Many of us have a place where we feel like we do our best thinking — maybe outside on a walk, or at the kitchen table sipping a cup of coffee. It’s where we organize our thoughts to articulate messages, accomplish goals and make connections. And wherever we happen to do it, that thinking process almost always involves taking ideas from different tools and sources — whether quotes from books, instructions from websites or handwritten musings from notebooks — and combining them into new forms.
Large language models (LLMs) have given us an extraordinary opportunity to reimagine that process. With the advanced capabilities of LLMs, you can have more than just an organizational tool — you can have a personalized AI collaborator.
NotebookLM, an experimental product in Labs designed to help you do your best thinking, is now available in the U.S. to ages 18 and up. And it’s starting to use Gemini Pro, our best model for scaling across a wide range of tasks, to help with document understanding and reasoning.
Feedback from early testers
We opened up early access to NotebookLM in July, giving testers the chance to try out its source grounding capabilities. That means when you upload documents to NotebookLM, it becomes an instant expert in the information you need for your projects, capable of answering questions based on the supplied sources. Since then, we’ve talked to knowledge workers, creators, students and educators to learn more about the ways they’re using (and what they’re liking about) NotebookLM.
Through those conversations, we‘ve discovered that people particularly appreciate the way NotebookLM automatically generates summaries and suggests follow-up questions, providing a helpful new way to comprehend difficult text and synthesize connections between multiple documents.
Today’s NotebookLM release builds on that foundation, introducing more than a dozen new features that allow you to shift effortlessly from reading to note-taking to writing. Here are a few highlights.
A new space to take and reference notes
One key feature request was the ability to save interesting exchanges with NotebookLM as notes. So we’ve introduced a new noteboard space where you can easily pin quotes from the chat, excerpts from your sources or your own written notes. Like before, NotebookLM automatically shares citations from your sources whenever it answers a question. But now you can quickly jump from a citation to the source, letting you see the quote in its original context.
Save responses from NotebookLM as a note with citations.
Helpful suggested actions
Building on our popular suggested questions feature, we’re rolling out new features that dynamically suggest actions based on whatever you happen to be doing. For instance, when you select a passage while reading a source, NotebookLM will automatically offer to summarize the text to a new note, or help you understand technical language or complicated ideas. And while you’re writing a note, NotebookLM will offer tools to polish or refine your prose, or suggest related ideas from your sources based on what you’ve just written.
NotebookLM now dynamically suggests actions based on whatever you’re doing.
Formats for different writing projects
NotebookLM also has new tools to help you organize your curated notes into structured documents. Simply select a set of notes you’ve collected and ask NotebookLM to create something new. It will automatically suggest a few formats, like a thematic outline or study guide. But you can also just type any instructions you want into the chat box. So you could tell NotebookLM to transform your notes into an email newsletter, a script outline, a draft of a marketing plan — whatever is most helpful to you. And when you’re ready to start working on the final version, export what you’ve created to Docs in one click.
Select notes and ask NotebookLM to create an outline for you.
NotebookLM is an example of a truly AI-native application, built from the ground up using the extraordinary capabilities of today’s technology. Because this is new terrain technologically and creatively, NotebookLM continues to be an experiment that will improve with your feedback. And your personal data is not used to train NotebookLM — so any private or sensitive information you have in your sources will stay private, unless you choose to share your sources with collaborators.
Wherever you currently do your best thinking, give NotebookLM a try today — and let us know what you discover along the way.