Jeroen Sangers logo Jeroen Sangers

Can you have a real conversation with your notes?

Niklas Luhmann, the prolific sociologist behind the Zettelkasten method, often described his note-taking practice as having a conversation with his system. He would write a note, and the system would “respond” by surfacing related ideas, unexpected connections, unexpected tensions.

It was a metaphor. A beautiful one, but still a metaphor.

But what if it didn’t have to be?

At the PKM Summit in Utrecht last week, I proposed a breakout session around exactly this question: what would it mean to have literal voice conversations with your personal knowledge management system? Not just speaking to transcribe, but speaking to think, and having your notes respond.

I’ll be honest: I went in with more questions than answers. And I came out with even more. But the discussion surfaced a framework that I find genuinely useful.

The four levels of voice interaction

The participants in our session quickly recognized that “voice with PKM” means very different things depending on how sophisticated the interaction is. We mapped it into four levels.

Level 1: transcription

This is where most people start. Tools like Wispr Flow, Onit, or Handy let you speak and get text back. It’s a fast, friction-free way to capture thoughts, especially useful when your hands are busy or you think faster than you type.

Useful, certainly. But this is essentially just a faster keyboard. Your PKM isn’t doing anything with your ideas yet.

Level 2: AI post-processing

Here’s where it gets interesting. You speak your thoughts, including instructions, and AI restructures them into something more useful than raw transcription.

This is what I do myself. I’ll verbally draft an idea in Tana, weaving in instructions like “turn this into bullet points” or “reorganize this around the main argument.” The result isn’t just captured speech; it’s been processed into a form my PKM can actually work with. Non-linear thinking becomes structured notes.

The key difference from level 1: you’re not just inputting; you’re collaborating.

Level 3: interactive voice dialogue

At this level, the AI doesn’t just process your input, it engages. It asks clarifying questions. It pushes back. It says: “You mentioned three different things here; which one is the core point?”

This is where voice starts to feel like the conversations Luhmann was describing, and where I’m currently experimenting myself. Using the voice chat feature in Tana, I’ve found that my thoughts become sharper not because I transcribed them, but because something challenged them. It’s slower than level 2, but noticeably deeper.

Level 4: the Jarvis mode

This is the aspirational level. Imagine being able to ask your PKM: “What did I decide about this project in January?” or “What sources have I read on habit formation?” and getting a coherent spoken response drawn from your own notes.

Full integration. Your PKM as a genuine thinking partner you can speak with, not just write to.

We’re not there yet. But the direction is clear.

The tension I can’t resolve

Here’s what I keep coming back to.

A few years ago, I wrote a post arguing that writing is the best medium for deep thinking. The act of writing forces you to formulate ideas clearly, to make vague thoughts concrete, to notice where your logic breaks down. The friction is the feature.

Voice removes that friction.

So is voice input actually good for thinking, or just good for capturing? Is it a shortcut that helps you move faster, or a shortcut that lets you skip the hard part?

I don’t have a clean answer. My instinct is that levels 1 and 2 are primarily about capture efficiency: getting ideas into the system faster and with less friction. Levels 3 and 4 are where real thinking might happen, but only if the AI engagement is substantive enough to replicate what writing does naturally.

The question is whether today’s tools get there.

Where are you?

Most people working with PKM systems are operating at level 1. A smaller group has reached level 2. Levels 3 and 4 are still being figured out.

What I took away from the PKM Summit is that the ceiling is much higher than the current tools suggest. And that the interesting work isn’t just building better transcription. It’s figuring out how spoken dialogue can become a genuine mode of thinking, not just a faster mode of typing.

Luhmann’s metaphor might become literal sooner than we think.

At which level are you using voice in your PKM? And do you think voice can ever match writing as a medium for deep thought?

🛫EIN – BCN 🛬 I’ve had a blast at the PKM Summit! Still wrapping my head around everything I saw and heard.

Two of my productivity tips made it into the March issue of Forbes España: on beating procrastination and taming your inbox.

A person wearing glasses and a red sweater is sitting atop a clock, surrounded by a text discussing how to overcome procrastination.

Multitasking leads to an overestimation of your own ability to perform multiple tasks simultaneously

Multitasking is a common phenomenon in our modern society, but research shows that we are much worse at it than we think. The problem lies not only in the fact that we struggle to perform multiple tasks simultaneously, but especially in our inaccurate assessment of our own capabilities. Studies show that people who frequently multitask wrongly believe they are doing so effectively. They significantly overestimate their abilities, while the reality is different. This lack of self-awareness is worrying: we are not only bad at multitasking, but we also seem unable to see or acknowledge it.

The consequences of frequent multitasking go beyond just a distorted self-perception. Research on chronic media multitaskers, people who regularly process multiple media streams simultaneously, shows striking results. These heavy multitaskers are actually more sensitive to environmental distractions and irrelevant information in their memory. Paradoxically, they even perform worse on tests measuring the ability to switch between tasks, likely because they are less capable of filtering out distracting information. This suggests that frequent multitasking is associated with a fundamentally different way of processing information.

The comparison to a drunk person who thinks they are walking in a straight line captures the problem well: we think we are better than we actually are. Thus, multitasking creates a dangerous combination of reduced performance and inflated self-confidence. As multitasking plays an increasingly larger role in our daily lives, it becomes all the more important to be aware of these limitations and the gap between our perception and reality.

The artisan and the tinkerer

Last week I read about custom vibe-coded RSS readers: quick and scrappy tools, non-polished, built to solve a particular need of their owner. Today I read about Current, which has thoughtful design, interesting concepts, and attention to detail.

And then I noticed something curious.

Two divergent paths

On one hand, there’s this artisan tendency. People who dedicate time to building personal tools with the same mindset a cabinetmaker uses to make a table: every decision matters, every detail counts. The result is beautiful, thoughtful, unique software.

On the other hand, there’s the explosion of tools made with the help of artificial intelligence. Quick solutions, imperfect, often somewhat rough. But deeply personal. Software that does exactly what you need, even if it won’t win any design awards.

Two completely different approaches. And both are happening at the same time.

They’re not opposites

What’s fascinating isn’t that both exist, but that they coexist without conflict. They’re not opposing approaches; they’re different answers to the same question: what should my tools look like?

The artisan values the process as much as the result. Technical perfection, elegance, the pleasure of doing something well done. It’s software as personal expression, as craft.

The person using artificial intelligence values speed and perfect adaptation to their specific case. They prefer something imperfect that works today over something perfect that requires months. It’s software as a practical extension of oneself.

Neither approach is better. They simply prioritize different things: craft versus immediacy, polish versus personalization, beauty versus direct utility.

And you?

Here’s the question: where are you on this spectrum?

When you think about the tools you use every day, the software that surrounds you, what do you value most? Do you care that something is well made even if it’s not exactly what you need? Or do you prefer it to fit like a glove to your way of working, even if it has rough edges?

There’s no right answer. But knowing what you value says a lot about how you relate to your work, to your time, to what you consider worthy of your attention.

What kind of tools are you building, or choosing, for yourself?

AI slop isn’t coming from the AI. It’s coming from the decision to skip the editing, to treat the tool like a magic button. AI amplifies your process. If your process is “generate and go,” that’s what shows up. Are you reviewing what you publish, or are you just hoping it’s good enough?

Audio conversations promote a more equal distribution of speaking time and alignment of speaking patterns, which leads to better group performance than video meetings, despite the absence of visual cues

When we are physically in the same space, we use various subtle signals to manage speaking turns: eye contact, facial expressions, and body language. This leads to a more even distribution of turns among everyone. In audio conversations, these visual cues are absent, so you focus entirely on auditory signals such as pitch, speaking speed, pauses, and small sounds indicating someone wants to respond. In video meetings, which theoretically offer more data than audio conversations, we pay less attention to audio cues, while visual signals are less perceivable on a screen. Interestingly, the limitation of audio conversations actually ensures you listen better to auditory signals and respond more effectively than in video conversations. This results in everyone having more equal speaking time, preventing anyone from easily dominating the conversation.

This more equal distribution of turns positively affects what researchers call ‘prosodic synchrony’: you better align your rhythm, intonation, and speech patterns. When you have more equal turns in an audio conversation, you naturally become more attuned in how you speak. You unconsciously mimic each other in tempo and pitch, resulting in a smoother conversation. This alignment contributes to what is called ‘collective intelligence’: the ability of a group to solve problems together. Teams using only audio are more successful in synchronizing their voice usage and turns, and when they achieve this, they perform better as a group.

Although video theoretically offers more information, in practice, visual signals are less perceivable than in in-person meetings. This raises questions about the assumption that richer media are always better for remote collaboration. For certain forms of teamwork, audio meetings can be more effective than video conferencing.