NotebookLM Tutorial (Gemini Notebook): A Complete Guide for Your Documents

NotebookLM Tutorial (Gemini Notebook): A Complete Guide for Your Documents

Create a notebook, add sources, check citations, and make Persian audio overviews, quizzes and slides in NotebookLM, now Gemini Notebook, with limits, Iran status and an open-source option.

ZharfAI TeamNovember 16, 202630 minutes

NotebookLM is Google's research notebook that answers from the sources you give it: you put PDFs, Google Docs, web pages, YouTube videos or audio files into a notebook, ask questions, and get answers with citations that point back to sentences in those sources. You can also turn the same sources into audio overviews, quizzes, flashcards, slide decks or infographics. The workflow has four steps: create a notebook, add sources, ask in the Chat panel, and open every citation to confirm the claim is really in the source.

On July 16, 2026 Google renamed the tool Gemini Notebook and said it remains the same standalone product. According to the Workspace announcement, automatic redirects keep old links and shared notebooks working, and mobile users may need to update the app. This guide uses both names, because most people still search for NotebookLM.

This tutorial was checked on November 16, 2026 against Google's official Gemini Notebook help pages, the Google blog, and the Google Terms of Service. It is written for teachers, students, language learners and office workers who want exact steps and an honest account of where the tool goes wrong. If you searched for "notebook lm", "Google NotebookLM tutorial" or "Gemini Notebook tutorial", this is the same product.

Is NotebookLM available in Iran?

Short answer: no. This section states what Google's own pages say, with a source for each point. It is not legal advice.

  • Iran is not on the supported-countries list. The Learn about Gemini Notebook page says the browser version is offered to users above the age of consent in supported countries and territories, and it prints the list. In the list we read on the review date, Iraq is followed directly by Ireland, and Iran does not appear. The same page says the mobile app has a separate availability list.
  • Paid plans follow the same map. The Gemini Notebook plans page says Plus, Pro and Ultra access exists only in the regions where those Google AI plans are available, and Iran is not on the Google AI Pro country list either.
  • The Gemini app route is closed too. The Gemini web app country list does not include Iran, so creating notebooks inside Gemini is not another door.
  • Google's terms require sanctions compliance. The Google Terms of Service, effective July 30, 2026, ask users in the conduct rules to comply with applicable laws, including export control and sanctions laws. Google's pages for this tool do not explain why any particular country is absent.

So Gemini Notebook is not a service Google offers in Iran, and this guide gives no method for getting around that. The tutorial sections below are for readers who live in a supported country. If you are in Iran and want the same experience, asking questions of your own documents and getting cited answers, the "open-source alternative" and "organisational version" sections further down this page describe running the same pattern on your own computer or servers; read the open-source section's note on where its software is downloaded from. To compare domestic services with foreign tools, use the criteria in our guide to choosing between Iranian and foreign AI tools, and if you need a language model over an API, our guide to AI API access in Iran compares the lawful options.

NotebookLM website tutorial: create a notebook and learn the three panels

A notebook is the set of sources for one project, and each notebook is independent: the create-a-notebook guide says the tool cannot read across several notebooks at once. Make one notebook per course, case or project.

  1. Open notebook.google.com and sign in with your Google Account. Some features require age verification on the account.
  2. Click Create new notebook.
  3. Choose the sources to upload, or search for new ones. You can add more later with Add sources in the Sources panel.
  4. Once a source is in, the screen has three panels:
    • Sources: the source list, with a checkbox beside each item. Untick a source and it is left out of answers and outputs. With five or more sources, the tool labels and groups them automatically, and you can rename, delete or move labels.
    • Chat: where you ask questions and get answers with citations.
    • Studio: where outputs, from Audio Overviews to slide decks, are generated and kept.
  5. From Settings at the top of the page, set Output Language (Persian, if that is what you want). Your usage is shown in the same menu, under Usage.

In the Sources panel click Add sources and pick the type. The add sources guide lists every type and its limits:

Source typeWhat is importedKey limit
PDF, Word (docx), plain text, Markdown, CSV, PowerPoint (pptx), ePubThe file's textUp to 200 MB and 500,000 words per file
Google Docs, Slides and Sheets from DriveThe file content, re-synced every few minutesFootnotes and comments are not imported; Slides up to 100 slides; Sheets up to 100k tokens; several tabs become one source
Web URLThe page's text onlyNo images, embedded videos or nested pages; paywalled pages unsupported
YouTubeThe caption text onlyPublic videos with captions only; videos under 72 hours old may fail; deleted videos leave the notebook within 30 days
Audio file (mp3, wav, m4a and many more)A transcript made at importAudio without speech is unsupported, and low-quality audio may fail to import
Image (jpg, png, heic, webp and others)The imageGoogle says some image types may not work as well
Copied textA note that counts as a sourceYou set its title when you create it
Play BooksText onlyPurchased, eligible titles only; depending on the publisher, outputs from such a notebook may not be downloadable

Behaviour worth knowing in advance:

  • Drive sync is one-way. Changes to the original reach the source when you open the notebook, but the tool never edits or deletes your Drive file. If you lose access to the file, the source goes inactive but still counts toward your source limit.
  • Old outputs do not update. If you change or delete a source, Audio Overviews or quizzes you made earlier stay as they were. Regenerate outputs after changing sources.
  • Add several links at once. Separate multiple web URLs with spaces or new lines.
  • Discover sources. Type a research question into the search box in the Sources panel and choose Web or Drive, and Fast Research lists results with a short note on how each relates to your question. Turn on Deep Research and the tool spends a few minutes browsing and returns a report plus its source list, which you can import in full or in part. Deep Research is for users over 18.

Asking questions and checking citations in Chat

The chat guide says the tool uses direct quotes, text and images from your sources as citations. Hover over any citation to see the full quoted text, and click it to open the source at that spot. The right habit is to make that click for every claim that matters.

To set the answer style, click Configure Chat in the Chat panel and pick one of three styles: Default for research and brainstorming, Learning Guide for learning a new concept, and Custom to set a role or tone. Set the response length in the same place.

Good questions in this tool share three traits. They name the source, because Google says naming sources narrows the search when many are selected. They ask for verbatim quotes. And they say what to do when the answer is missing. For example:

In the source "Lease contract 2026", list the termination conditions. For each one,
give the clause number and the exact sentence. If the contract is silent on a point,
write "not in the source".

For writing more precise requests, see our prompt writing guide. A few other tools in the same panel:

  • Save to note keeps an answer with its tables and citations. The notes guide says notes are themselves sources and get cited in later answers. If you want answers only from the original documents, untick your notes so your own summary does not stand in for evidence.
  • Narrow the selection: ask about Annex 2 of a contract with only that annex ticked.
  • Chat history is private to you and can be cleared with Delete Chat History from the panel's three-dot menu. If a request is running, press Stop to revise it.

Know one recent change. The same guide has a section on agentic capabilities: chat can search the web, run code, and create files such as charts, Word documents, Excel workbooks and PowerPoint decks, "with or without sources". Google calls these functions experimental and warns that they can do unexpected things. So "answers come only from your sources" holds for normal question answering, not for everything you can do in Chat. When the tool has searched the web, open citations with extra care.

Studio outputs: Audio and Video Overviews, reports, quizzes and slides

Every output is made in the Studio panel. Each has a pencil icon that opens a customisation panel before generation. Creating or deleting outputs requires edit access to the notebook, and outputs are generated in the background.

OutputMain optionsDownload or exportLimit
Audio OverviewDeep Dive, Brief, Critique and Debate formats; language; length; focus promptAudio file download
Video OverviewCinematic, Explainer and Short formats; visual style; focus promptVideo downloadSometimes takes more than 30 minutes
Mind MapMade from its button in the Chat panel and kept as a note in Studio; clicking a node asks about that topic in ChatDownloadNot in the mobile app
ReportsInteractive or Document; templates for FAQ, study guide, briefing doc or a custom reportExport to Docs; tables via Export to SheetsCustomising a report is web-only
Data TableA prompt describing the rows and columns you wantExport to Sheets; citations on the second tab
Flashcards and QuizzesEasy, medium or hard; promptFlashcards as CSV
Slide DeckFormat, language, length, sources, promptPDF or PowerPoint (pptx)18+ only
InfographicVisual style, promptPNG image18+ only

What the table does not say:

  • Audio Overviews. In the Audio Overview guide, Deep Dive is a two-host conversation, Brief delivers the key points with a single speaker in under two minutes, Critique gives constructive feedback on a text, and Debate is a formal two-host debate. Of the length options, Longer is English-only. Interactive mode is English-only too: you press Join during playback and ask the hosts questions by voice.
  • Video Overviews. In the Video Overview guide, Short runs about 60 seconds. Turn on Review producer notes to see and refine the producer notes before rendering, but after you press Proceed they can no longer be changed.
  • Reports. An interactive report built on the Learning Overview template embeds other Studio outputs. Exported Docs or Sheets files do not stay in sync with the notebook and do not inherit its sharing permissions.
  • Flashcards and quizzes. In flashcards and quizzes, Explain explains an answer and Hint helps on a quiz question. Progress is saved, and at the end you see your results and can review or retake.
  • Slide decks. In a slide deck, Revise takes instructions per slide, but sources are not consulted during revisions and every revision creates a whole new deck that counts against quota, so batch your changes.
  • Infographics. Google warns explicitly that infographics and slide decks may contain visual or factual inaccuracies. In Persian output, read every word rendered inside the image.

Every output, including the voices, is AI-generated, and Google reminds users that it may contain inaccuracies or audio glitches. If you want to analyse the numbers in a data table further, the work moves into a spreadsheet; our guide to AI in Excel covers cleaning Persian data, Jalali dates and testing formulas.

Persian support in NotebookLM

Chat answers, reports and Audio Overviews can be produced in Persian, but several features are English-only. The output language page lists Persian among more than 80 languages and says study guides, documents, Audio Overviews, Video Overviews and chat answers follow that setting. The default is the preferred language of your Google Account; change it under Settings then Output Language.

AreaPersian statusKey limit
Chat answers, reports, study guidesPersian is in the output-language listSet the language in Settings
Audio OverviewsCan be generated in 80+ languagesThe Longer length option and interactive mode are English-only
Video OverviewsExplainer and Short formats list PersianCinematic is English-only and 18+
Uploaded audio filesPersian is in the transcription listLow-quality audio may fail to import
YouTube videosOnly the caption text is importedImport fails if the video language is unsupported
Slide decksLanguage is chosen in the customisation panelRead every Persian word on the slides
Menus and interface labelsNot confirmedWe found no page separate from the output language

We found no page that documents the interface language, so the Persian edition of this guide gives each button's English label with a Persian equivalent beside it.

Can NotebookLM read scanned PDFs and handwritten Persian?

Many Persian documents are scans: old textbooks, office letters, signed contracts. In a November 13, 2025 announcement, Google added image sources and said you can upload "a photo of your hand-written notes or a brochure". The sources guide, however, warns that certain types of images may not work as well. We found no official page that explains how an image-only PDF, one without a text layer, is read, or how accurately scanned Persian script is recognised. So before you rely on a scanned document, run this test:

  1. Upload the file and open the source from the Sources panel. Google says the viewer may look different from the original file because it shows the content prepared for analysis. If the viewer is empty, or Persian letters appear reversed or disconnected, the tool does not have usable text.
  2. Ask a quote-based question, such as "quote the first sentence of the second paragraph on page 12 verbatim", and open the citation. If the quote differs from the page, do not trust later answers from that source.
  3. Ask for a specific number or name from the middle of the document. One wrong digit or letter in a number or name changes its meaning, yet it is easy to miss in flowing text.

If the document fails, convert it to text before uploading. For a few key pages, such as a table of contents or one important table, our free Persian OCR tool reads one page at a time, is free for up to 6 pages a day and 3 an hour, and returns tables as tables. It sends the page to an AI service outside Iran for reading and does not keep the file, so do not use it for confidential documents. Paste the result into the notebook as Copied text from the add-sources window, and put a line such as "Page 12" before each page so citations map back to real page numbers. For a 300-page book this route is not practical; reading whole scanned archives belongs to the organisational version described near the end.

NotebookLM for teachers: a lesson and a quiz from a textbook chapter

Say you teach eighth-grade science and want a lesson plan, a ten-question quiz and vocabulary cards for a chapter about atomic structure.

  1. Create a notebook named after the chapter. Upload only material you have the right to use; Google's sources guide says to avoid uploading documents you do not have rights to. The chapter PDF, your own lesson notes and the curriculum objectives make three good sources.
  2. If the chapter is a scan, run the scan test above.
  3. Ask in Chat: "List the learning objectives of this chapter with page citations, and tell me which objective my notes do not cover."
  4. In Studio, open Reports and generate the study guide template, or ask for a custom report: "a 45-minute lesson plan with three class activities and an exit question".
  5. Open Quizzes with the pencil icon, set difficulty to medium, and write: "Ten multiple-choice questions from sections 2 and 3, with wrong options that reflect common student misconceptions."
  6. Generate Flashcards for key terms and download the CSV.
  7. If you want a class presentation, generate a Slide Deck and batch your corrections in one Revise pass.
  8. Before using anything, check every quiz question and answer key against the textbook. The quiz is built from your source, but the questions and answers are AI-generated.

If you share the notebook with students, give viewer access and remember that chat view does not fully hide the sources. Slide decks, infographics and Deep Research are closed to users under 18, but on Workspace for Education accounts the service itself is open to all ages.

A student can use the same routine to prepare for an exam: one notebook per course with class notes, the lecturer's slides and any past questions you are allowed to use; the Learning Guide chat style; a question asking which concepts appear in past questions but not in your notes; and a quiz set to hard. The night before the exam, do not ask the tool to confirm "the right answer"; open the citation for every important answer and compare it with your notes.

Learning a language with NotebookLM

The tool is not a language teacher, but it builds practice from sources you choose. A workflow for a Persian speaker learning English:

  1. Add a public YouTube video with English captions, a web article, or a podcast audio file as a source.
  2. Ask in Persian: "List 20 important words or phrases from this source with their Persian meaning and a sentence from the source."
  3. Build the same list as a Data Table, describing the columns: word, Persian meaning, example sentence from the source. Export it to Sheets as your personal vocabulary list.
  4. Generate flashcards and quizzes. For English comprehension questions, switch the output language to English before generating or name the language in the prompt; keep Persian for meaning drills.
  5. Generate an English Audio Overview and say in the prompt that it is for an intermediate learner. Listen to the result; a prompt does not guarantee the pace or vocabulary level.
  6. Use interactive mode for conversation practice: press Join during playback and ask your question aloud. The mode is English-only, which suits this exercise.

Know the limits: the tool does not assess your pronunciation, and if a grammar rule is not in your sources it may not answer a grammar question. For languages other than English, check the output-language list and the audio-transcription list separately.

Sharing a notebook with colleagues, students or the public

  1. Open the notebook and click Share.
  2. Enter the person's email address and choose Viewer or Editor access. A viewer can read the shared sources and notes; an editor can add or remove sources and notes and can share the notebook further.
  3. Copy the link. Copy link to chat view gives a link that shows only the chat.

Three points from Google's guide that are often missed:

  • Chat view does not revoke access. Google states that chat view hides sources and outputs for focus, but viewers may still find their way to them. If a source must not be seen, do not put it in a shared notebook.
  • Personal accounts share with up to 50 people. A personal Gmail account can share a notebook with up to 50 users and cannot share with Google Groups.
  • Allow copies deliberately. With Allow copies, recipients can duplicate the notebook with its sources and outputs.

For public sharing, set access to Anyone with a link. Public sharing is enabled only for personal accounts and is disabled for Workspace enterprise and education accounts. Each output, such as a Video Overview, also has its own link, provided the notebook itself is shared with the recipient or public.

How to install NotebookLM and use the mobile app

The desktop version needs no installation; it runs in the browser. According to the mobile app guide, the app is available for Android 10 and later and for iPhone and iPad, listed as Gemini Notebook in the Play Store and App Store. It is rolling out gradually and may not yet be available in every country.

The app is not the full product, and Google itself recommends the desktop version for the complete experience. Current app limits:

  • It accepts only PDF, website, YouTube, audio file and copied text as sources.
  • Notes, mind maps, reports and data tables cannot be generated in the app, and notes cannot be edited there.
  • Audio Overviews can be downloaded for offline playback inside the app, but not saved as a file on the phone.
  • Live voice conversation with a notebook is available only in the mobile app and only to users over 18.

The app's advantage is the share sheet: from any web page, PDF or YouTube video you can send the item straight into one of your notebooks.

Limits, plans and privacy in November 2026

The table below gives personal-account limits from the Gemini Notebook plans page. Google labels these limits "subject to change".

LimitNo planPlusProUltra (20 TB)Ultra (30 TB)
Notebooks per user100200500500500
Sources per notebook (excluding notes)50100300500600
Note sources per notebook500500500600600

The usage limits page explains that day-to-day use is metered by compute, not by a simple count: prompt complexity, model, chat length and output type all count. The quota refreshes every 5 hours until you reach a weekly limit. Plus gives twice the standard limit, Pro four times, and Ultra 5 or 20 times the Pro limit. Check usage under Settings then Usage; if you run out, Generate later in the Studio panel queues an output for a couple of hours later. Limits for Workspace work and school accounts are on a separate page. We give no prices: these pages do not list them, and prices depend on your country.

What Google does with your sources. According to the privacy and terms page, notebook content is not used to directly train Google's foundation models unless you give feedback. If you press thumbs up or down, the related prompts, sources, uploads and outputs are collected, reviewed by specially trained teams, and kept for up to 3 years, disconnected from your Google Account. For Workspace and Workspace for Education users, uploads and answers are not reviewed by humans even with feedback and are not used for training. Data that Gemini Notebook shares with other Google services such as the Gemini app is used under Google's Privacy Policy, which the same page says includes product improvement.

Before uploading a work document, check whether your organisation's policy allows it to go to an external cloud service. The Learn about Gemini Notebook page tells users to consult a qualified professional for medical, legal or financial advice; treat the tool's output as a starting point for reading, not an expert opinion.

The open-source alternative: Open Notebook on your own computer

Open Notebook is an MIT-licensed project whose authors describe it as "an open source, privacy-focused alternative to Google's Notebook LM". It has notebooks, sources, chat over sources, notes and podcast generation, and connects to more than 20 model providers, including Ollama for running models on your own hardware. The latest release on the review date was 1.15.1, published November 4, 2026. The interface languages listed in the README do not include Persian; the language of answers depends on the model you connect. It is a single-user tool; its README lists multi-user support among directions "under consideration", described as "directions, not dated promises".

The project's fully local quick start runs Open Notebook and Ollama side by side in Docker. Its prerequisites are Docker with Compose v2, at least 8 GB of RAM, and a few gigabytes of disk for models. The steps:

bash
mkdir open-notebook
cd open-notebook
curl -o docker-compose.yml https://raw.githubusercontent.com/lfnovo/open-notebook/main/docker-compose.yml
echo "OPEN_NOTEBOOK_ENCRYPTION_KEY=$(openssl rand -hex 32)" > .env

These commands are for macOS and Linux. For Windows PowerShell, the official guide says to use curl.exe instead of curl, and it covers generating the encryption key on Windows in the project's Docker Compose installation guide.

Then create docker-compose.override.yml in the same folder to add the Ollama service:

YAML
services:
  ollama:
    image: ollama/ollama:latest
    volumes:
      - ./ollama_models:/root/.ollama
    restart: always

Start the stack and pull one chat model and one embedding model:

bash
docker compose up -d
docker compose exec ollama ollama pull qwen3
docker compose exec ollama ollama pull nomic-embed-text

Open http://localhost:8502, add the Ollama provider with no API key and the base URL http://ollama:11434, add the chat model as a Language model and the embedding model as an Embedding model, and click Auto-assign Defaults. Points that are easy to miss:

  • Network exposure. Per the same guide, the UI on port 8502 and the API on port 5055 are published on all network interfaces with no password by default. If other devices can reach the machine, bind the ports to 127.0.0.1 or set OPEN_NOTEBOOK_PASSWORD in .env before you start.
  • Where the downloads come from. The images in this setup come from Docker Hub, and the Docker Terms of Service bar the use of its services, and the re-export of content obtained through them, to countries under a US embargo. The models come from the Ollama library through ollama pull. We have not tested whether these addresses are reachable from inside Iran; read each service's terms yourself before you plan around this route. Installing Ollama outside Docker is covered in our Ollama installation tutorial.
  • Speed. Without GPU access the models run on the CPU and are slow. If answers time out, use a smaller model or enable GPU access.
  • Podcasts. Ollama provides chat and embedding models only. Podcasts need a separate text-to-speech server; for Persian voices, see our Persian text-to-speech guide.
  • Scanned documents. The official docker-compose.yml has an optional line, OPEN_NOTEBOOK_ENABLE_DOCLING=true, which, once uncommented, installs the Docling engine with OCR and image sources. It is a large download that slows the first start; measure its accuracy on your own Persian pages.
  • An embedding model for Persian. The guide's example embedding model is nomic-embed-text. The bge-m3 page in the Ollama library says that model supports more than 100 languages. Try both on your own real questions before you choose.

Where it goes wrong, and how to tell

Answers limited to the sources

The Learn about Gemini Notebook page gives three reasons the tool may not answer: the source content triggered a safety flag (even on topics such as violence in a historical text), the question was unclear and the tool could not find the relevant part of a source-heavy notebook, or the answer is simply not in the sources. According to the chat guide, creative requests, such as rewriting the ending of a story, may also get a "can't answer this question" reply. That behaviour is not a defect; the tool is built for sourced answers.

Citation errors

Having a citation is not the same as being right. A citation may point to a nearby sentence that does not support the claim, or a number may be misread from a table. Google also says that when a source is very short, the tool cites the whole document rather than a sentence. Three simple tests: open the citation and check that the sentence says what the answer claims; match numbers against the source; and keep your own notes, which have become sources, apart from the original evidence. The reasoning behind that check, separating "the answer is faithful to the source" from "the source is correct", is set out in our article on retrieval discipline and knowledge quality.

Long Persian documents

The per-source limit is 500,000 words, but Google says that in a source-heavy notebook the most relevant parts are retrieved first and the answer is built from them. A broad question about a whole book can therefore miss an important section. We found no documentation on retrieval quality for long Persian text, so test it: upload a book chapter by chapter with clear names, restrict a question to one chapter, and ask a question you already know the answer to from the end of the document to see whether it is found.

Persian and mixed Persian-English text

We found nothing in Google's documentation about how the tool handles right-to-left text. Treat these as checks to run, not confirmed behaviour:

  • If a document was typed with an Arabic keyboard layout, Arabic "ي" and "ك" replace Persian "ی" and "ک", and one word ends up stored in two forms. If an answer is not found, ask with both spellings.
  • Check Persian and Latin digits in output tables against the original, especially amounts and dates.
  • In bilingual text, Latin names in the middle of a Persian sentence can disturb display order; compare the sentence with the source before quoting it in a formal report.

The organisational version: asking questions of company documents on your own servers

What NotebookLM does is a well-known pattern: documents are indexed, the passages relevant to each question are retrieved, and a language model writes the answer with citations to those passages. The same pattern can run on an organisation's own servers with open language models, so that no document leaves the organisation's network. The organisational version differs from a personal notebook in things a single-user tool does not have:

  • Access control: each employee gets answers only from documents their role is allowed to see, and that filter applies before retrieval, not after the answer is generated.
  • Reading scanned documents: scanned letters and contracts are converted to text page by page on the same server, keeping page numbers for citations.
  • Logging and audit: the question, retrieved passages and answer are recorded with user and time.
  • A Persian evaluation set: a few dozen real questions with answers and authoritative passages, so every change of model or index is measured against them.

In our view, document quality and retrieval matter as much as the model in these systems; the retrieval-discipline article linked above sets out why. If you want the same experience for your organisation's documents on your own servers, our page on private AI on your organisation's servers explains how we work.

Frequently asked questions

Is NotebookLM free?

Yes. Without a paid plan you can have 100 notebooks with up to 50 sources each, with a usage quota that refreshes every 5 hours up to a weekly limit. Plus, Pro and Ultra raise the limits. The service, free or paid, is not offered in Iran.

Is Gemini Notebook the same as NotebookLM?

Yes. On July 16, 2026 Google renamed NotebookLM to Gemini Notebook and said it is the same standalone product. Old links redirect to the new address, so any NotebookLM tutorial and any Gemini Notebook tutorial describe one tool.

Does NotebookLM speak Persian and make Persian podcasts?

Persian is in the output-language list and Audio Overviews can be generated in more than 80 languages. The Longer Audio Overview length, interactive mode and the Cinematic Video Overview format are English-only. Listen to the Persian voice quality yourself; Google says voices may contain inaccuracies or glitches.

Do I need to install anything to use NotebookLM?

No. The desktop version runs in the browser. The Android and iOS apps are optional and lack some features, such as mind maps and reports.

Does Google train its models on my files?

According to the Gemini Notebook privacy page, notebook content is not used to directly train foundation models unless you give feedback. Content attached to feedback is reviewed by humans and kept for up to 3 years. On Workspace accounts, there is no human review or model training even with feedback.

What is the difference between NotebookLM and Gemini?

You can also create and open notebooks inside the Gemini app, and changes sync between the two apps. But according to the help page on notebooks in Gemini Apps, chat answers inside Gemini Notebook are grounded only in your notebook sources, while in the Gemini app they may also use web search and other tools. For answers that come only from your sources, open the notebook in Gemini Notebook itself.

Source Notes

This guide was reviewed on November 16, 2026 against Google's official Gemini Notebook help pages, the Google blog, a Google Workspace announcement, the Google and Docker terms of service, and Open Notebook's official documentation. Limits, feature names and country lists are vendor statements and change without notice; check the linked page again before you decide. The steps, labels and behaviour described here come from Google's documentation, and we did not operate the product itself for this review; wherever the documentation was silent, we say so.

TagsNotebookLMGemini NotebookNotebookLM TutorialGoogle AIDocument Q&AAI for TeachersStudy Tools

Related Posts

Run this inside your own team

If you want the agents and automation in this guide working for your engineering team or business processes, start with a small pilot you can measure.