Google is today introducing NotebookLM with Gemini 3.5 and a major upgrade to the underlying models, results, and research made possible by Antigravity.
NotebookLM now uses Gemini 3.5 and Antigravity – Google’s coding tool – to provide “more accurate and reliable information along with better visibility into the thought process”.
Every notebook now has a “secure cloud computing” that allows NotebookLM to “write and run useful code to help you conduct deeper research and more complex analyses.”
The system includes over 100 curated software skills that unlock a wide range of new capabilities to help you gain a deeper understanding of the resources on your notebook.
This results in major improvements over the previous system, according to side-by-side evaluations:
- “…Enhanced NotebookLM achieved an average win rate of more than 65% across our first five key evaluation criteria – a 15% margin above parity.”
- “…major improvements in large document parsingDelivering a 69.9% win rate…”
- “…achieved an exceptional performance advanced web research and resource discovery achieved a 78.2% win rate compared to our previous base.
NotebookLM can now generate outputs ready for download in more file formats:
- Data visualization and graphics: PNG, SVG
- Documents: PDF, DOCX, Markdown, text files
- Images with Nano Banana: PNG, JPG, GIF
- Structured data: CSV, JSON
- Microsoft Excel: XLSX
- Microsoft PowerPoint: PPTX
You can provide detailed instructions, such as creating PDF reports with charts and tables or detailed budget tables. You can request editing after generation. More formats will come in the future.
If you’re just starting a project with “empty ideas and questions,” NotebookLM’s chat experience can now “guide you through building your source repository.”
Perhaps you want to find primary sources in other languages to better understand new perspectives, or you’re looking for related works by an author you’ve recently discovered. It can even use Google Search to find relevant, high-quality resources from around the web and add them to your notebook.
Taken together, Google is making more workflows possible in NotebookLM with these three key improvements:
- Researchers: A data analyst can combine data from different countries with conflicting formatting. To make this information useful, an analyst can ask NotebookLM to perform web research to find additional context, write code to perform accurate data analysis, and generate graphs and a PDF report to display the results.
- Technical Professionals: A program manager can decipher complex specifications for customer integration, instantly turning technical documents into a polished, simplified guide, slide deck, and step-by-step roadmap for the team.
- Small Business Owners: A gym owner can run a media campaign and analyze raw sales data against ad spend. By calculating the financial impact of a campaign using NotebookLM, a business owner is better equipped to decide whether to expand to other cities.
These improvements are rolling out to Google AI Ultra and Workspace business customers with AI Ultra access starting today. This will come to other levels “over time”.
FTC: We use automatic affiliate links that generate income. More.
