How I Use Gemini + NotebookLM to Read Less, Learn More, and Remember Everything

Here, I’m going to share a simple AI workflow that will help you read books, and even research papers, faster than 99% of people.

Image generated by Nano Banana Pro

Let me say something that might annoy a few people.

Most people aren’t bad at reading. They’re actually bad at deciding what deserves to be read.

And in the AI era, this mistake is brutally expensive.

But how? Well, we still read books the same way our parents did.

Page one to page three hundred, highlight a few lines, and then forget 90% of it in the same sense.

That made sense when information was scarce, but it makes zero sense now.

Today, the real skill isn’t reading faster. It’s extracting only what you actually need to know, and that’s where AI can help.

And in this post, I’m going to share a simple AI workflow that will help you read books, and even research papers, faster than 99% of people, retain more, and save you more time than you can imagine.

Note: If you found this post valuable or learned something new, consider becoming a paid subscriber to this newsletter. It’s the best way to support my work and keep this kind of content coming.

With that said, let’s get started.

The Real Problem: Linear Reading in a Non-Linear World

Here’s what most people do:

• They buy a book.

• They start reading it line by line.

• They assume every chapter deserves equal attention.

That’s the mistake.

Most books, especially business, productivity, and self-help books, are 20% original insight and 80% repetition, stories, and padding.

To be precise, they usually have:

• 3 to 6 strong ideas

• 10 to 15 supporting insights

• 200 pages of repetition, stories, and padding

But why is it so? Well, authors write books for humans. To explain each idea clearly, they go into more detail, repeat points, and share similar stories.

However, thanks to AI, you don’t need to rely on repetition anymore, and you can read faster than 99% of people.

For sure, you can go ahead and read line by line, but you’re simply wasting the one resource you don’t get back, time.

And you still won’t retain 100% of what you read.

The smarter question now is not, “Should I read this book?” It’s, “What exactly do I need from this book?”

That single shift changes everything.

Here, I’ll use “Rich Dad, Poor Dad” as the example by uploading the book itself.
Since most people already know it, this will keep the workflow simple.

Step 1: Interrogate the Book Before You Read It

Before I open a book to read, I ask Gemini or ChatGPT to justify the book’s existence.

I also try to be very direct (& rude), because AI usually performs better when you don’t use words like “please” and similar soft language.

Here’s the kind of prompt I actually use:

• Summarize the core thesis of this book in one paragraph.

• List the five most useful lessons.

• Tell me who this book is NOT for.

• And tell me which chapters can be safely skipped.

To give you a practical example, I uploaded the book Rich Dad, Poor Dad and asked it the questions above.

And here are the five most useful lessons suggested by Gemini.

This does two things immediately:

• It tells me whether the book has anything new for me.

• It gives me a mental map before I touch page one.

Also, I get a clear idea of whether I need to read the book fully, whether I will actually learn something, or if it only covers basics I already know.

And that’s what helps me save time and focus only on what actually matters.

---

Step 2: Start Extracting That I Need to Learn and Remember

Once a book passes the filter, I upload it to NotebookLM.

This is where things change.

And instead of reading passively or asking, “What does this book say?”, I interrogate the book like a consultant would.

I also try to upload similar videos, documents, articles, or other content by the same author or even by different authors.

Sometimes, I even upload a couple of books from the same niche so I can get a better perspective and learn more about the topic I’m researching.

Then I ask questions like:

• What frameworks does this book introduce?

• What are the 5 most important lessons I need to learn from this book?

• Which ideas are actionable, and which ones are just motivational fluff?

• What assumptions does the author make that might be outdated?

• What frameworks does the author use repeatedly to build wealth?

You see, I’m not spending time reading the entire book. Instead, I’m learning exactly what I need to.

---

Just so you know:

Everything I’ve shared here is something I actually use.

If this post changed how you think about NotebookLM even a little, that didn’t happen in isolation. It came from a much bigger shift in how I use AI overall.

That’s why I put that entire system down inside “The (Unfair) AI Workflow Playbook” with everything you need.

It’s the exact set of workflows I use daily to run my work faster than feels normal, and if you apply even a few of them, you’ll save hundreds of hours.

You can spend months figuring this out on your own, or you can steal my entire playbook right now.

---

Step 3: Turn Books Into Formats Your Brain Actually Remembers

Let’s be honest, reading isn’t the best learning format for most people.

We just pretend it is.

And that’s where, NotebookLM lets me convert the same content into:

• Audio overviews – I listen while walking or working out

• Visual summaries – concepts laid out instead of buried in paragraphs

• Quizzes – to see if I actually understood anything

• Infographics – because visuals help you understand faster

• Slide Deck - to generate presentations that I can go through

This matters because:

Your brain remembers patterns, contrasts, visuals, and not pages.

And let me tell you: “A 10-minute audio overview + one infographic will outperform 3 hours of passive reading every single time”.

---

The Same Logic Applies to Research Papers (Even More So)

If you are reading research papers, then you know they are worse than books.

They’re:

• Overly formal

• Filled with irrelevant methodology

• Written for reviewers, not learners

And I still need to read them to learn about recent advancements in AI, how different models work, and related topics.

But I don’t read them directly anymore.

Instead, I upload multiple papers on the same topic into NotebookLM and ask:

• What are these research papers actually about?

• Where do they contradict each other?

• What can I safely ignore?

• What really matters if I want to apply this, not publish it?

Sure, I could use Gemini as well, but I prefer NotebookLM since it has more features and is built for this kind of task.

This turns academic noise into usable insight, and much faster.

---

Your Simple AI-First Reading Workflow

Let me be brutally honest, even today, most people still read like it’s 2015.

They:

• Ask random questions

• Copy random prompts from Twitter

• Highlight stuff they’ll never revisit

• And use AI like a fancy Google search

So instead of doing that, I shared the simplest AI-first reading workflow I actually use when I read anything serious.

My core idea is simple:

Reading isn’t about finishing pages anymore. It’s about deciding, extracting, transforming, and applying.

And, here’s the simplest and practical workflow you can follow:

And here are the steps that you need to go with:

• Filter – Is this worth reading?

• Extract – What are the non-obvious ideas?

• Transform – Audio, visuals, quizzes

• Apply – What changes in my work after this?

And you can do this across different AI tools like:

• LLMs for filtering and interrogation

• NotebookLM for synthesis, and recall

• And so on

---

Let’s Wrap Up

I know most of you may be seeing this workflow for the first time, and some of you may not like it.

You might love reading and not want to follow a structured AI workflow like I shared.

And that’s okay.

This is not for people who read fiction or read simply because they enjoy the process.

This is for people who are spending too much time reading and want a better way to read faster and retain what they read.

AI does not make reading obsolete. It makes lazy reading obsolete, especially with workflows like this.

So if you are still reading everything line by line, hoping something sticks, you are playing an old game in a new world.

The people who win now do not read more.

• They read with intent.

• They let AI do the heavy lifting so their brain can focus on thinking, connecting, and applying.

And once you experience this shift, there is no going back.

---

Hope you like it.

That’s it, thanks.

Also, don’t forget to checkout “The (Unfair) AI Workflow Playbook” where I shared exact set of AI workflows I use daily to run my work faster than feels normal.