Google's AI Notebook Can Now Read Your Purchased Books and Answer Questions About Them
Google's Gemini Notebook can now pull information from books users have purchased on Google Play Books through a new feature called Expert Intelligence, the company announced on August 27, 2026. Google Labs editorial director Steven Johnson demonstrated the feature to The Verge during a briefing. The Verge
Expert Intelligence lets users bring Google Play Books titles into Gemini Notebook and ask questions, generate plans, infographics, and AI podcasts based on the book contents. Think of it as having a conversation with your bookshelf — you can ask a book to explain a chapter, summarize a key argument, or pull together points from several books at once. Compatible titles display a "Gemini Notebook" listing under the "Tools" badge on Google Play Books, so users can see which books support the feature.
More than 100,000 books from publishers including Penguin Random House, Johns Hopkins University Press, Macmillan Publishers, and O'Reilly Media will support Expert Intelligence at launch. The O'Reilly inclusion is notable for practitioners in software engineering and data science, where the publisher's catalog is deeply embedded in day-to-day reference and learning workflows.
Google also worked with 15 authors, including Michael Pollan, Kim Scott, Steven Pinker, and Jennifer Wallace, to create what it calls "Featured Notebooks." These are customized by the authors themselves, who add supplementary source material and write intro letters for readers navigating their books through Gemini Notebook.
The feature arrives with access controls designed to address a persistent concern with AI-assisted reading tools: the tension between useful extraction and copyright protection. Gemini Notebook includes protections preventing users who do not own a purchased book from accessing its full text or related information when a Notebook is shared. Non-owners see the source listed but are directed to Google Play Books to purchase it. This mirrors the approach that has been part of the product since its original 2023 launch as NotebookLM. In that system, the AI is constrained to work only with material the user has provided, and every response includes citations showing the original text it drew from, so users can check the answers themselves. Google noted at the time that while this approach appeared to reduce the risk of the AI making things up, fact-checking against original material remained essential. Google Blog, 2023
The product now called Gemini Notebook has built up a substantial feature set since its introduction. Originally launched in July 2023 as NotebookLM, a virtual research assistant that worked with a user's own content, the product could initially use Google Docs, with Google promising additional formats to come. By September 2024, an Audio Overview feature could turn documents, slides, and charts into generated podcast-style discussions. Video Overviews were upgraded in October 2025 with visuals powered by the Nano Banana model and a new "Brief" format for quick summaries. In December 2025, slide deck generation arrived, converting research notes into presentations. In June 2026, Google announced new Gemini models and code execution capabilities. The rebrand to Gemini Notebook came in July 2026, with all existing notebooks remaining fully accessible. Google Blog, 2026
Expert Intelligence fits into a familiar pattern for this product: start with a small set of source types, prove the system works, then expand. The original 2023 launch supported Google Docs. Three years later, the sources include purchased books from major publishers, and Google has stated plans to expand Expert Intelligence to scholarly articles, magazine articles, and newspapers. Google also plans to bring Expert Intelligence to AI Mode in Search and the Gemini app, which would take the feature well beyond the standalone Notebook interface.
The design choices here are worth attention. The core idea — limiting the AI to reason over material the user has provided rather than letting it draw freely from whatever it learned during training — is what Google has been doing since the product first launched. Expert Intelligence extends that principle to licensed, purchased book content. The access-control layer, which blocks full-text access unless the system verifies you own the book, is the mechanism that makes this acceptable to publishers who have otherwise been hostile to AI using their catalogs. Whether the 100,000-title launch catalog and the publisher list signals broader industry acceptance of this approach, or selective participation by a subset of willing partners, is a question the launch itself does not answer. The expansion to newspapers and scholarly articles, if it arrives, will test whether the same ownership-gated approach transfers to content types where purchase and ownership models differ from trade books.
For people who already use Gemini Notebook as a research tool, Expert Intelligence adds a source category that was previously unavailable: purchased nonfiction and technical titles. The ability to ask questions across multiple books, cross-reference their claims, and generate structured outputs like infographics and podcasts from their combined content is a straightforward extension of what the product already does with uploaded documents and notes. The publisher participation and the access controls are the parts that required work.
