Google Gemini Notebook (NotebookLM) - Advanced Guide and Masterclass

TL;DR

This is a full, self-contained course on Gemini Notebook - the tool Google renamed from NotebookLM on July 16, 2026. Same tool, same free plan, new name and a new home at notebook.google.com.

We're not sending you anywhere else to "finish learning it." Every module below - from your first notebook to Deep Research reports, Audio Overviews, and multi-notebook power workflows - is taught here, in full.

It's completely free to start: 100 notebooks, 50 sources each, 50 chats a day, 3 Audio/Video Overviews a day, and 10 Deep Research sessions a month - no credit card.

By the end of this course, you'll be able to build a source-grounded research assistant, run Deep Research investigations, generate podcast-style Audio Overviews, and automate recurring research workflows - all without writing a single line of code.

Gemini Notebook (NotebookLM) complete course — Deep Research, Audio Overviews, and advanced workflows explained

Reviewed by Imran Khan Pathan, Editor at AI Tech Safar. I built out real notebooks for this course - dumped in PDFs, YouTube links, and web sources, ran actual Deep Research sessions, and generated Audio and Video Overviews - before writing a single instruction below. Every workflow in this course is something I ran myself, not a rewording of Google's help docs. Where a feature is locked behind a paid tier, I've said so plainly.

Last updated: September 2026

Who This Course Is For

This is written for people who already know Gemini Notebook exists but have never gone past "upload a PDF, ask it a question." If that's as far as you've gotten, you're using maybe 20% of what this tool can actually do.

By the time you finish this course, you'll know how to:

Structure notebooks so the AI stops giving you vague, generic answers
Run genuine multi-source research investigations using Deep Research
Turn a pile of documents into a podcast, a slide deck, a study guide, and a quiz - from the same source material
Automate recurring research so your notebook updates itself
Avoid the mistakes that make most people's notebooks hallucinate or give shallow answers

No prior AI experience needed. No other tutorial required. Let's start from the actual foundation.

Module 1: What Gemini Notebook Actually Is (The Part Everyone Skips)

Before touching the interface, understand this one idea, because it changes how you should use the tool: Gemini Notebook is not a general chatbot. It's a source-grounded research assistant.

ChatGPT, Gemini's regular chat, and Claude all answer from their training data plus whatever you type. Gemini Notebook does something fundamentally different: it answers only from the specific documents, videos, and links you feed it. If you don't upload it, the notebook doesn't know it exists - and it will tell you that, rather than guessing.

This single design choice is why the tool was originally built (under the codename Project Tailwind back in 2023) for research, studying, and analysis - tasks where "confidently wrong" is worse than "I don't know." It's now used by over 30 million people and 600,000 organizations, and it runs on Google's Gemini 3 model under the hood.

The practical implication for you: the quality of what you get out is almost entirely determined by the quality and structure of what you put in. This course spends real time on that, because nobody else does.

Module 2: Choosing Your Plan (Free Is Genuinely Enough to Start)

Gemini Notebook has four tiers, all bundled into Google's broader AI subscription structure since the May 2026 restructure at Google I/O. Here's exactly what each gives you:

Plan	Price	Notebooks	Sources/Notebook	Deep Research
Free	$0	100	50	10 sessions/month
Plus (Google AI Plus)	$4.99/mo	200	100	Several/day
Pro (Google AI Pro)	$19.99/mo	500	300	20 reports/day
Ultra (Google AI Ultra)	From $99.99/mo	500-600	500-600	75+/day

What's identical on every tier: the same Gemini 3 model, the same 500,000-word (or 200MB) cap per individual source, no page limit, and every core Studio feature - Deep Research, Audio Overviews, Video Overviews, Slide Decks, Study Guides, Flashcards, and Quizzes. Paying buys you more of the same, not a smarter version. The single exception: Cinematic Video Overviews (built with Google's Veo 3 video model) are Ultra-only.

Course recommendation: start on Free. Everything in this course works on the free tier - you'll only hit limits if you're running the tool professionally, every day, at volume.

Module 3: Building Your First Notebook Properly

Go to notebook.google.com and sign in with any Google account. Click New Notebook. This is where most tutorials stop being useful - they tell you to "add a source" without telling you how to think about sources. Here's the part that actually matters.

What You Can Add as a Source

PDFs and Google Docs - the most common source type
Google Slides and Sheets
Web page URLs - it pulls the page content directly
YouTube video links - it works from the transcript, so lectures, interviews, and long-form videos become searchable text
Audio files - upload a recording and it transcribes and grounds itself in it
EPUB files - full ebooks, added as a supported source type in 2026
Pasted text - copy-paste anything directly

The Rule Nobody Tells You: Curate, Don't Dump

The instinct is to upload everything you have. Resist it. A notebook with 40 loosely related sources gives vaguer answers than a notebook with 8 tightly relevant ones, because the model has to spread its attention across everything you gave it. Build one notebook per project or question, not one giant notebook for "everything I'm working on." This is the single biggest quality lever in the entire tool, and it costs nothing to do right.

Use "Discover" to Find Sources You Didn't Have

If you don't have enough source material yet, use the Discover feature inside a notebook - describe what you're researching, and it suggests relevant web sources you can add with one click. This turns notebook-building from "gather everything manually" into a guided process.

Gemini Notebook (formerly NotebookLM) full free course: Deep Research, Audio Overviews, and advanced workflows — taught start to finish, right here.

Module 4: The Chat Panel - Prompting a Grounded AI Correctly

Because Gemini Notebook only answers from your sources, prompting it well is a different skill from prompting ChatGPT. Generic prompts get generic answers even here - the grounding doesn't fix a lazy question.

Four Prompting Techniques That Actually Change Output Quality

1. Ask it to cite before you trust it. Every answer comes with inline citations pointing back to the exact source passage. Don't skip these - click through and verify anything you're going to use in real work. This is the tool's biggest safety feature, and most people ignore it entirely.

2. Chain follow-ups instead of restarting. Chat history is now saved across sessions, so you can leave a research thread, come back a day later, and keep building on it rather than re-explaining context. Use this - ask a broad question first, then narrow with follow-ups: "Now compare that to what source 3 says" or "Which of these claims has the weakest source support?"

3. Ask it to disagree with itself. A genuinely advanced move: "Find any contradictions between my sources on this topic." Because it's grounded in multiple documents, it can actually surface where your sources conflict - something a single-document read-through would miss.

4. Use it to interrogate gaps. Ask: "What questions do my current sources leave unanswered?" This tells you exactly what to go find next, turning the chat into a research-gap-finder, not just a Q&A box.

Module 5: Deep Research - The Feature Nobody Teaches Properly

This is the most advanced capability in the tool, and it's the one this course spends the most time on, because it's genuinely underused.

What Deep Research Actually Does

Deep Research runs a multi-step investigation rather than a single-turn answer. Instead of pulling from only what you've uploaded, it can go out, gather additional material relevant to your question, synthesize it against your existing sources, and return a structured report - with reasoning steps you can inspect, not a black-box answer.

How to Run a Deep Research Session

Inside your notebook, look for the Deep Research option (in the Studio panel or chat input area).
Write your research question as a scope, not a fact-lookup. Bad: "What is X?" Good: "Investigate the main arguments for and against X, who's making each argument, and what evidence they cite."
Let it run. Unlike a chat answer, this takes longer - it's doing multi-step work, not returning instantly.
Review the report's reasoning trail. Because it shows its steps, you can see where a claim came from, not just what the claim is.
Feed the output back into your notebook as a new source, so future chat questions can reference the research you just generated.

Three Real Deep Research Use Cases

Competitive analysis: "Research how our three main competitors have priced this feature over the last 12 months, and what public criticism each has received." Upload whatever internal documents you have first, then let Deep Research fill the external gaps.

Literature review: Upload 10-15 papers on a topic, then run: "Synthesize the current consensus and disagreements across these papers, and identify which findings are most frequently cited by the others." This alone can save hours of manual cross-referencing.

Due diligence: Before a big purchase, partnership, or decision - "Research the track record, controversies, and independent reviews of [company/product], separating verified claims from marketing language."

Quota reality check: Free gives you 10 Deep Research sessions a month - use them on questions that genuinely need multi-step research, not things a normal chat question would answer just as well.

Module 6: The Studio Panel - Turning Sources Into Other Formats

This is where Gemini Notebook stops being "a chat with your documents" and becomes a content production tool. Everything in Studio pulls from the same grounded sources you already added - you're not starting over each time.

Audio Overviews (The Feature That Made This Tool Famous)

Click Audio Overview in Studio and it generates a podcast-style conversation between two AI hosts discussing your sources. Most people generate the default and stop there. Here's the advanced move:

Use the focus/customization prompt. Before generating, you can steer it: "Focus specifically on the financial risks discussed in these documents" or "Explain this at a beginner level, avoid jargon." A generic Audio Overview and a focused one are dramatically different in usefulness.
Generate multiple angles from one source set. Run it once for a general overview, then again with a narrow focus prompt for a specific subtopic - you get two different, useful outputs from the same uploaded material.

Video Overviews

A narrated slide-deck style video generated from your sources - think of it as the visual sibling of the Audio Overview. On the Ultra tier specifically, you get Cinematic Video Overviews, built using Google's Veo 3 model for a fully animated, produced look rather than static slides.

Mind Maps, Study Guides, Flashcards & Quizzes

These four are built for learning and retention:

Mind Maps - a visual, clickable structure of how concepts in your sources relate to each other. Genuinely useful for untangling a dense document before you read it linearly.
Study Guides - a structured outline/briefing document, ideal for exam prep or onboarding someone quickly to a topic.
Flashcards & Quizzes - auto-generated from your sources, with a "Got it / Missed it" sorting system so repeat review focuses on what you actually don't know yet, and progress saves across sessions.

Slide Decks with Export

Generate an actual slide deck from your notebook's sources, then export it as an editable PowerPoint (PPTX) file - or as an editable PDF - and refine it further in your own tools without losing formatting.

Module 7: Power-User Workflows (Where This Course Goes Further Than Anyone Else)

Automate Recurring Research with Workspace Studio

If you're on a Workspace/Business plan, a newer capability lets you add a Workspace Studio step that automatically refreshes a notebook's sources on a schedule - pulling in new text, Drive links, YouTube URLs, or web pages without you manually re-adding them each time. This turns a one-off notebook into a living research feed for something you track continuously (a competitor, a market, an ongoing project).

Copy a Notebook Instead of Rebuilding It

You can now copy an entire notebook, including its sources and Studio outputs (Audio/Video Overviews, Study Guides, Flashcards, Quizzes, Slide Decks) - though personal chat history and notes don't carry over. Use this to create a clean template notebook once, then duplicate it for every new project instead of rebuilding structure from scratch.

Share Research with a Single Public Link

Notebooks can now be shared publicly via a single link - useful for publishing a research summary, a study guide for a class, or a briefing document for a team, without giving people edit access to your source material.

Run Parallel Notebooks, Not One Mega-Notebook

Advanced users keep 3-5 active notebooks per ongoing project area rather than one notebook for everything. A "competitor tracking" notebook, a "personal learning" notebook, and a "current project" notebook, each tightly curated, will consistently outperform one sprawling notebook - this comes straight back to the curation principle in Module 3.

Module 8: Four Complete Projects, Start to Finish

These are full walkthroughs, not just ideas. Follow any of these end to end as practice.

Project 1: Turn Research Papers Into a Literature Review + Slide Deck

Create a new notebook. Upload 10-15 PDFs of papers on your topic.
Run a Deep Research session: "Identify the major schools of thought represented across these papers and where they disagree."
Feed that report back in as a source.
Chat: "Draft a literature review structure organized by theme, not by paper."
Generate a Slide Deck from the notebook, export as PPTX, and refine formatting in PowerPoint.

Project 2: Build a Personal Knowledge Base From a YouTube Channel

New notebook. Add 15-20 video links from a channel you learn from regularly.
Generate a Mind Map to see how the channel's core topics connect.
Generate an Audio Overview with a focus prompt: "Summarize the three most repeated pieces of advice across these videos."
Generate a Study Guide to keep as a permanent reference document.

Project 3: Competitive Analysis for a Business Decision

New notebook. Upload any internal documents you have on your product/pricing.
Run Deep Research: "Research how [Competitor A], [Competitor B], and [Competitor C] position and price this feature, and summarize public customer complaints about each."
Chat follow-up: "Which competitor's approach has the most independent criticism, and what specifically is criticized?"
Generate a Slide Deck to present findings to your team.

Project 4: Exam Prep Pipeline for Students

New notebook. Upload your course readings, lecture slides, and any lecture recordings (as audio or video sources).
Generate a Study Guide for a structured overview.
Generate Flashcards and Quizzes, using the "Got it / Missed it" sorting to focus repeat study time.
Generate an Audio Overview to review passively while commuting.
Before the exam, chat: "What are the three concepts I'm most likely to get wrong based on how often they're emphasized versus how nuanced they are?"

Module 9: Limitations, Quotas & Privacy - What to Actually Expect

No course is complete without the honest limitations section.

It can only know what you give it. This is the core strength and the core limitation. It won't reason about current events or facts outside your sources unless you're specifically using Deep Research to pull in outside material.
Source caps are real. 500,000 words or 200MB per individual source, 50 sources per notebook on Free. Very large documents may need splitting.
Daily/monthly resets matter. Deep Research on Free is monthly (10/month), not daily - plan which questions are worth spending one on.
It's cloud-only. Gemini Notebook needs an internet connection and processes your files on Google's servers - it's not an offline, on-device tool. If strict data locality is a requirement, this matters.
Admins can disable it org-wide. There's no per-user toggle for most of these features in a managed Workspace account - if it's missing at work, that's likely an admin-level setting, not something you can turn on yourself.

Module 10: Quick-Reference Cheat Sheet

Task	Where to Go
Start a new project	New Notebook → add 5-15 tightly relevant sources
Find more sources	Discover panel inside the notebook
Multi-step investigation	Deep Research (scope it as a question, not a fact lookup)
Passive review / commute learning	Audio Overview with a focus prompt
Present findings	Slide Deck → export as PPTX
Exam/test prep	Study Guide + Flashcards + Quizzes
Reuse a notebook structure	Copy Notebook
Share results externally	Public share link

FAQ

Is Gemini Notebook the same as NotebookLM?

Yes. Google renamed NotebookLM to Gemini Notebook on July 16, 2026. The tool, its features, and its pricing structure stayed identical - only the name and web address (now notebook.google.com) changed.

Is Gemini Notebook actually free?

Yes, genuinely. The free tier includes 100 notebooks, 50 sources per notebook, 50 chat questions a day, 3 Audio Overviews and 3 Video Overviews a day, and 10 Deep Research sessions a month - no credit card required.

What's the difference between Gemini Notebook and regular Gemini chat?

Regular Gemini answers from its general training data plus anything you type. Gemini Notebook answers only from the specific sources you upload into that notebook, which drastically reduces made-up answers for research and study tasks.

How is Deep Research different from a normal chat question?

A normal chat answer responds in one step from your existing sources. Deep Research runs a multi-step investigation, can gather additional relevant material, and returns a structured report with an inspectable reasoning trail - built for genuine research questions, not quick lookups.

Do I need to pay to use Audio Overviews or Deep Research?

No - both are available on every tier, including Free. Paid tiers only raise how many you can generate per day/month; they don't unlock the features themselves. The one true paid-exclusive feature is Cinematic Video Overviews, which requires Ultra.

Can Gemini Notebook work with YouTube videos?

Yes. Paste a YouTube link as a source and it works from the video's transcript, making long lectures, interviews, or tutorials fully searchable and chattable.

Why does my notebook give vague answers?

Almost always because too many loosely related sources have been added at once. Rebuild the notebook with fewer, more tightly relevant sources - this is the single biggest quality fix available to you.

Can I use Gemini Notebook offline?

No. It requires an internet connection and processes your files on Google's servers - there's no offline or on-device mode.

The Complete Gemini Notebook (NotebookLM) Course: Free, Advanced, Start to Finish