Three years ago, we launched NotebookLM as an experimental AI product at Google Labs to help you understand everything. Millions of people and organizations use NotebookLM as a collaborative knowledge and research partner because it helps them organize their thoughts, identify deeper connections between documents, and generate new ideas. Today, we’re introducing a complete upgrade to NotebookLM that brings new agent capabilities in chat and more advanced reasoning to tackle your most complex research projects.
An upgraded, more thoughtful chat experience
First, we’re upgrading NotebookLM to run on Gemini 3.5 and Antigravity, providing more accurate and reliable information and increased visibility into your thought process.
Each notebook is equipped with a secure cloud computer that allows NotebookLM to write and run code that helps it perform deeper investigations and more complex analyses. This system includes over 100 carefully selected software skills that unlock a wide range of new features to help you better understand the sources in your notebook.
In a comparative evaluation against the previous system, the upgraded NotebookLM achieved an average win rate of over 65% (15% points margin over peers) across the top five core metrics. The system showed significant improvement in large-scale document analysis, securing a 69.9% win rate, and achieved superior performance in advanced web research and source discovery, reaching a 78.2% win rate compared to the previous baseline.
