You can now ask Gemini questions about your NotebookLM notebooks
|
By
Pranob Mehrotra Published December 15, 2025 |
We recently learned that Google was prepping a new feature that would allow users to ask Gemini questions about their NotebookLM notebooks. Although Google still hasn’t made anything official, this feature now appears to be rolling out to users.
According to recent X posts from Sai Nemani and TestingCatalog, the attachment menu in Gemini on the web now includes a NotebookLM button. This option lets users attach a notebook and ask Gemini questions about the attached notebook to get more relevant responses.
TestingCatalog reports that the feature lets users attach multiple notebooks as sources. In addition, the NotebookLM integration works with Gemini Gems, meaning users can create custom AI assistants with expertise on the information in their NotebookLM notebooks.
At the moment, the NotebookLM integration appears to be limited to the web version of Gemini. The attachment button is not available in the Gemini for Android on any of our devices. Availability also seems limited overall, with several users reporting that the feature has yet to appear on their Google accounts.
Google may expand access in the coming days and eventually bring the NotebookLM attachment button to the Gemini app for mobile, but there’s no confirmation yet. An official announcement with more details could be right around the corner.
Over the last few weeks, Google has introduced several major upgrades for NotebookLM, including support for additional file types, such as Google Sheets, Drive files, images, PDFs, and Microsoft Word documents, along with a significantly larger context window, longer conversational memory, and improved response quality. The NotebookLM mobile app has also picked up several improvements, including support for flashcards and quizzes, as well as broader chat improvements that first rolled out on the web version.
Related Posts
New study shows AI isn’t ready for office work
A reality check for the "replacement" theory
Google Research suggests AI models like DeepSeek exhibit collective intelligence patterns
The paper, published on arXiv with the evocative title Reasoning Models Generate Societies of Thought, posits that these models don't merely compute; they implicitly simulate a "multi-agent" interaction. Imagine a boardroom full of experts tossing ideas around, challenging each other's assumptions, and looking at a problem from different angles before finally agreeing on the best answer. That is essentially what is happening inside the code. The researchers found that these models exhibit "perspective diversity," meaning they generate conflicting viewpoints and work to resolve them internally, much like a team of colleagues debating a strategy to find the best path forward.
Microsoft tells you to uninstall the latest Windows 11 update
https://twitter.com/hapico0109/status/2013480169840001437?s=20