More new features for NotebookLM
Google’s NotebookLM is one of the most useful generative AI (GAI) tools around. NotebookLM is a form of retrieval augmented generation (RAG) AI, which basically means that the chatbot will use information resources you provide when developing its responses. For example, you can upload a set of policy documents then ask questions about the documents, create summaries, FAQs and much more. I use NotebookLM almost every day, usually multiple times a day. The first time I wrote about NotebookLM was in September of last year. It was useful then, but Google just keeps adding more and more features making it even more useful. For example, recently they added the ability to create a comprehensive mind map of the information resources you provided. Seriously, if you’re not using NotebookLM, you’re missing out. In the last few weeks, I became aware of not one, but two new, useful features for NotebookLM.
Source Guide
Earlier today (at the time I wrote this, I have no idea when you’re reading it), I was working with NotebookLM and stumbled across a new feature. Now, clicking on an information source brings up an information summary, like the one below.
You can use this in a couple of ways. The way I found it was through interacting with the chatbot. I was working on a paper and had uploaded a few relevant journal articles to NotebookLM. I was using the chatbot to zero in on a specific area. The chatbot produced the output below. Notice the footnotes.
If you park your pointer on a footnote, NotebookLM shows you an excerpt from which it pulled that part of its output. This isn’t new, although it is useful.
Clicking on the footnote takes you to the source that was referenced in the footnote. Here’s where the new feature comes in. Notice the source guide pill? That’s new. I’m not sure when Google rolled this out, but it was the first time I’d seen it.
Clicking on the open button (the down arrow) brings up the source guide, which consists of a summary of the resource along with the key topics covered in the source. Yes, you could produce something similar on your own, but this little feature, while not being as groundbreaking as the mind map, still seems quite useful to me, especially when you have dozens of sources. (The $20 per month Pro version of NotebookLM allows up to 300 sources. It’s included with Google AI Pro.)
In addition to having a concise summary of the source, the Key Topics feature might prompt you to explore that source further. Maybe you don’t experience this, but when I have dozens of sources, I sometimes forget exactly what each on covers. For example, I might have forgotten that this source covered AI bias in healthcare.
The Source Guide even works on videos! To me, this could save tons of time. I can scan a long article pretty quickly, but it’s hard to do the same with a video. Sure, you might be able to find the transcript and scan that, but the Source Guide makes it SO MUCH easier. I might not use the Source Guide a lot, but it will be a huge time saver when I do.
Discover Sources
The second new feature lets you quickly discover relevant sources. It’s been around a while, but is still relatively new. When you create a new notebook, you see this screen:
Notice discover sources in the upper right corner. Clicking on this brings up a chat window in which you can describe what you’re looking for.
To test this out, I said I was interested in videos about bias in AI. A few moments later, I had a notebook of ten sources. Interestingly, NotebookLM did NOT limit the sources to videos. Notice that you can unselect sources that you do not want to include in your notebook. Clicking on Import creates the notebook and brings in the sources. From there you use the notebook as normal.
Here’s what the notebook looks like. You can add new sources that you find on your own, or can use NotebookLM to discover additional sources. I probably won’t use Discover Sources much for my scholarly work since I probably already have credible sources, but for more casual uses this seems like a great addition.
Bottom Line
These new features—Source Guide and Discover Sources—significantly enhance NotebookLM's usefulness. Source Guide makes it easier to manage large collections of documents and videos. Discover Sources streamlines the initial research phase, though it's best used as a complement to traditional academic source gathering rather than a replacement.
But there's a bigger story here: the dizzying pace of AI development. Google's rapid iteration on NotebookLM shows how quickly the AI landscape is evolving. Just nine months ago, NotebookLM was a relatively simple RAG implementation. Today, it's a sophisticated research assistant with mind mapping, source discovery, and intelligent document summarization.
Keeping up with these developments, and more importantly, understanding how to leverage them effectively, is crucial for everyone in higher ed. That's why I write AI Goes to College. Subscribe now to stay informed about the latest AI tools and strategies that can enhance your research and productivity.
Postscript: AI Assignment Repository Survey
If you haven’t already done so, I would appreciate it if you would complete this short survey gauging interest in a free, open-source repository of learning activities that discourage inappropriate AI use and/or leverage AI to enhance student learning. We’re planning to close the survey at the end of June.
Want to continue this conversation? I'd love to hear your thoughts on how you're using AI to develop critical thinking skills in your courses. Drop me a line at Craig@AIGoesToCollege.com. Be sure to check out the AI Goes to College podcast, which I co-host with Dr. Robert E. Crossler. It’s available at https://www.aigoestocollege.com/follow.
Looking for practical guidance on AI in higher education? I offer engaging workshops and talks—both remotely and in person—on using AI to enhance learning while preserving academic integrity. Email me to discuss bringing these insights to your institution, or feel free to share my contact information with your professional development team.