works:
- You upload sources. PDFs, websites, YouTube videos, audio files, Google Docs, Google Slides, whatever you’ve got
- From these sources then creates a learning resource for you (based only on those sources)
Worth noting, if you don’t already have sources, you can have it search the internet and come up with sources for you. From there you choose which sources you want it to use, and then it will create the learning resource.
What It Can Create
This is where it gets very cool.
What kind of learning resource can it make? Pretty much anything you could want.
- Audio overview (which is a podcast episode between two cohosts!)
- Video overview
- Mind map
- Reports
- Flash cards
- Quiz
- Infographic
- Slide deck
- Data table
Are you kidding me?!?!
I’ve personally only used it for a mind map, an infographic, and a slide deck, but what it created for all three was genuinely amazing. Based on that, I have zero doubts that the rest are just as good. (Tina used it to create super helpful podcast episodes which is how I learned about Google Notebook LM from her in the first place.)
Why It’s So Good
What really makes this tool special is that it can’t hallucinate.
Google NotebookLM only pulls information from the sources you give it, AND it provides citations, showing you the exact quote it pulled from the source.
This thing is truly awesome.
Where I really see the utility is with internally facing use cases, meaning using it for yourself.
Want to summarize a long article or podcast episode? Want to actually understand something instead of just skimming it? No problem.
I personally used it to wrap my brain around foundational computer science concepts because I wanted to understand how the pieces fit together, and the mind map it made was better than I could have imagined.
No matter what your learning style is, this tool can meet you there.
This right here taps into the broader excitement I have around AI and its potential to democratize learning. Imagine what something like this could do in schools, especially for kids with different learning styles. Everyone can learn everything. That’s fucking amazing.
External Use Cases and One-Sheets
As for externally facing use cases, yes, you can use it to generate presentation slides, but you can’t edit the slides.
I actually had it generate slides for me, and the slides it made were fantastic, but I personally couldn’t present from them, because for me making the slides is part of how I practice the presentation. So, having them auto-generated isn’t that helpful, even though they were objectively bomb ass slides.
What it was phenomenal at, and what I did use and share, was creating a one-sheet.
A one-sheet, at least the way I make them, shares the most important takeaways from a presentation.
For my ChatGPT for Online Business Owners webinar, I uploaded my slide deck and asked Google NotebookLM to make a one-sheet. I gave it a few stylistic instructions, and by the third iteration it was a gotdamn banger.
I will never not use this tool for one-sheets. Ever.
Patterns and Abstraction
Something worth noting is that because this tool uses the Gemini language model, it’s phenomenal at identifying and abstracting patterns (as all LLMs are). That’s how it creates such strong mind maps and one-sheets.
Sticking with this idea of patterns, one way I’ve yet to personally use Google NotebookLM, but is actually pretty genius, is uploading brainstorming notes or market research and asking it to identify trends, generate product ideas, or surface hidden opportunities.
Yes, you could do this with ChatGPT, but based on my experience with Google NotebookLM, I suspect it might actually be better at this specific type of work.
What I Don’t Know and Pricing
I do not know exactly how Google Notebook LM works under the hood. I tried to find details, didn’t see much, and honestly didn’t feel like going down a research rabbit hole.
I’m happy with my cursory understanding that it’s a language model that generates responses solely based on the resources you provide. That’s good enough for me.
You interact with it using natural language, just like ChatGPT, and the experience feels very similar.
As for pricing, there is a free version. How it compares to the paid tier, I can’t say for sure, because I’ve only used the paid version. If you have a Google Workspace account, the pro tier is included.
If you don’t, I think it’s around $19.99 a month, and they also push a Google One AI plan, which bundles extended cloud storage with AI features. It’s all a bit confusing if you ask me. My suggestions: Just go to the site and poke around.
How I Used ChatGPT This Week
Each episode, I share how I used ChatGPT that week.
This week, I used it a ton while vibe coding my first web app, a med tracker for my sister! I used Cursor, which is an AI-assisted code editor, but I leaned on ChatGPT heavily during the planning phase and throughout the build to save money, since Cursor charges per AI interaction.
While I do think that in general you probably want code generation to be more deterministic (remember, LLMs are probabilistic models), when you don’t know how to code at all, being able to use AI to write code (and check it!) is one hell of a start.
Da Wrap-up
I don’t have an affiliate link or a discount code or anything like that. I just genuinely hope you check this tool out.
I really do think Google Notebook LM is the best AI tool you’ve never heard of…except now you have 😉
As always, endlessly appreciative for you and your curiosity.
Catch you next Thursday.
Maestro out.
AI Disclaimer: In the spirit of transparency (if only we could get that from these tech companies), this email was generated with a very solid alley-oop from ChatGPT. I write super detailed outlines for every podcast episode (proof here), and then use ChatGPT to turn those into succinct, readable recaps that I lightly edit to produce these Curious Companions. Could I “write” it all by hand? Sure. Do I want to? Absolutely not. So instead, I let the robot do the work, so I can focus on the stuff that I actually enjoy doing and you get the content delivered to your digital doorstep, no Airpods required. High fives all around.
Did someone forward you this email?
Click here to join the ChatGPT Curious newsletter family.
Stay curious.