Designing Notebooklm

That said, this article was a very nice overview. Clean page, interesting to see his perspective. He clearly took tare and thought about the project. I don't agree with his conclusions and results, but that's just one user. Hopefully we see more thoughtful approaches. The space moving so quickly doesn't exactly foster a craftsman-like care in design.

NotebookLM: obviously useful, but I just wanna select some files and chat w/ them or have them summarized for me. It's got low info density, way too many cards/buttons/sections/icons, and it makes the core UX really difficult for me to navigate.

This post: I wanted to know what cool thoughts he had while designing it. Instead I get some weird scrolljacking, image carousels, unnecessary visual hierarchy, cards galore, etc.

Not trying to be too negative, it's slick and all but it just gets in the way for me instead of disappearing.

I currently support a data application where the vendor's documentation for it is not particularly well organized. It's spread across dozens of PDFs, sometimes without particularly well reasoned organization. Dumping all those PDFs into NotebookLM has been extremely useful since it allows us to ask questions that either give us answers, or are immediately fruitless requiring us to contact the vendor. Having an LLM capable of processing all that text has been great.

I've also used it with tabletop roleplaying game manuals. It's especially useful for badly organized TTRPGs, or those with poor indexing. Being able to type a question out in the middle of a game and getting an answer without having to dig through the book and find it yourself can be really very useful.

What I've never found a use for is anything in the Studio pane. They're neat tools, but... it's never been anything I've wanted or needed.

I also don't get why NotebookLM refuses to write things either, I can't make it write an essay based on the information I fed through PDFs or other files.

Other than the podcast thing of course which is unique.

Mostly curious about perspectives of folks who used both and can compare them.

As I designer I was trying to skate to where the puck was going technically. We’d get some insight on what was coming from the model side and we’d try to build UI around that future before it arrived. The labs team at Google has done a solid job of trying to build with that mentality.

We were in a mad dash for 1.5 years launching early and listening to user feedback then iterating our way to where the product landed. As I mentioned, those close to me knew how all consuming this process became. It was an amazing time taking a new product from 0 to 1 inside Google.

I Definitely never expected my portfolio site to make the rounds like this!

The most recent example of this is with the addition of 2 new capabilities (Flashcards and Quiz), "Artifacts Button Container" now has 6 large buttons, and is 328px in height! There are users who are accessing the site from small screen devices in India and they have been asking for help on Discord forums because they cannot see their notes anymore. So I had to create a Tampermonkey script to let users collapse it.[0] I heard the team is fixing that soon, but they should have done more testing before releasing it.

There are other issues like this that I've fixed with scripts. The strangest one is the "notes." Why force the users read a 2000 word essay in a 360px sidebar? So I wrote a script I wrote to let you pop it into full screen mode.[1]

Another example is the chat input field. The follow up questions are hardly usable at all. And they're not stable after you select them.

I can go on all day, but I think it's better to fix things than to complain.

[0] https://gist.github.com/volkanunsal/94db50629cad816eca84c836...

[1] https://gist.github.com/volkanunsal/fded9124d62422c0d2672b8a...

The user interface has been confusing to me. And note, I have built some projects using notebooklm https://asimov.learntosolveit.com

and if you're not very clear about what drove notebooklm's success you might be at risk of cargo culting ALL of their process instead of just focusing on the thing that worked.

But I think there are a few things that I noticed about NBLM which was painful for me.

1// The three panels should be toggle based with icons on the top bar. There is no need to occupy real estate for both notes and chat together if they are not being used together.

2// The center of screen or the largest middle section should be focused on outputs and not chat. If you are focusing on creating something why should it be on the side. Especially since chat isn’t all that special a feature compared to the audio overviews, etc.

3// Information density - the buttons and icons are all too large and clunky. You are in fight for real estate because AI is helping you process superhuman amounts of information.

I think the magic of NBlM is the audio overviews, the chat based Q&A is with citation is pretty standard for all LLMs.

Also I think it only uses Gemini flash which feels like a search model - this needs to be paired with a reasoning model instead.

“Synthesizes learnings into a scalable and adaptive layout.”

Genuinely curious: what is inherently scalable and adaptive in a three panel layout?

Pretty awful UX to be honest. Credit goes to the backend engineers who made this happen.

Took me ages to figure out you can copy paste simple text. Editing any text isn't great either.

Why isn't there a dedicated markdown notes section with folder and files? Most of us won't have ready to use PDFs but almost all of know how to use a text editor and paste text into it. Your Notes app UI is without proper support for editing and maintaining notes.

I've been working on my own knowledge management app to help small businesses with high part-time and employee turnover to manage FAQs and centralize local expertise. I think the 3-pane with the chat in the middle is a really clean way of making a whole library knowledge repository easily accessible, especially for someone wanting to avoid minimize clicks or as you say 'tab-overwhelm'.