For the full, up-to-date post this audio connects to, visit https://wondertools.substack.com/p/notebooklm

Google’s NotebookLM is a new free service that lets you apply AI to your own notes and documents. You can use it to find connections between your own ideas and see patterns you hadn’t noticed. Read on for how I’m using it, what I like most about it, its limitations, and interesting alternatives.

How to start using NotebookLM

Sign up free at notebooklm.google.com Upload up to 20 documents into a collection of material you want to explore. You can add PDFs, Google Docs, or other materials you’ve either written yourself or gathered as part of your research. You can create multiple collections for different topics.

Tip: I recommend creating separate collections for your own writings and for research that you’ve gathered from others. That way there will be clear demarcations between your own material and what comes from others.

I have a collection about entrepreneurial journalism, for example, with a variety of notes and materials I’ve created over time. I’m building another one focused on the history of classical music, with articles, research and notes I’m gathering from others.

What to use NotebookLM for

Analyze your own material

Once you have a collection, NotebookLM creates asummary for each of the documents in it. It also add subject matter tags based on the content. Anytime you want to remember what’s in a particular document you’ve added to your collection, you can select it to see the AI-generated summary and the subject tags. You can then query a particular document, a subset of the documents in your collection, or the full collection. That’s helpful if you want to analyze material from a particular source that you’ve added, or just documents on a narrow subject.

Suggested queries

NotebookLM will also suggest a few queries you can start with, based on its analysis of material you’ve uploaded. For example, in my collection of entrepreneurial journalism notes, it suggested queries about best practices for presenting startup projects.

It suggested that because I had written extensively about presentation tactics in the documents I uploaded. When I clicked on that query, NotebookLM drew from various strands of materials in my notes and created a summary of some of my key points. To help me identify where it was sourcing the material in that summary, NotebookLM provided a a list of 10 citations from across the 9 documents I had uploaded thus far to that collection. I could click through to see those original sections it was drawing from to understand how the AI was sourcing its material. I could later add to the collection new materials.

Ask your own questions

In addition to using suggested queries that NotebookLM provides based on its analysis of your materials, you can pose any question you want. I could ask my own notes, for example, about the highest potential — and most challenging — revenue streams to pursue for those producing independent podcasts. Rather than searching across the Web, or digging into some an abstract AI predictive data model, as other AI tools do, NotebookLM scours its analysis of my own notes to pull together an answer and citations.

While chat AI services like Claude, ChatGPT, and Gemini are useful for a wide range of queries, your responses may be hard to trace back to any particular source unless you’re using a custom AI trained on your own material. That’s what’s most special about NotebookLM: you benefit from the power of AI applied specifically and narrowly to analysis of your own notes.

Building on your own notes

After querying NotebookLM you can save its responses and build on them to make new notes. If you’re preparing a presentation, a report, or analyzing trends or patterns, you can use NotebookLM as a partner in exploring your materials. You can have a dialogue with your own notes in a way that goes beyond searching for keywords or simply re-reading individual documents.

Limitations

* It’s not available to everyone yet. I can’t use it with my work account, only with my personal Gmail. It’s not open to people in all countries yet.

* There’s no mobile app, though the mobile Web version works well for simple queries.

* The design still feels a bit clunky to me. The interface includes multiple panels — one for your source documents and another for your queries, alongside various notes you save or create. Given that this is a new kind of tool, it may take some time for the service to shed clutter and provide a more streamlined view.

* Google doesn’t train its models on your material, which remains private to you, but if you are skeptical about the company, you may not want to upload private material.

Alternatives

* Mem.ai is a tool for digital notes that also brings AI to your own materials.

Unlike NotebookLM, which is free, Mem has a TK cost and works on TK platforms and unlike NotebookLM, is available everywhere CheckTK. When you start typing a note, its AI can helpfully surface related notes. And the helpful chat function lets you ask natural language questions to surface notes. I wrote about why Mem is like a next-generation Evernote. I don’t use it as my primary notes tool because the design and interface no longer appeals to me.

* AnythingLLM is a promising new software tool you can download to create a private repository of material to analyze with AI on your own computer. I'm still testing and will be able to share more in the future on this.

Final thought

AI flavors are expanding. AI for multimedia, AI for search. What’s exciting about a new tool like NotebookLM is that you can apply AI with a narrow lens to your own material. What are your thoughts on this new direction for AI, how are you using it, or what other AI tools are you most excited about?