A major overhaul adds a per-notebook cloud computer, Gemini 3.5 Flash, and agentic research capabilities to Google's AI notebook tool.

Google has significantly upgraded NotebookLM, its AI-powered research tool, adding a dedicated cloud computer for each notebook, code execution capabilities, and agent-based research features designed for more complex projects. [1]

The updated tool now runs on Gemini 3.5 Flash, Google’s latest model in that family, and is integrated with Antigravity, Google’s coding tool. [1] Each notebook is provisioned with its own cloud compute environment that can write and execute code directly. [1]

The agent-based research features represent a meaningful shift in how the tool handles multi-step tasks. A new zero-source mode allows NotebookLM to automatically find and add relevant sources by querying Google Search, removing the requirement for users to manually supply all reference material. [1]

On the output side, users can now export results in several formats: PDF reports with embedded charts, Excel spreadsheets, PowerPoint presentations, and image files. [1] Previously, NotebookLM’s outputs were largely confined to the in-app experience.

Google says internal testing showed the new system outperformed the previous version approximately 65 percent of the time. [1]

The update is currently available to Google AI Ultra subscribers and Workspace customers with AI Ultra Access or AI Expanded Access, and has been rolled out worldwide. [1]

Sources

  1. The Decoder — Google's NotebookLM now runs its own cloud computer with code execution and agent-based research

This article was drafted with AI from the cited sources and checked against them before publication. Spot an error? Let us know.