NotebookLM gains code execution to automate research
notebooklm's gemini 3.5 upgrade adds a cloud computer for code execution, allowing agents to perform multi-step research and generate dynamic visual reports.
google has upgraded notebooklm with gemini 3.5 and integrated its antigravity coding platform, giving the ai a secure cloud computer to write and run code during research. users can now initiate projects by simply asking a question, prompting the agent to search the web for sources and import relevant data automatically. the upgrade expands output capabilities significantly, allowing notebooklm to generate python-powered charts, pdfs, and csv sheets. currently available for ai ultra and workspace users, this update signals a shift from static note-taking to dynamic, agent-based analysis tools.