# What is NotebookLM (now Gemini Notebook) and how to use it for work > NotebookLM, now Gemini Notebook, is Google's AI research tool that answers only from sources you add, with citations. How it works and how to use it at work. - URL: https://computese.com/unlocking-efficiency-and-precision-googles-ai-powered-notebooklm-now-available-to-us-users/ - Author: Duong Quan Nguyen, CEO, Computese - Published: 2023-12-10 - Updated: 2026-09-25 - Topics: AI & automation ## In short - NotebookLM is Google's AI research assistant: it answers questions and writes summaries from the sources you add, with inline citations back to the passages. Since July 16, 2026 it is called Gemini Notebook. - It began as Project Tailwind at Google I/O 2023, opened to U.S. users aged 18 and up in December 2023 on Gemini Pro, reached over 200 countries in June 2024 and began moving to Gemini 3.5 in June 2026. - A free account holds up to 50 sources per notebook, each up to 500,000 words or 200 MB: PDFs, Word and Google files, web pages, YouTube videos, audio and images. Sources imported from Drive stay in sync. - Where your Workspace edition includes it as a core service, Google says uploads, chats and outputs are not reviewed by people or used to improve AI models. On a personal account, sending feedback changes that. - Grounding makes errors less likely, not impossible: open the citation behind any figure, date or obligation before it goes into your work. NotebookLM is Google's AI research assistant. You add your own sources, such as PDFs, Google Docs, web pages or recordings, and it answers questions and writes summaries from those sources only, with citations that open the passages the answer came from. Since July 16, 2026, Google calls it Gemini Notebook. This page first covered NotebookLM in December 2023, when Google opened it to everyone in the U.S. aged 18 and up. The product has changed a great deal since, so this is now a dated explainer: where it came from, how its source grounding works, what you can upload and how much, a walk-through for your first notebook, how Google handles your data on personal and work accounts, where it fits in a business and where it still goes wrong. ## What NotebookLM is, and why it is now called Gemini Notebook NotebookLM started as a Google Labs experiment built around one idea: a notebook with a language model at its core (the "LM" in the name) that works from material you choose rather than from everything it absorbed in training. [Google's July 2023 launch post](https://blog.google/innovation-and-ai/technology/ai/notebooklm-google-ai/) called this source grounding. A notebook is a collection of sources for one project. The model reads them, summarizes them and answers questions about them, and each answer carries inline citations that point to direct quotes, text or images in your sources. The difference from a general chatbot is the boundary. Google's help pages say chat responses only use data from your sources, and if the answer is not in the source material, [it won't provide a response](https://support.google.com/gemininotebook/answer/16269187). That makes it a tool for understanding documents you already trust, not for asking the internet a question. On July 16, 2026, Google [renamed NotebookLM to Gemini Notebook](https://blog.google/innovation-and-ai/products/gemini-notebook/notebooklm-gemini-notebook/). It remains a standalone product, now at notebook.google.com (old notebooklm.google.com links redirect there), and Google put its reach at more than 30 million people and over 600,000 organizations. Google tied the new name to the product doing more across its ecosystem: notebooks now also open in the Gemini app and in AI Mode in Google Search. The models underneath are Google's Gemini family, whose versions and naming are explained in our post on [what Google Gemini is](https://computese.com/google-unveils-gemini-the-most-advanced-and-versatile-ai-model-yet/). This post uses NotebookLM for the history and Gemini Notebook for how the product works today. ## NotebookLM release history, from Project Tailwind to Gemini Notebook Every date below comes from Google's own announcements. | Date | What changed | | ------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | May 2023 | [Announced at Google I/O](https://blog.google/innovation-and-ai/technology/developers-tools/google-io-2023-100-announcements/) as Project Tailwind, an AI-first notebook built on your notes and sources | | Jul 12, 2023 | Renamed NotebookLM and opened to a small group of U.S. users, grounded in Google Docs you choose | | Dec 8, 2023 | [Opened to everyone in the U.S. aged 18 and up](https://blog.google/innovation-and-ai/products/notebooklm-new-features-availability/), now on Gemini Pro, with a noteboard for saved notes, suggested actions and writing formats | | Jun 6, 2024 | [Over 200 countries and territories](https://blog.google/innovation-and-ai/products/notebooklm-goes-global-support-for-websites-slides-fact-check/) on Gemini 1.5 Pro; Google Slides and web URLs as sources; citations that jump to the passage; questions about images and charts | | Sep 11, 2024 | [Audio Overviews](https://blog.google/innovation-and-ai/products/notebooklm-audio-overviews/): two AI hosts discuss your sources | | Sep 26, 2024 | [Public YouTube URLs and audio files](https://blog.google/innovation-and-ai/products/notebooklm-audio-video-sources/) as sources | | Oct 17, 2024 | ["Experimental" label removed](https://blog.google/innovation-and-ai/products/notebooklm-update-october-2024/); a NotebookLM Business pilot for organizations; instructions for Audio Overviews | | Dec 13, 2024 | [NotebookLM Plus](https://blog.google/innovation-and-ai/models-and-research/google-labs/notebooklm-new-features-december-2024/) subscription; the Sources, Chat and Studio layout; joining an Audio Overview by voice; experimental Gemini 2.0 Flash | | Feb 5, 2025 | [A Google Workspace core service](https://workspaceupdates.googleblog.com/2025/02/notebooklm-and-notebooklm-plus-now-workspace-core-service.html) for Business and Enterprise customers; Plus [joined Google One AI Premium](https://blog.google/feed/notebooklm-google-one/) on February 10 | | Apr 29, 2025 | [Audio Overviews in more than 50 languages](https://blog.google/innovation-and-ai/models-and-research/google-labs/notebooklm-audio-overviews-50-languages/) | | May 19, 2025 | [Android and iOS apps](https://blog.google/innovation-and-ai/products/notebooklm-app/), with offline Audio Overviews and sharing into a notebook from other apps | | Jul 29, 2025 | [Video Overviews](https://blog.google/innovation-and-ai/models-and-research/google-labs/notebooklm-video-overviews-studio-upgrades/) as narrated slides, and a redesigned Studio | | Oct 29, 2025 | [Gemini's full 1 million token context window](https://blog.google/innovation-and-ai/models-and-research/google-labs/notebooklm-custom-personas-engine-upgrade/) in chat on all plans; custom chat goals; saved chat history | | Nov 13, 2025 | [Deep Research](https://blog.google/innovation-and-ai/models-and-research/google-labs/notebooklm-deep-research-file-types/); Google Sheets, Word (.docx), images and Drive links as sources | | Mar 4, 2026 | [Cinematic Video Overviews](https://blog.google/innovation-and-ai/products/notebooklm/generate-your-own-cinematic-video-overviews-in-notebooklm/), made with Gemini 3, Nano Banana Pro and Veo 3, for Google AI Ultra | | Jun 8, 2026 | [Gemini 3.5 and a secure cloud computer](https://blog.google/innovation-and-ai/products/notebooklm/better-research-notebooklm/) that writes and runs code, with outputs such as xlsx, pptx and PDF reports; Google AI Ultra and Workspace AI Expanded Access first | | Jul 16, 2026 | Renamed Gemini Notebook; notebooks sync with the Gemini app | | Sep 2, 2026 | [Compute-based usage limits](https://blog.google/innovation-and-ai/products/gemini-notebook/new-flexible-usage-limits/) on personal accounts, refreshing every five hours | | Sep 15, 2026 | [A new look](https://blog.google/innovation-and-ai/products/gemini-notebook/new-study-tools-september-2026/); spoken conversations with a notebook and an audio recorder announced for the mobile app | Two threads run through that list. The model underneath keeps changing, from Gemini Pro to 1.5 Pro, 2.0 Flash and, since June 2026 on the top plans, Gemini 3.5, so reviews written in 2024 describe a different engine. And the product has moved from a personal experiment to a work tool, with Workspace terms, admin controls and paid tiers. ## How NotebookLM works: answers grounded in your sources Grounded assistants follow a pattern called [retrieval-augmented generation](https://computese.com/breaking-new-ground-in-ai-continuous-learning-system/) (RAG): instead of answering from memory, the model is handed the relevant parts of your documents and writes from them. Google's own description of its tool matches that pattern. When a notebook contains many sources, Gemini Notebook retrieves the most relevant information for your question, then builds its response from it. In practice, four things happen: 1. **Your sources are stored in the notebook.** Google defines a source as a copy of the document you upload, or an auto-synced version for Google Drive files. 2. **You choose what chat reads.** It uses every source, or only the ones you select in the Sources panel. Notes are used only when you select them, and the conversation history is used too. 3. **The model answers from what it retrieved.** Since October 2025, chat has used Gemini's full 1 million token context window on all plans, which Google said improved its handling of large document collections. 4. **Each point carries a citation.** [Hover over a citation](https://support.google.com/gemininotebook/answer/16179559) to see the full quoted text; select it to open the quote in context. ![Three sources feed an open notebook, which produces an answer bubble with small link markers; a dashed line runs from one marker back to a highlighted passage in the source document.](https://computese.com/images/blog/unlocking-efficiency-and-precision-googles-ai-powered-notebooklm-now-available-to-us-users/grounding.d72c769092-1536.webp) *A citation shows where the model looked, which is what makes an answer checkable rather than merely plausible.* Two consequences follow. First, the question matters: Google advises naming the source you mean, for example asking for the key findings in one specific document rather than a general summary, because a specific question helps it find the most relevant passages. Second, each notebook is independent. Gemini Notebook cannot draw on several notebooks at once, so a policy in one notebook does not exist for a question asked in another. The boundary also depends on where you open the notebook. Inside Gemini Notebook, responses are grounded only in your notebook's sources. The [same notebook in the Gemini app](https://support.google.com/gemininotebook/answer/17003757) or in [AI Mode in Google Search](https://support.google.com/gemininotebook/answer/17513891) is grounded in your sources but may also use web search and other tools. When an answer must come only from your documents, ask it in Gemini Notebook. Since June 2026, starting with the top plans, chat can also act for you: search the web for new sources, write and run code on a secure cloud computer, and produce files such as spreadsheets, slide decks and charts. Google says you stay in control of which sources join the notebook, labels these functions experimental, and asks you to supervise them and double-check the results. ## What you can add as a source, and the limits As of September 2026, [Gemini Notebook accepts](https://support.google.com/gemininotebook/answer/16215270) these source types: | Source type | What is imported | | -------------------------------------------- | ------------------------------------------------------------------------------------------------- | | PDF, Word (.docx), PowerPoint (.pptx), ePub | The file's contents; copy-protected PDFs fail | | Text, Markdown and CSV files, or pasted text | The text as given | | Google Docs, Slides and Sheets | Synced from Drive; Slides up to 100 slides, Sheets up to 100,000 tokens; no footnotes or comments | | Web URLs | Page text only: no images, embedded videos or nested pages; paywalled pages are not supported | | YouTube URLs | The transcript of a public video with captions; videos under 72 hours old may not import | | Audio files (MP3, WAV, M4A and many more) | A transcript made at import; recordings without speech are not supported | | Images (JPEG, PNG, HEIC, WebP and others) | The image; Google notes some kinds work less well | | Google Play Books ebooks | The text of eligible titles you have bought | Each source can hold up to 500,000 words, or 200 MB for an uploaded file, and there is no page limit. A free account can keep up to 100 notebooks with 50 sources each; paid plans raise both (see the plans section below). A YouTube source is removed within 30 days if the video is deleted or made private. Sources imported from Google Drive sync every few minutes, so the next answer reads the current version of a policy or a handbook. If you lose access to the file, or it is deleted, the source becomes inaccessible: it still counts toward your limit, but chat and Studio stop referring to it. Gemini Notebook cannot edit or delete your original files. ![Two documents in a cloud drive link to a notebook's list of sources. One syncs through an orange sync symbol; the other, locked, has a broken line and appears faded in the notebook.](https://computese.com/images/blog/unlocking-efficiency-and-precision-googles-ai-powered-notebooklm-now-available-to-us-users/drive-sync.bbf32a37d1-1536.webp) *Keep reference documents in Drive: the notebook follows their edits, and a file someone loses access to drops out of the answers.* If you do not have sources yet, type a question into the search box in the Sources panel. Fast Research returns candidate web pages or Drive files to review and import. Deep Research browses up to hundreds of websites on your behalf, writes a multi-page report and lets you import the report with its sources. Both give you material to check, not conclusions: web sources vary in quality, so look at who published each one before you keep it. ## How to use NotebookLM: your first notebook 1. **Sign in with the right account.** Go to notebook.google.com, or install the Android or iOS app. It is free for anyone [above the age of consent](https://support.google.com/gemininotebook/answer/16164461) in a supported country. For work material, use your work account, because the data terms follow the account (see the privacy section). 2. **Create one notebook per project.** Select **Create new notebook**. Keep a project's material together, since a notebook cannot see another notebook's sources. 3. **Add sources.** Upload files, pick documents from Google Drive, paste URLs (separated by spaces or new lines) or paste text. With five or more sources, the notebook can label and group them by topic. 4. **Read the overview, then ask specific questions.** The Chat panel opens with a summary of all your sources. Ask about one topic at a time, name the document when you mean one, and untick sources that are not relevant. 5. **Open the citations.** Hover to read the quote, select it to see the passage in context. Do this for every figure, date or name you will reuse. 6. **Set the chat style if needed.** Under **Configure Chat**, choose Default, Learning Guide or a Custom role and goal, plus a response length. 7. **Save and create.** Save useful answers with **Save to note**, then use the Studio panel for a briefing document, study guide, FAQ, Audio Overview or data table. Reports export to Google Docs and tables to Google Sheets. 8. **Share deliberately.** Add people as Viewer (read-only access to sources and notes) or Editor (can add or remove sources and share further). A personal account can share a notebook with up to 50 people, and each person's chat history stays private to them. > [!TIP] > Start with a narrow notebook: one policy set, one project, one customer. The model answers from the passages it judges most relevant, so a notebook without loosely related documents gives it fewer wrong places to look. ## What NotebookLM can make from your sources The Studio panel turns a notebook's sources into other formats. [As of September 2026](https://support.google.com/gemininotebook/answer/16206563) it offers: - **Reports:** a briefing document, study guide, FAQ or a format you describe, exportable to Google Docs. - **Audio Overviews:** [AI hosts discussing your sources](https://support.google.com/gemininotebook/answer/16212820) in four formats: Deep Dive (two hosts, the default), Brief (one speaker, under two minutes), Critique and Debate, in shorter, default or longer lengths. - **Video Overviews:** [Explainer, Short](https://support.google.com/gemininotebook/answer/16454555) (about 60 seconds) or Cinematic (English only, 18 and over); a video can take more than 30 minutes to generate. - **Data Tables:** rows and columns you describe, exported to Google Sheets with the citations on a second tab. Google's own example is [meeting transcripts turned into action items](https://blog.google/innovation-and-ai/models-and-research/google-labs/notebooklm-data-tables/) by owner and priority. - **Mind maps, flashcards and quizzes, slide decks and infographics:** slide decks download as PDF and infographics as PNG. Every Studio output is generated, not extracted. Google describes an Audio Overview as a reflection of your sources rather than the hosts' opinions, and warns that the voices and content may contain inaccuracies. Outputs made with Veo, Omni or Nano Banana carry an invisible SynthID watermark, and generated images and videos get a visible one, which some paid plans can switch off. Use the formats to get oriented or to brief others, then check the source for anything that matters. ## NotebookLM for business: where it fits The tool is strongest where a team keeps asking questions that a known set of documents already answers. Google's own [Workspace announcement](https://workspaceupdates.googleblog.com/2025/02/notebooklm-and-notebooklm-plus-now-workspace-core-service.html) describes sales teams loading product roadmaps, competitor analysis and customer interviews to prepare account plans, and marketers summarizing customer research into campaign briefs. | Use | Sources to add | What to ask or generate | Watch for | | ------------------------ | -------------------------------------------------------------- | ---------------------------------------------------- | ----------------------------------------------------------------- | | Research and comparisons | Reports, papers, vendor documentation, Deep Research results | A briefing document, a data table comparing options | Web sources vary in quality; check each publisher | | Onboarding | The handbook, process documents, recorded walk-throughs, decks | An FAQ, a study guide, an Audio Overview, flashcards | An outdated document gives outdated answers; keep it in Drive | | Policies and procedures | HR, IT and security policies, the current versions only | Direct questions answered with the clause cited | Remove superseded versions; this is not legal advice | | Meeting material | Transcripts, agendas, slides | A briefing, a table of action items by owner | Check owners and dates against the transcript | | Sales and account prep | Product specifications, roadmap, customer interview recordings | An account plan | Internal material belongs on a work account with enterprise terms | For sharing inside a company, three details matter. Public sharing is only enabled for consumer accounts; it is turned off for Workspace Enterprise and Education accounts. A "chat view" link hides sources for a focused experience, but Google notes it does not remove a viewer's underlying access, so it is not a way to keep documents from someone. And once a notebook is shared with at least four other people and has had chat activity in the past week, you can see its last seven days of analytics: users and queries per day. ## How Google handles your data: personal and work accounts Google's wording differs by account type, and the difference is in the details. **Personal Google accounts.** Google says the content in a notebook [will not be used to directly train](https://support.google.com/gemininotebook/answer/17004255) its foundational AI models unless you choose to give feedback. A thumbs up or thumbs down is that choice: Google collects the associated content (your prompts, sources, uploads and outputs, including any Gemini chats in the notebook), has specially trained teams review it after disconnecting it from your Google Account, and keeps it for up to three years. Data the notebook shares with other Google services, such as the Gemini app, follows those services' privacy notices, including their use for product improvement. Chats with a notebook in AI Mode in Search may be used for ads, personalization and improving Google's generative AI models, while the notebook's sources and instructions are not. **Workspace accounts where Gemini Notebook is a core service.** That covers editions such as Business Starter, Standard and Plus, Enterprise Standard and Plus, Frontline and the Education editions. Google says [uploaded files, chats and model outputs](https://support.google.com/gemininotebook/answer/16337734) are not reviewed by human reviewers or used to improve generative AI models, even when you give feedback, and the Google Cloud Terms of Service (or the Workspace for Education terms) apply. Where Gemini Notebook is only an additional service, as with Workspace Individual or Essentials Starter, the ordinary Google Terms of Service and the personal-account wording apply. **Google Cloud.** Organizations can also license it through Google Cloud, as Gemini Notebook for Enterprise or within Gemini Enterprise plans. Google [says uploaded files remain](https://support.google.com/gemininotebook/answer/16213268) in your Google Cloud project, data regionalization is honoured, and VPC Service Controls and IAM controls are available. ![Two laptops show chat panels with thumbs icons. From the upper one, an orange bundle of question, document and answer travels to a review server; the lower laptop is behind a shield and sends nothing.](https://computese.com/images/blog/unlocking-efficiency-and-precision-googles-ai-powered-notebooklm-now-available-to-us-users/feedback.4442253db2-1536.webp) *On a personal account, a single thumbs up or down sends the whole exchange for human review; an enterprise-grade work account sends nothing.* > [!WARNING] > Check which account you are signed in with before you upload client or employee data. One browser often holds a personal Gmail account and a work account, and the terms follow the account, not the document. ## Plans and usage limits as of September 2026 Google marks every figure here as subject to change. | Account | How it is provided | Sources per notebook | Data terms | | ------------------------------------------------------------------ | ------------------ | ----------------------------------------- | --------------------------------- | | Personal Google account, no plan | Free | 50 | Personal-account terms | | Google AI Plus, Pro or Ultra | Subscription | 100 (Plus), 300 (Pro), 500 or 600 (Ultra) | Personal-account terms | | Workspace Business Starter, Enterprise Essentials, Frontline | Core service | 50 | Enterprise-grade | | Workspace Business Standard and Plus, Enterprise Standard and Plus | Core service | 300 | Enterprise-grade | | Workspace AI Expanded Access or AI Ultra Access add-on | Add-on | 400 or 600 | Enterprise-grade | | Workspace Individual, Essentials Starter | Additional service | 50 | Google Terms of Service | | Google Cloud (Gemini Notebook for Enterprise) | Cloud licence | Higher limits | Enterprise-grade, in your project | On personal accounts, [limits since September 2, 2026](https://support.google.com/gemininotebook/answer/17670842) are measured in compute rather than counted per feature. They take into account prompt complexity, chat length, the number of sources and the features you use, refresh every five hours until you reach a weekly limit, and are two times higher on Google AI Plus and four times higher on Pro. When you run out, Studio outputs can be set to **Generate later**. Workspace editions still list daily counts: on Business Starter, for example, 50 chats and 3 Audio Overviews a day; on Business Standard and Plus, 500 chats and 20 Audio Overviews. On a work account, the Workspace administrator turns the service on or off. If a work account cannot open Gemini Notebook, Google's help sends you to that administrator. ## Where NotebookLM gets things wrong, and how to check it Source grounding narrows what the model draws on; it does not make the model read correctly. Google said as much in its first announcement: grounding seemed to reduce the risk of hallucinations, but it was still important to fact-check responses against the original sources. Its [May 2026 I/O notebook](https://blog.google/innovation-and-ai/products/notebooklm/notebooklm-google-io-2026/) carried the same reminder that, like all AI, NotebookLM can generate inaccuracies. The failures to expect: - **A misread passage.** A citation proves where the model looked, not that it drew the right conclusion from the passage. - **A missed passage.** In a large notebook the model works from the passages it judges most relevant, and a vague question can miss the one that matters. - **Content that never arrived.** Footnotes and comments in Google files, images on web pages and everything visual in a YouTube video (only the transcript is imported) are not in the notebook. - **Whole-document citations.** When a source is very short, the notebook cites the whole document instead of individual passages. - **Generated media.** Audio and Video Overviews can contain inaccuracies and glitches, and are summaries, not records. - **Agent actions.** Google says the code, web and file features can make mistakes and do unexpected things. Google also says not to rely on Gemini Notebook for medical, legal, financial or other professional advice. A workable routine before an answer goes into anything you send: 1. Open the citation behind every number, date, name and obligation you will reuse. 2. Read the cited passage in context, including the sentences around it. 3. Ask which source supports any claim that has no citation; if none does, treat the claim as unsupported. 4. For comparisons across documents, ask for a data table and check the citations cell by cell. 5. Keep the notebook current: remove superseded versions so the old policy and the new one never both answer. ## When a notebook is not enough Gemini Notebook is a tool for people working with documents in Google's own apps. If the questions come from customers on your website, if answers must include live facts such as prices or availability, or if the assistant has to run inside your own systems under your own access rules, that is a different build. Our [AI and automation service](https://computese.com/services/ai-automation/) builds assistants grounded in your content that answer from your own pages, documents and live data, cite their sources and say when they do not know. Sometimes the answer is a feature you already pay for; if it is, we will say so and not build it. For the wider question of how AI gets built into software, see our guide to [intelligent apps](https://computese.com/artificial-intelligence-and-intelligent-apps/). ## Key terms - **Gemini Notebook**: The name of NotebookLM since July 16, 2026. It is still a standalone Google product, and its notebooks now also open in the Gemini app and in AI Mode in Google Search. - **Source**: A document, web page, video, recording or image you add to a notebook. Gemini Notebook keeps a copy, or an auto-synced version for Google Drive files, and answers from it. - **Source grounding**: Making a language model answer from material you supply rather than from what it absorbed in training. It narrows what the model draws on; it does not guarantee the model reads that material correctly. - **Inline citation**: A marker in an answer that links to the quote, text or image in your source that supports it, so you can read the passage in its original context. - **Retrieval-augmented generation (RAG)**: The general technique behind grounded assistants: find the passages most relevant to a question, then have the model write its answer from them. - **Context window**: How much text, counted in tokens, a model can take in at once. Since October 2025 NotebookLM chat uses Gemini's full 1 million token context window on all plans. - **Hallucination**: A fluent, confident statement from a language model that its sources do not support. Source grounding makes it less likely, not impossible. - **Studio panel**: The part of a notebook that turns its sources into other formats: reports, Audio and Video Overviews, mind maps, data tables, flashcards, quizzes, slide decks and infographics. - **Audio Overview**: A generated audio discussion of a notebook's sources, by default two AI hosts in a Deep Dive format. Google warns it may contain inaccuracies. - **Workspace core service**: A Google Workspace app covered by the customer's Workspace terms and data protections, like Gmail or Docs. NotebookLM became one for Business and Enterprise customers on February 5, 2025. ## Common questions ### Is NotebookLM free? Yes. Anyone above the age of consent in a supported country can use Gemini Notebook with a Google account at no cost, with up to 100 notebooks and 50 sources per notebook. Google AI Plus, Pro and Ultra plans raise the limits, as do qualifying Google Workspace editions and Google Cloud licences. Since September 2, 2026, limits on personal accounts are measured in compute and refresh every five hours, up to a weekly cap. ### Is NotebookLM the same as Gemini? No, but the two are now connected. NotebookLM was renamed Gemini Notebook on July 16, 2026 and remains a standalone product that runs on Google's Gemini models. Your notebooks also appear in the Gemini app, where answers may draw on web search as well; in Gemini Notebook itself, answers are grounded only in your sources. ### Does Google use my NotebookLM uploads to train its AI? On a personal account, Google says notebook content is not used to directly train its foundational models unless you give feedback; a thumbs up or down sends the exchange for human review, kept for up to three years. On Workspace and Workspace for Education editions that include it as a core service, Google says uploads, queries and responses are not reviewed by people or used to train AI models, even when you give feedback. ### Can NotebookLM write a first draft for me? Yes, from your sources. Since December 2023 it has turned selected notes into formats such as an outline, an email newsletter or a draft marketing plan, and the Studio panel now writes briefing documents, study guides and custom reports you can export to Google Docs. Check the citations before the draft goes anywhere. ### How many sources can NotebookLM handle? On a free account, up to 50 sources per notebook, each up to 500,000 words or 200 MB for an uploaded file, with no page limit. Paid Google AI plans allow 100 to 600 sources per notebook, and Workspace editions between 50 and 600, depending on the plan. Each notebook is separate: it cannot answer from another notebook's sources. ### Can NotebookLM search the web? It can find sources for you. Fast Research suggests web pages or Drive files, Deep Research browses up to hundreds of websites and writes a report you can import, and since June 2026, on the plans that have the upgrade, chat can search Google and offer what it finds as new sources. Answers in Gemini Notebook still come only from the sources in the notebook. ## Sources 1. [Introducing NotebookLM](https://blog.google/innovation-and-ai/technology/ai/notebooklm-google-ai/), Google 2. [Frequently asked questions](https://support.google.com/gemininotebook/answer/16269187), Gemini Notebook Help 3. [NotebookLM is now Gemini Notebook](https://blog.google/innovation-and-ai/products/gemini-notebook/notebooklm-gemini-notebook/), Google 4. [100 things Google announced at I/O 2023](https://blog.google/innovation-and-ai/technology/developers-tools/google-io-2023-100-announcements/), Google 5. [NotebookLM launches in the U.S. with new features](https://blog.google/innovation-and-ai/products/notebooklm-new-features-availability/), Google 6. [NotebookLM goes global with Slides support and better ways to fact-check](https://blog.google/innovation-and-ai/products/notebooklm-goes-global-support-for-websites-slides-fact-check/), Google 7. [NotebookLM now lets you listen to a conversation about your sources](https://blog.google/innovation-and-ai/products/notebooklm-audio-overviews/), Google 8. [NotebookLM adds audio and YouTube support, plus easier sharing of Audio Overviews](https://blog.google/innovation-and-ai/products/notebooklm-audio-video-sources/), Google 9. [NotebookLM update: Audio Overview controls and team collaborations](https://blog.google/innovation-and-ai/products/notebooklm-update-october-2024/), Google 10. [NotebookLM announces NotebookLM Plus and other new features](https://blog.google/innovation-and-ai/models-and-research/google-labs/notebooklm-new-features-december-2024/), Google 11. [NotebookLM and NotebookLM Plus now available as a Google Workspace core service with enterprise-grade data protection](https://workspaceupdates.googleblog.com/2025/02/notebooklm-and-notebooklm-plus-now-workspace-core-service.html), Google Workspace Updates 12. [NotebookLM Plus is now available in the Google One AI Premium subscription](https://blog.google/feed/notebooklm-google-one/), Google 13. [Google's NotebookLM Audio Overviews adds more than 50 languages](https://blog.google/innovation-and-ai/models-and-research/google-labs/notebooklm-audio-overviews-50-languages/), Google 14. [Google launches official NotebookLM mobile app](https://blog.google/innovation-and-ai/products/notebooklm-app/), Google 15. [NotebookLM updates: Video Overviews, Studio upgrades](https://blog.google/innovation-and-ai/models-and-research/google-labs/notebooklm-video-overviews-studio-upgrades/), Google 16. [NotebookLM adds custom goals, upgrades performance](https://blog.google/innovation-and-ai/models-and-research/google-labs/notebooklm-custom-personas-engine-upgrade/), Google 17. [NotebookLM adds Deep Research, Docx, Sheets and more](https://blog.google/innovation-and-ai/models-and-research/google-labs/notebooklm-deep-research-file-types/), Google 18. [NotebookLM adds Cinematic Video Overviews](https://blog.google/innovation-and-ai/products/notebooklm/generate-your-own-cinematic-video-overviews-in-notebooklm/), Google 19. [Do your best research with NotebookLM](https://blog.google/innovation-and-ai/products/notebooklm/better-research-notebooklm/), Google 20. [More compute flexibility in Gemini Notebook](https://blog.google/innovation-and-ai/products/gemini-notebook/new-flexible-usage-limits/), Google 21. [Sharpen your study routine with new Gemini Notebook tools](https://blog.google/innovation-and-ai/products/gemini-notebook/new-study-tools-september-2026/), Google 22. [Use chat in Gemini Notebook](https://support.google.com/gemininotebook/answer/16179559), Gemini Notebook Help 23. [Notebooks in Gemini Apps](https://support.google.com/gemininotebook/answer/17003757), Gemini Notebook Help 24. [About notebooks in AI Mode in Google Search](https://support.google.com/gemininotebook/answer/17513891), Gemini Notebook Help 25. [Add or discover new sources for your notebook](https://support.google.com/gemininotebook/answer/16215270), Gemini Notebook Help 26. [Learn about Gemini Notebook](https://support.google.com/gemininotebook/answer/16164461), Gemini Notebook Help 27. [Create a notebook in Gemini Notebook](https://support.google.com/gemininotebook/answer/16206563), Gemini Notebook Help 28. [Generate Audio Overview in Gemini Notebook](https://support.google.com/gemininotebook/answer/16212820), Gemini Notebook Help 29. [Generate Video Overviews in Gemini Notebook](https://support.google.com/gemininotebook/answer/16454555), Gemini Notebook Help 30. [Google's NotebookLM introduces Data Tables feature](https://blog.google/innovation-and-ai/models-and-research/google-labs/notebooklm-data-tables/), Google 31. [Privacy and Terms of Use in Gemini Notebook](https://support.google.com/gemininotebook/answer/17004255), Gemini Notebook Help 32. [Use Gemini Notebook with a work or school Google account](https://support.google.com/gemininotebook/answer/16337734), Gemini Notebook Help 33. [Upgrade Gemini Notebook](https://support.google.com/gemininotebook/answer/16213268), Gemini Notebook Help 34. [Manage your Gemini Notebook usage limits](https://support.google.com/gemininotebook/answer/17670842), Gemini Notebook Help 35. [Dive deeper into Google I/O 2026 with NotebookLM](https://blog.google/innovation-and-ai/products/notebooklm/notebooklm-google-io-2026/), Google