Google on Monday announced an update to its NotebookLM<\/a> research tool, which includes new features and the shift to Gemini 3.5 as the default model. The company is also adding Antigravity<\/a>-powered software skills to help users with research and generating different kinds of outputs. <\/p>\n This is similar to Google adding coding chops to its search<\/a> products to make them more engaging for Q&A.<\/p>\n Google said that with the latest update, you can start a chat about a project with the app, and it will help you build the knowledge base by suggesting different sources using its research skills and Google Search. The feature could help users get primary sources in other languages or find new material from related authors.<\/p>\n Previously, NotebookLM required you to bring your own sources to start building a knowledge base in order to extract insights.<\/p>\n The company added that users can now give detailed instructions to NotebookLM to generate output in different formats. Plus, they can edit the output once generated. The tool now supports exports in formats including Data visualizations and charts (.png, .svg); Documents (PDFs, .docx, Markdown, text files); Nano-banana-powered images; Structured data (.csv, .json); and Microsoft Excel and PowerPoint.<\/p>\n Last year, the company introduced a \u201cDeep Research\u201d mode for structured online research<\/a>. With the new feature rollout, NotebookLM will show detailed steps in the chat about how it arrived at the answers for users to check the output. <\/p>\n Google said that the updates are available to Google AI Ultra users and all Workspace business customers with AI Ultra Access and AI Expanded Access starting today, with the aim of expanding them to others. <\/p>\n<\/div>\n When you purchase through links in our articles, we may earn a small commission<\/a>. This doesn\u2019t affect our editorial independence.<\/em><\/p>\n![\"\"](\"https:\/\/techcrunch.com\/wp-content\/uploads\/2026\/06\/NotebookLM-Thinking.jpeg?w=680\")