Google tests Personal Intelligence in NotebookLM to learn how users think and work

NotebookLM could get even better with this Gemini feature

However, unlike Gemini, NotebookLM may not access context from different Google apps. Gemini earned a big upgrade last month when Google rolled out Personal Intelligence in the chatbot, allowing the chatbot to access context from other Google apps and refine responses. That's a shift toward a more personalized and aware AI chatbot, and Google may be bringing it to other Gemini-powered apps and platforms, including NotebookLM. Google now appears to be testing Personal Intelligence in the celebrated learning and research app. TestingCatalog recently discovered this option being tested and also gave us a preview of what it facilitates. Based on the screenshots and description, it appears NotebookLM's version of Personal Intelligence will vary from how it works in Gemini. Unlike the latter's ability to imbibe knowledge from your activity across different Google apps, NotebookLM might only limit itself to knowledge sharing across different notebooks in the app. Besides just information, it could also extract "your goals" to serve you better. In addition, NotebookLM might allow you to set "personas," or a set of guidelines or instructions based on your profession or study objectives, to help improve responses. According to the initial findings, you might be able to set these goals either per notebook as well as for the entire notebook collection. There's no mention of accessing information from other Google apps yet. Despite the framing, therefore, Personal Intelligence in NotebookLM may be more like chat memory in chats with Gemini, and more recently expanded to Search. Whether Google adds the option for broader access remains to be seen. However, the converse could be possible if Gemini gains the ability to access NotebookLM chats, as has also been suggested in the recent past. Meanwhile, there's no timeline on how soon the feature could be available for more users to try out.

Google wants NotebookLM to learn how you think and work

Rajesh started following the latest happenings in the world of Android around the release of the Nexus One and Samsung Galaxy S. After flashing custom ROMs and kernels on his beloved Galaxy S, he started writing about Android for a living. He uses the latest Samsung or Pixel flagship as his daily driver. And yes, he carries an iPhone as a secondary device. Rajesh has been writing for Android Police since 2021, covering news, how-tos, and features. Based in India, he has previously written for Neowin, AndroidBeat, Times of India, iPhoneHacks, MySmartPrice, and MakeUseOf. When not working, you will find him mindlessly scrolling through X, playing with new AI models, or going on long road trips. You can reach out to him on Twitter or drop a mail at [email protected]. At the beginning of this year, Google announced Personal Intelligence, enabling Gemini to connect to your Gmail, Photos, Search, and YouTube history to tailor its responses accordingly. It now appears that the company is working on expanding Personal Intelligence to one of its best AI tools, NotebookLM. The main highlight of NotebookLM is how it grounds its responses in the sources you add. With Personal Intelligence, Google wants NotebookLM to learn from your chats to understand you and better what you want. TestingCatalog spotted a Personal Intelligence option in NotebookLM. The toggle appeared in the Settings menu as well as on a per-notebook level. This suggests Google will give NotebookLM users the choice to turn Personal Intelligence on for everything or keep it restricted to select notebooks. Based on strings, the report speculates that Personal Intelligence in NotebookLM will learn from your chats and create a persona. That may help the tool tailor its responses more to your liking. The current string reads: "You are a researcher interested in AI and machine learning. You prefer concise, technical explanations with code examples when relevant." This persona appears to be editable, which should help correct any wrong assumptions NotebookLM makes about your preferences or workflow. For now, though, it's still too early to understand how exactly Personal Intelligence will work in NotebookLM. If anything, the feature might allow NotebookLM to reference past chats for more context. Personal Intelligence will further supercharge NotebookLM capabilities Given that the AI tool is designed for ongoing research work, note-taking, and long-form thinking, Personal Intelligence should be more beneficial here. With it enabled, NotebookLM should understand how you prefer information to be presented, the tone you like, and the topics you care about -- without needing repeated prompts. AP Recommends: Subscribe and never miss what matters Tech insights about everything mobile directly from the Android Police team. Subscribe By subscribing, you agree to receive newsletter and marketing emails, and accept our Terms of Use and Privacy Policy. You can unsubscribe anytime. While Personal Intelligence in Gemini pulls context and information from various Google services, the NotebookLM version should be more self-contained and limited to your chats. Since Personal Intelligence in NotebookLM has just been spotted in testing, it may take a while for the feature to roll out. Google has been aggressively rolling out improvements to its AI-powered note-taking tool, so hopefully, the wait should not be long.

Google's testing a feature that makes NotebookLM learn your preferences - Phandroid

Google's experimenting with NotebookLM Personal Intelligence, a feature that would let the AI research assistant learn from your past conversations and adapt to how you work. According to TestingCatalog, the option showed up in recent builds of NotebookLM, appearing both in global settings and inside individual notebook configurations. The feature includes a custom prompt field that pre-fills with a persona-like description. An example from the test builds reads something like "a researcher focused on AI and machine learning who prefers concise, technical explanations with code when relevant." It's unclear whether this profile gets pulled from your broader Gemini account, inferred from past notebook conversations, or if it's just a placeholder for now. Google already rolled out Personal Intelligence for Gemini, which can pull data from Gmail, Photos, YouTube, and Search to personalize responses. The NotebookLM Personal Intelligence version works differently. It appears more self-contained, focusing on analyzing your chat history and note-taking habits within the app itself rather than reaching across other Google services. This makes sense given how NotebookLM already connects with Gemini through different integration points. The tool's strength has always been grounding its answers in the specific documents you provide. Adding cross-notebook context means it could remember how you work across different projects instead of starting fresh every time. The feature could work at two levels: globally across all your notebooks and locally per individual notebook. That means different research projects could have different personas. A notebook for technical documentation might prefer code examples and concise explanations, while another for creative writing might need more descriptive, flowing responses. For students and researchers who use NotebookLM for presentations and study materials, this saves time. You wouldn't need to constantly restate your preferences about tone, technical depth, or formatting. The AI would just know you prefer bullet points over paragraphs or want multiple perspectives instead of single conclusions. There's no official release date yet. The feature appearing in settings suggests Google's getting closer to testing it with real users, but right now it's just code sitting in recent builds. When it does arrive, it'll build on the Gemini 3 upgrade that already improved NotebookLM's reasoning capabilities.

Google Is Reportedly Bringing Personal Intelligence to NotebookLM

Personal Intelligence was recently added to AI Mode in Search Google is reportedly planning to expand Personal Intelligence to NotebookLM conversations. As per the report, the Mountain View-based tech giant is testing the capability, which allows AI chatbots to seamlessly retrieve data from compatible knowledge hubs to personalise responses, within NotebookLM. If true, this will mark the tech giant's second expansion of the feature, after it was added to AI Mode in Search last month. While some details are currently missing, the report claims that Google plans to add two layers of Personal Intelligence to NotebookLM, allowing each notebook to behave differently. NotebooKLM to Reportedly Get Personal Intelligence According to a TestingCatalog report, the Gemini maker is now testing Personal Intelligence within NotebookLM. The publication said it found evidence of the integration within the codebase of the platform, revealing how Google might bring the capability to the artificial intelligence (AI)-powered research platform. As mentioned above, Personal Intelligence is reportedly being added at two levels. The publication found options to activate it inside Settings and within each notebook's configuration. This indicates that users might be able to add custom prompts for the entire platform and then fine-tune each notebook as per requirement. References reportedly highlight that once activated, NotebookLM can learn from the chat history to understand what the user wants. Additionally, TestingCatalog was also able to surface a custom prompt field that "pre-fills a profile-like description." It is currently not clear whether Google plans to let NotebookLM connect to Gemini to understand more about the user's preferences, or if it will also be able to access Gmail and other platforms for the same. The publication claimed that, based on its existing configuration, the feature appears more like a persona customisation instead of a data integration and personalisation feature. Do note that the abovementioned information is taken from code snippets. However, many times developers add references to planned features that never materialise, or even if they do, the implementation is vastly different. So, we would recommend taking this information with a pinch of salt and waiting until Google officially announces these features.