There’s a specific kind of tired that doesn’t go away when you close your laptop.

It follows you to dinner. It’s still there when you’re trying to sleep. It’s why you reached for your phone in the middle of a conversation that deserved your full attention. It’s the reason your evenings don’t fully belong to you.

The low hum of open loops: commitments half-made, threads you meant to pick up, the thing from last week’s meeting you haven’t let yourself forget.

At some point, something slipped.

Maybe it was small. A reply you forgot to send, a follow-up that came a few days too late. Embarrassing for a moment, but recoverable.

Or maybe it was bigger. The kind of fuck-up you still think about.

What would have happened if you hadn’t let it slip?
What opportunities did someone else pick up instead?

Meanwhile, someone with the same workload was juggling fifteen of those threads without dropping one.

You’ve seen this person.

The one people lean on because they know they won’t drop the ball.
Walks into every meeting with what feels like an abnormal memory.
Knows the thread from three conversations ago.
Never scrambles.

The person who makes you wonder if the Red Sea just parts for them. While the rest of us are fighting desperately to stay above water.

The one whose work stops when they leave work.
Who is actually present at dinner.
Whose evenings belong to them.

That’s who got those opportunities you missed out on.

Not more talented than you. Not working harder.

Just a better system.

And the frustrating part is you’ve tried to build one.

Everyone has some version of a system.

It works well enough when things are manageable. But as soon as life piles on, the same system that was holding you starts holding you back. A burden you carry out of habit more than hope.

Every tool that was supposed to fix that made the same promise: if you just captured it properly, nothing would fall through.

It still fell through.

Not because the tools were bad. Because every one of them asked you to adapt to it. None of them could keep up when the workload hit.

Here’s why: our brains were never built to hold open loops. They were built to think, to connect, to create. Not to act as a filing cabinet for every commitment made in every meeting ever attended. Every unresolved thread you’re carrying is taking up space that was supposed to go somewhere else.

The problem was never your discipline. It was that you were asking your brain to do something it was never designed for.

For the first time, the system adapts to you. Not the other way around.

What makes that possible is thinking in projects.

Every project gets a home: one page where everything connects back to it. Meeting notes, work sessions, tasks, decisions. Not scattered across three apps and a notebook. One place.

I had a call last week with a client I hadn’t spoken to in eight weeks. I typed two lines to Claude Code: “Create a meeting with Theo at 2pm tomorrow. Give me context.” Thirty seconds later the meeting was on tomorrow’s daily note, linked to the project, linked to Theo. Inside it: the summary from our last session, the full email chain, and every open item still outstanding. I walked in knowing exactly where we’d left off and what to prep.

That’s Obsidian as the structure, Claude Code as the assistant that handles the administration. The logging, the linking, the filing. All of it handled without you touching it.

This results in you having more time to think about the important things instead of spending an hour or two sifting through notes like a depressed European in the winter looking through their medicine cabinet for vitamin D pills.

The evenings come back. The dinners belong to you again. You become the person who walks into every meeting knowing exactly where things stand. Not because you have a better memory, but because you stopped asking your brain to do a job it was never built for.

That’s the system. The one that makes you the person who never scrambles.

Want to build it out?

Lifestack-OS (free webinar happening 2026-05-09)

Website

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Lifestack-OS | Newsletter

Think about every area of your life that has some level of admin attached to it.

Your work. Your journaling. Your travel planning. Your finances. Your family responsibilities. Your social life: the birthdays you want to remember, the restaurants you want to try, the people you keep meaning to catch up with. Your hobbies. The ideas you have, business or creative. The things you read and watch and want to come back to.

Most people carry all of this in their flesh computer - aka their brain. Or spread across ten different apps, saved links, and notebooks they haven’t opened since the week they wrote in them.

Think about the last time you were at dinner and not fully there. Something churning in the back of your mind. Work, life admin, something unresolved. That is not a focus problem. That is a system problem.

Your brain was never built for storage. It was built for thinking. Every open loop you’re holding in it is taking up space that was supposed to go somewhere else.

After four years of consulting and helping people build PKM systems, I have found that almost all of it falls into three buckets. Three areas you can build out directly in Obsidian, that between them cover most of the overhead in your life.

Your days. Your work. Your curiosity.

Your Days

Not everyone needs a journaling system. Everyone can benefit from one.

We have all heard about the payoffs of a journaling practice. It gives you space to reflect on your life and where it is heading. It helps you understand yourself well enough that you get to the end and can honestly say: this was a life well lived.

The only way to know if your life is still on track is to have regular moments of reflection, and you can only reflect meaningfully if you have something to look back at.

The minimum effective dose is a short summary of your day and a rating. That is enough. If you want to go further, add three photos and a running log of what you did. Suddenly you have a window into every day you have ever lived.

Once your days are connected to everything else in your system, you can set long, medium, and short-term goals and actually see whether your daily life is moving towards them. Not at the end of the year when it is too late to course-correct. Every week. Every month. Your days tell the story. The system just makes it readable.

Most people attempt this kind of reflection at their yearly review. By then the substance of the year is already gone.

Your Work

Everyone has career, work, study, or entrepreneurial ambitions that take up a large portion of their life. And because the portion is large, the overhead is large. Meetings, projects, stakeholders, follow-ups, work sessions: all of it generating threads that need to be held somewhere.

Having a single place where everything related to a project lives (meetings, work sessions, tasks, people) does two things. It makes the current project easier to navigate. And it makes every future project easier too, because the context never disappears.

You walk into every meeting knowing the full thread behind it. Nothing slips. Your work stops following you home.

Your Curiosity

Your ideas are disappearing. Not because you are not curious. You are more curious than you think. But because there has never been a single place for them to land.

The book recommendation buried in a DM. The business idea from a walk. The interest you filed under “later” that is still there, three years on, waiting.

All of these have a fingerprint in them: the particular combination of things only you would find interesting. A picture of who you actually are, the potential that you have never been able to see because the pieces were never in one place.

Give them somewhere to land and the picture starts to form. Your hobbies stop being things you mean to get back to. They become things you actually do. Your interests compound instead of dissolve. You look at what you have collected and think: oh. So this is what I am like.

Why now

Up until the end of 2025 a PKM still required a lot of work.

People who built and maintained these systems genuinely had an edge. They thought better, worked better, dropped fewer balls.

But there was a catch: maintaining the system was in itself admin.

You still had to write the summary. Still had to manually link and tag the note. Still had to process the meeting before the next one started. The system offloaded admin from your brain, but handed some back in the form of upkeep.

For most people, when life gets busy, that upkeep was just enough friction to stop them entirely.

That wall is now gone.

Tools like Obsidian - with Claude Code stacked on top of it - offer, for the first time, what a perfect PKM should actually look like. One where the maintenance happens automatically. Where the input is as effortless as speaking a sentence. Where the system adapts to you, not the other way around.

The payoffs were always real. Now the cost of entry has almost entirely disappeared.

That is why now is the perfect time to start.

The tools: Obsidian, Claude Code, and voice-to-text

Obsidian

One year from now you will have a vault that knows more about your life than any app you have ever used.

Every project you worked on. Every person you’ve met. Every idea you had, connected to every related idea that came before or after it. All of it searchable, all of it yours, sitting on your own device with no subscription and no company that owns it.

That is what Obsidian builds over time. Calling it a note-taking app is technically accurate and completely misses the point. What makes it different is not what it stores. It is what it connects.

What makes Obsidian different from other note-taking apps, is linking.

Notes connect to each other. A project connects to its meetings, its tasks, its people. A person connects back to every conversation you have had with them.

The longer you use it the more the connections multiply, and the more the vault starts to feel less like a filing system and more like an extension of how you actually think.

Claude Code

Every system you have tried before had the same weakness: it needed you to do the admin. Write the summary. Link the note. Process the meeting. File the idea. And at the end of a long day, that was exactly the thing you skipped.

Claude Code removes that layer entirely. It is a personal assistant that sits directly on top of your Obsidian folder, reading it, writing to it, acting on it, without you copying and pasting anything into a chat window. You teach it how you work once. After that it handles the parts you used to skip. You instruct it in plain English, as you would a personal assistant sitting right next to you. You don’t need to be technical. You just need to know what you want.

But it doesn’t just stop at Obsidian. You can connect it to your email, your calendar, excel workbooks, presentations, and a plethora of other services.

Because it has the full context of your vault, it does not just fetch information: it connects it.

Ask it to summarise the emails that came in overnight and it ties each one back to the project it belongs to. It already knows the thread, the history, the people involved.

The more you use it, the more it understands you. The admin that used to fall on you gradually falls on it instead.

Voice-to-text

The last piece of friction in any knowledge system is typing. We now have highly accurate voice-to-text services - Wispr Flow is one - that work system-wide, in any app, in any language. You speak, it types. The barrier to capturing something drops to near zero.

Speak a thought on a walk. Dictate a meeting note in the car. Add a log entry while you make coffee. It lands in your Obsidian, claude processes it.

A PKM still needs structure

The tools are only half the equation. Without a tested structure underneath them, an empty vault is just another app you opened once.

The foundation lives in your Obsidian vault and is built around three things.

Daily notes first. Your daily note is your entry point to every single day. Everything starts there: what you are working on, who you are meeting, ideas you want to capture, how the day went. It is not just a journal. It is a living index that connects outward to everything else in your system: your weekly, monthly, quarterly, and yearly notes; the projects you are pushing forward; the topic pages that organise your thinking. One note a day. Everything else flows from it.

A project structure. Every project gets its own note. Your work sessions connect to it. Your meetings connect to it. Your tasks, your stakeholders, your decisions, all anchored in one place. The context for any project is never more than a click away, whether it started yesterday or two years ago.

A logging system. This is the connective tissue between the daily notes and the project structure. It is a methodology that allows information captured anywhere in your vault to flow automatically to the places it belongs. Nothing needs to be manually filed. The system routes it.

Claude Code sits on top of all three. In the beginning it handles the admin: capturing, linking, processing, retrieving. The more it learns how you work, the more it becomes your thinking partner that already has the context before you ask the question.

This is the combination we have not had until now. A personal assistant with the full context of your knowledge base, connected to your email and calendar, that you can speak to in any language without touching a keyboard.

If this is the structure for you

Without a tested structure, most people lose momentum within the first two weeks. Not because the tools are hard (they are not) but because an empty vault with no methodology is just another blank page. The question that kills it: is this really worth it?

The honest starting point: go to YouTube, find an Obsidian and Claude Code channel you resonate with, and start with their structure. Commit to one system. The specific one matters less than sticking with it.

If the approach in this article resonates: daily notes as your entry point, a project structure that connects your work, a logging system that ties everything together. You do not have to build it yourself.

LifeStack OS hands you the structure on day one. A fully configured vault: daily notes, project structure, logging system, and Claude Code already set up and working. Three live sessions to make it completely yours. One week later, an office hour where the group shares what they built.

By the end you will have a system most people spend years trying to piece together - or never build at all.

Next cohort starts 16 May 2026.
Claim your spot: lifestack-os.com

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Lifestack-OS | Newsletter

Last month, a friend texted me the night before she landed in Amsterdam. She’d just ended a long relationship and booked the trip on impulse.

“I don’t know anyone there, I don’t know what I’m doing, I just need someone to point me somewhere.”

So I run the same routine, as I have countless times before:

• dig through my notes

• pull out the restaurant recommendations

• find the museum that’s worth the queue

• what running clubs to join

• remember which neighbourhood to go to for a drink at sunset

I spent forty minutes digging through three years of Amsterdam notes. Typed it out. Sent it.

She wrote back: “This is exactly what I needed. It felt like having you there.”

That’s when it hit me: she was essentially talking to my notes. Not to me. I was just the translator.

Which got me thinking: what if she could just ask the notes directly, without me in the way?

Here’s what’s now possible that wasn’t two years ago.

You take a specific slice of your Obsidian vault, just the Amsterdam notes, with all your opinions on each place, why you like it, when to go, the spots worth the queue. Point a chatbot at it. Share a link.

She messages:
“Best cafes for sundowners in Amsterdam?”
“Any running clubs I can join?”
“Links to buy museum tickets?”

She gets your notes. Your opinions. Your experience. Not a stranger’s review on Google. A conversation with a version of you that knows Amsterdam and knows her.

You could do this for any knowledge you’ve spent years accumulating:

• Travel - every city you’ve lived in becomes a queryable guide

• Work handovers - a new team member inherits a knowledge base they can ask questions to, instead of documents that go stale

• Jiu jitsu - your training notes, recovery protocols, gym recommendations. Your training partners get to ask your experience questions while you’re asleep

• Parenting - your frameworks on money, health, relationships, passed to your kids not as a letter but as something they can have a conversation with

The problem

Most of us don’t capture our lives.

Not because we can’t. Because we don’t think our story is worth telling. We assume our experiences are ordinary, our opinions unremarkable, our daily life too mundane to record.

But you are the most interesting story you will ever have access to. Nobody else will live your specific combination of cities, relationships, failures, and hard-won lessons. Nobody else will have your take on things.

The laziness excuse used to hold up. Writing takes effort. But AI has quietly removed that barrier - you can speak, ramble, half-finish a thought, and something useful comes out of it. That excuse is gone.

What’s left is the belief problem. You have to actually think your story is worth capturing.

And if you do? The sharing part takes care of itself. Ask an AI to extract the relevant subset. Strip out anything sensitive. Hand it over. It’s like a surgeon carefully slicing out a piece of your brain, making a copy, while making sure the important bits stay attached and safe.

So far we’ve been talking about sharing with people who are here. Friends visiting your city. Colleagues inheriting a project. Your kids asking questions you’ve already answered in your notes somewhere.

But there’s a version of this nobody thinks to ask until it’s too late.

What happens to your story when you die?

Right now: nothing. It disappears with you.

My grandfather died before I could ask him anything useful. And it’s not just the big questions I missed out on. It is the mundane. The boring questions that only a grandson would find interesting. What he ate on a random Tuesday. His favourite book. What his parents were like. His favourite childhood holiday. The best place he ever lived. What he actually thought about my grandmother the first time he met her.

What having my father as a son was like, watching someone become the person I’d one day call Dad.

Nobody thought to write it down. He certainly didn’t. And now the knowledge is just gone.

But plain text files outlive every app ever built on them. An Obsidian vault from today is still readable in 500 years. The AI layer that makes it conversational: it exists right now, and it will only get better.

The conversation I couldn’t have with my grandfather is the one your grandchildren could have with you. Just by you writing things down, in your own words.

A vault full of clipped URLs and half-finished notes doesn’t become a conversation partner. A vault full of your actual thinking does: your opinions, your reasoning, your specific experience. Not what you know but how you know it.

That’s what makes your journal more valuable every year you keep it. Not because you’ll reread it. But because someone else might need it, in ways you can’t predict, at a time when you won’t be around to answer the question yourself.

But you choose to be selfish...

Questions I’m still sitting with:

• Does knowing someone might query your vault one day change how you write in it?

• How do you structure a vault to be navigable by someone who didn’t build it?

• What’s the line between public and private? Amsterdam restaurant notes: yes. Personal reflections: obviously not. But where exactly is that line?

• Could this become social? Friends seeing who else has used your recommendations, connecting through them.

I’m building the Amsterdam version first and I’ll document the whole setup.

If there’s a slice of your vault you’d want to make shareable, what would it be?

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Lifestack-OS | Newsletter

-2 is the worst day you could imagine. +2 is the most blissful. 0 is dead average - not good, not bad, just another Tuesday.

I thought it was a slightly obsessive thing to do. Turns out it’s the most useful thing I’ve ever done.

Here’s what I found. My best days almost always have at least one of three things in common:

• Novel - learning to snowboard, traveling somewhere new, trying a drawing class, long-boarding through Vondelpark

• Difficult - producing a YouTube video, giving a speech, competing in something, cooking a complicated dish

• Social - dinner with friends, a coffee catch-up, a phone call with family, celebrating someone’s birthday, a boat-ride with fellow humans

Now here’s what’s interesting. Theoretically I could do all three of those things in one day and still have a terrible day.

But that’s very unlikely.

And that’s the point. You have more influence over whether today is a good day than you think. The deck is stacked in your favour - you just have to know which cards you’re holding.

But you can only know which cards you’re holding if you’ve actually been paying attention.

Most people only attempt this at their yearly review. And by then, the substance of the year is gone. You try to reconstruct what made a day great or awful. It’s like asking someone to list every thought they had last week Tuesday.

That’s pretty much it. Start tracking your days, and whenever you sit down to reflect, whether that’s weekly, monthly, or at the end of the year, you’ll actually have something to work with. The enlightened Obsidian brethren/sistren reading this are already nodding.

So here’s your task, starting today.

Open whatever app you want. I will say that if you open a Google Doc I’m going to jump out of the screen and gut punch you, but honestly, any tool works. The software is the easiest problem to solve later. What you can’t do is go back and capture the days you didn’t track.

Give yourself a rating. Write two sentences about why. That’s it.

Just start capturing. Every day you wait is another day without data. And if your life is already great, good. Now find out exactly why, so you can make it even better.

If you want to see what this looks like in practice, here’s a screenshot of my own yearly review in Obsidian, filtered down to my best days. This is just one way to do it, the principle works in any tool.

See you at the end of the year.

And remember: all roads lead back to the daily note.

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Newsletter

My dad is severely addicted to his phone. He’d never admit it. But I’ve watched him pick it up and put it down more times than he’s looked his children in the eye (except of course for the grandchildren my sisters have bestowed upon my parents). Facebook’s algorithm has gotten very good at this.

If an alien species came to earth and only had my dad to make inferences about humanity, they’d conclude that a superior species in the form of a glowing brick had enslaved us.

Even as I’m writing this in a cafe, I can see people getting dopamine-punched every 90 seconds when the telepathic siren-call of their phone goes off. Looking up from their laptops, checking their phone, hot-potatoing through every app, putting it down, picking it up again - oeh, what is this? Another hot potato.

Cal Newport, the author of Deep Work, believes one of the biggest competitive advantages you can have in the coming years is the ability to sit down and do deep, focused work.

Easier said than done with fresh “hits” just a button-click away. Now more than ever we are being robbed of our attention.

One way to cure this is to lock your phone in a kitchen safe for two hours. Another is to build the willpower to sit down and do the work.

But what I want to talk about is activation energy. The bottleneck isn’t willpower. It’s activation energy. How hard it is to start.

Most of us try to optimise with productivity apps, timers, cold showers, journaling routines. My approach is embarrassingly simple.

Restrict yourself to the confines of a meeting.

I stumbled onto this while trying to stop losing track of what I was working on. I started with what I call “logs” - a timestamp on my daily note with a bit of information about what I was working on.

Sometimes the log got long enough that I turned it into its own meeting - a work-session. Every work-session ties to a project, which makes everything easy to find. But something else started happening after a few weeks of working this way.

Four benefits I didn’t expect.

You never start from zero

I have a briefing command built into my setup that looks at the project, the previous work-sessions, outstanding tasks, and what my next steps are - and gives me a summary of my progress so far.

I don’t need to start from a blank screen anymore. I don’t have to go back through previous sessions to extract what I’ve done or what I need to do next. My AI assistant does it for me.

Never. Starting. From. Zero.

Four walls go up

Think of a cinema. You’ve created conditions to pay attention to one thing - the story playing out in front of you. You’re in a dark room, talking is frowned upon, your phone sits untouched in your pocket. The result is full immersion.

When I’m in my work-session, that is the only page that is open. It feels like being thrust into a cockpit where all other distractions are blocked out - at least for the 30 minutes I dedicate to it. It allows me to get into a flow state easier.

Your work-session is the stranger glaring at you when you try to open Instagram.

(Here’s the rabbit hole I’m saving for a future article - the more immersed we are in whatever we’re doing, the more value we derive from that time. Similar to being completely absorbed by learning a new skill that we are interested in, practicing a song on the guitar, or listening to your favourite musician live. Attention divided is attention lost.)

You see the progress

On this very article, I can see the Hansel and Gretel trail I’ve left for myself. If someone looked at this project and dove into each work-session, they’d see my thought process, the paragraphs I decided to remove, the iterations I worked through, the research I drew on to formulate my opinion - from inception to completion.

That trail doesn’t just feel good to look at. It’s receipts.

You create material for reflection

What gets measured gets managed.

Just “completing” the project doesn’t make the next one any easier. Having notes of how you completed it lets you see the shortcuts, the inefficiencies, and - above all - build something that helps future you.

This isn’t just about getting into flow. It’s about getting better at the work over time.

A chef won’t relearn a recipe. They write it down. When they need to whip up that Italian dish again, the note is ready. They don’t go back to an old lady in rural Italy to learn everything from scratch.

Yet here we are. Back in rural Italy. Every. Single. Time.

If you’re tired of being a slave to the pitiful (yet powerful) distractions of life, try the work-session approach. But be warned, it might make your life better - not everybody is ready for it.

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Newsletter

Last year, the tech geeks were quietly talking about AI tools in the dark corners of the conference. Still niche, still early adopter energy.

This year, that was everyone.

Old, young, no coding background whatsoever. Building read-it-later apps, book catalogues, study assistants, home automation systems, mindfulness applications. Someone even built a personalised music teacher for their kid. All of it inside Obsidian, all with Claude Code.

You can now build something like that in 10 minutes. And the best part? It’s yours. No subscription. No company that owns your data. Yours.

The age of traditional apps is dead. The age of personalised, self-built apps is here.

Clive Thomson is a tech journalist who has spent decades covering the intersection of people and technology. He attended the summit and said it gave him a glimpse of what the future of PKM will look like. And he’s right. This is where we’re heading.

But Clive also said this:
“Every time new technology arrives, we’re excited and overwhelmed in equal measure. 20 years ago, what tools did we have? A word processor. Today we have too many to choose from. How do we manage this?”

My take-away question became: how do we stay essentialists now that almost anything is possible?

Most people never figure it out. Most hop from one app to the next promising one that promises to relieve all the tension that has been building up in their disorganised minds. But sooner or later, they all collapse under their own maintenance.

What finally fixes it isn’t discipline or a better app. It’s removing the friction entirely.

PKM systems don’t fail because people aren’t disciplined. They fail because the friction of filling things in is just enough to stop you from reaping the benefits. In the past it almost felt like an unteachable lesson - that you need to start and stop 10 different systems and methodologies, that you need to grind your teeth and build up the mental resilience to input the data in the right way, to use the correct template, to diligently sit and fill in your journal, to give that meeting a summary. End of a long day, you tell yourself you’ll process it later. You don’t. Three weeks later you’re piecing together fragments of memories you should know by heart.

I can finally say: it’s no longer a discipline problem. It’s a design problem. And it’s fixable.

And the scale of what’s now possible is bigger than most people realise. You can have multiple Claude instances running at the same time. One is processing your meeting. Another is doing your week review. You’re making coffee. This isn’t one assistant. It’s a department.

But with that power came a question nobody had a clean answer to. Another speaker at the conference, Thijs Pepping, said it best: “The more you measure, the more you behave like a robot.”

With data about ourselves so easily acquirable, how can we remain in the driver’s seat of our own lives? Will we quietly hand over the thinking to an algorithm?

We’re building systems to track sleep scores, day ratings, step counts, productivity metrics. At some point the measurement starts to erode the thing you’re measuring. Worth sitting with, especially for those of us building quantified-self systems in Obsidian.

What I’m trying to hold onto is this: AI wraps around your methodology, it doesn’t replace it. The structure of your life - your life areas, your projects, your daily rhythm - stays yours. Designed by you, for you. AI handles the admin layer around it. The logging, the summarising, the linking, the processing. The thinking stays human.

I don’t know if that’s the answer. But it’s the line I’m trying to protect.

I’ve never been more excited about where this is going. And I’ve never thought harder about what to protect from it.

We’re launching a 4-week live cohort in April to help you build this yourself.

Interested in building your own system?
Sign up and you’ll get a free email series + a free live webinar before the cohort opens - and first access when sign-up goes live.

https://lifestack-os.com/

Even one workflow that removes one piece of friction is worth it. That’s how the avalanche starts.

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Newsletter

Duncan is the knight. Without his sword and armour, he can still throw a punch, but can’t do the things a knight needs to do.

The sword isn’t just a thing Duncan holds. It’s an extension of him. With it, he reaches further, strikes harder, moves differently. Take it away and he’s a different fighter.

If you are here you already know this feeling. Your vault isn’t just where you store notes. It extends what you’re capable of thinking. Your links surface connections your brain forgot it made. Your structure holds context across weeks and months that your memory never could.

If my Obsidian vault got deleted tomorrow, I wouldn’t just lose files. I’d lose a part of how I think. A small piece of my brain, chipped out. That’s how deeply these tools become part of you. In cognitive science they call this extended cognition: your mind doesn’t stop at your skull.

But there’s a lot of admin that comes with these tools. The sword needs to be sharp. The armour needs to be polished and maintained. All of it makes Duncan a better knight, but none of it is fighting.

That’s where Egg comes in. The squire. He sharpens the sword, polishes the armour, handles the logistics. Egg removes the friction so Duncan never has to stop being a knight to do maintenance.

That’s what AI is for me. That’s what Claude Code is. It handles the formatting, the tagging, the linking, the filing. All the stuff that keeps the system running but isn’t the actual thinking.

But here’s the thing about Egg.

Egg can sharpen the sword. Egg can’t (or rather, shouldn’t) swing it.

Skills are built through doing. Duncan becomes a better fighter by swinging his sword, getting bruised, taking that feedback to better approach challenges in the future. In cognitive science they call this enacted cognition: understanding created through action.

When you decide what to capture, how to structure a note, what connects to what, that’s you swinging the sword. The thinking happens in the doing. Not before it, not after it, in it.

This is the part most people get wrong with AI. You should know your structure. You should be the one enforcing it.

If you don’t, if you let AI run wild in your vault and do the structuring in a black box without you understanding it, it starts modifying the sword in ways that don’t reflect you. The tool stops being an extension of your mind. It becomes an extension of something else.

Once you don’t understand your tools anymore, the connection between you and the sword is broken. And a sword you don’t understand isn’t useful anymore.

The optimal way is to use your squire to talk through how to make the tools better. You understand what it’s doing. You can see how the sword is changing to your benefit. You’re in the loop.

Anything more than that, where the squire starts making decisions without you, that’s when things break down. The sword changes in ways you didn’t choose. The structure no longer reflects how you think. And one day you pick up the sword and realise you don’t recognise it anymore.

The outcome?

A guy with a shitty sword and a bold squire.
A guy who’s squire will outgrow him.
Congratulations.

If this article made something click, this is the fastest way to make it stick:

1-on-1 Consulting
Obsidian x Claude Code Workshop

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Newsletter

I looked at my daily note and thought, “this is ugly.” About as pleasant to look at as my family WhatsApp group’s AI slop videos that my dad keeps spamming. At least those have colour. My vault was a wall of grey plain text. Every tag, every link, every log entry, identical. So I decided to see if my personal assistant (AKA Claude Code) can prettify it for me.

Obsidian on the left. Claude Code on the right.

I started simple. I wanted all the tags starting with #log to be green. So I asked, “can you turn all the log tags green?” BAM. Hulk has entered the chat. Green baby!

While admiring my genius I noticed the green only showed up in Reading View but not in Live Preview. I told Claude it was a dumb piece of shit. It politely asked me to inspect the element so it could figure out what went wrong. A few back-and-forths later, everything was coloured:

Patient as a saint. Gently held my hand through the whole process while I insulted it.

I didn’t write a single line of code. I don’t know what a CSS selector is. Still don’t. I just looked at my vault, said what I wanted to see, and watched it update in front of me.

Now my tags are green and blue. My project links are red. Work sessions glow green. Log entries have clean little orange dots instead of checkboxes. I open my daily note and I can feel what kind of day it was before I’ve read a word. Like a trader scanning green vs red.

These colours don’t just live on the daily note. The dataview queries that pull logs into project pages keep the formatting too.

And the whole time, the only thing I did was complain. ”Too bright.” Claude toned it down. ”The links all look the same.” Claude coloured them by type. ”Those checkboxes are annoying me.” Claude turned them into dots. Every time I looked at my screen and didn’t like something, I said so. And a split second later, it’s done.

And when I get bored of it in three months, I’ll just tell Claude to change it again.

If you can complain about it, you can build it.

I’ve been using Claude Code not just for colours. It processes my meeting notes, pulls in YouTube sources, runs my weekly reviews, helps me with taxes.

You used to scroll through hundreds of community plugins hoping someone built the thing you wanted. Now you just describe it.

How To Get This For Your Vault?

Open Obsidian on one side. Claude Code on the other. Look at your vault and find something that annoys you. Tell Claude to slave away until your Obsidian looks like an extension of you.

If you want these CSS snippets, I made them available for download, but they’re based on my structure (projects are red, meetings are green, log tags are green, area tags are blue).

My honest advice? Learn how to do this yourself.

I run Claude Code x Obsidian workshops every couple of weeks. We set up Claude Code from scratch, walk through use cases like this one, and by the end you have a toolkit you can take home and use immediately. No dependency on me. Just you and your vault.

If you want more of this, I write a weekly newsletter about building systems in Obsidian, Claude Code, and the weird things I discover along the way.

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Newsletter

At this point I feel like a Pokémon trainer watching Charmander become Charizard.

Every evolution unlocks a new ability.

Obsidian gave me structure.
Claude Code gave me read, write, think.
Wispr Flow gave me hands-free capture.

This evolution? It learned a new move: control the screen.

The problem Up Until Now

Claude Code lives in my terminal.
Obsidian lives in its own app.

I’ve been running them side by side for months, and Claude has learned exactly how my vault works. It reads my notes, creates new ones, logs my day, and processes meetings.

Claude could do everything behind the scenes, but it had no way to control what I was actually seeing on screen. It couldn’t open a note for me. It couldn’t navigate.

Then I Found The Obsidian CLI (Command Line Interface).

“Anything you can do in Obsidian can be done from the command line.”

It’s built directly into Obsidian (not a plugin), bridging your terminal and Obsidian and letting anything running in your terminal, like Claude Code, control what happens on your screen.

You know that scene in Iron Man where Tony talks to Jarvis?

Tony walks in. No keyboard. No mouse.
“Wake up. Daddy’s home.”

“Pull up the schematics.”
“Enhance.”
“Cross-reference last Tuesday.”

Holographic screens flying around. Data surfacing exactly when he asks for it. He never clicks. He never searches. He just speaks, and the system responds.

That’s the vision.
That’s where this is going.

Before the CLI, I had Jarvis locked in the basement.
He could do the research, crunch the numbers, write the report.

He just couldn’t put anything on my screen.

Now Jarvis has access to the holographic screens.

“Jarvis, process this meeting.”
Summary created. Action items extracted. Note opens.

“Jarvis, open the lasagne recipe.”
There it is.

“Jarvis, log gym, 45 min biceps.”
Logged. Note opens.

“Jarvis, find the last two Charmander feet pics.”
Both open. Right in front of me.

No searching. No clicking. No sweating through your folder structure like a drug addict tearing apart the couch cushions looking for the next hit.

I speak. Immediate relief.

More upgrades. More power.

One problem:

You Can’t Multiply By Zero.

If your vault is empty, Jarvis has nothing to pull up on those holographic screens. No notes to open. No meetings to reference. No recipes to find.

All that functionality, and your Jarvis is just standing in the corner staring at his feet. Granted, they are handsome feet.

But if you’ve been building, even casually, your system just learned to talk back.

And it has a lot to say.

How Do You Access It?

Two things to do manually in Obsidian:

1. Update to Obsidian 1.12+ and ensure you have access to the CLI feature (currently Early Access, planned to be free for all users)

2. Go to Settings → Core plugins, toggle on CLI, and click “Register CLI path”

Keep Obsidian running. The CLI talks to it as a server.

Then launch Claude Code in your vault:

claude -p /path/to/your/obsidian/vault

And prompt it:

“Verify the Obsidian CLI is working by running obsidian help. Then add instructions to CLAUDE.md for how to use the Obsidian CLI for all vault interactions: searching, reading, creating, appending to notes, managing properties, daily notes, backlinks, tags, and using --format=json for parseable output. Also check what vault this is connected to with obsidian vault.”

That’s it. Future Claude Code sessions in your vault will automatically use the CLI instead of raw file reads.

A Quick Note on AI and Your Vault

I know I’ve been talking a lot about AI in knowledge management lately. That’s because I genuinely believe this is the next evolution, not a trend.

I hear the privacy concerns. I’m actively working toward running these tools locally (mac mini gang) so your data stays yours.

Even if you’re not ready to evolve your Pikachu yet, at least be aware of what’s possible for when you are.

Your Obsidian’s Next Evolution

If you want to hand your system its next evolution, I run Claude and Obsidian workshops regularly.

In the workshop, we run through different use cases to get the gears turning on how you can use this inside your life and your Obsidian:

• Meeting processing

• Source processing

• Daily logging

• Work sessions

• Content creation

You pick the ones that fit your workflow.

The course that comes with the workshop teaches you exactly how to upload each skill.

Think Neo in The Matrix:

“I know kung fu.”

Except it’s:

“I know meeting processing.”
“I know project management.”
“I know daily note logging”
Upload. Done.

Each skill is a new ability your vault didn’t have five minutes ago. You simply choose which ones you want to learn.

If you’d rather skip the learning curve and have it all working by the end of the day, book a one-on-one consulting session and we’ll set everything up in one go.

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Newsletter

It’s Valentine’s Day.

Most people’s effort ended with Googling “romantic restaurants near me.” Panic booking something with a suspiciously enthusiastic review from someone named Gary.

Gary once left a five-star review for a petrol station.
“Really enjoyed the atmosphere.”

You outsourced intimacy to Gary.

Allow me to shame you.

Shame.

Romance isn’t hard, kids.

Three months ago she mentioned her grandmother’s recipe while on the phone with a friend as you walked past. She called it “the best thing I’ve ever tasted.” One sentence. In passing. Immediately into the void. Forgotten by everyone else thirty seconds later.

Except you.

Because you, my dearest, you have the void by the nuts.

You have Obsidian. You don’t rely on memory. You rely on capture.

So when Valentine’s Day arrives, it resurfaces. You call her parents. You get the recipe. You make it.

She stares at you like a baby trying ice cream for the first time. Confused. Emotional. Slightly destabilised.

This is not romance.
It is attention.
And attention is attractive.

Most people confuse effort with attention. They are not the same thing.

Naming your firstborn after me is optional, but encouraged.

That pattern, capture once, forget completely, resurface on command, is where a system stops being storage and starts becoming a thinking partner.

Until January 2026, retrieval was the weak link. We built structure. Daily notes. Project systems. Tag taxonomies that made us feel organised and morally superior. It helped. But you still had to remember what tag you used. What you called it. Where past you decided to bury it.

It worked. Technically.

But not. easy. enough.
Friction kills systems.

So what killed my friction?

Claude Code.

You now have an AI chatbot pointed at your Obsidian folder. Something you can instruct in plain English. Not a search bar. Not a filter. A butler who has read every note you have ever written and still shows up for work.

Instead of remembering tags or digging through your own clever structure, you tell Claude to sift through everything and bring it to you. Handkerchief on your lap. Silver tray. Exactly what you ordered.

And it does not get tired. Or annoyed. Or forget.

Instead of trying to remember where you stored something, you type:

“It’s Anna the chemist’s birthday soon. Give me gift ideas based on all the logs and information I have on her.”

And it combs through everything. Passing mentions. Old ideas. Patterns. Context. It brings you high confidence hits. Experience gifts. Creative callbacks you forgot existed.

The image above is not creativity.

It is compounded attention.

She is getting a horse piñata filled with her favourite treats. Not because it is random. Because I want to see the self-proclaimed horse girl’s moral hesitation before the first swing.

Character is revealed under pressure.

I did not sit for three hours brainstorming like a Pinterest mother. I captured things over time and built a system that squeezes the vault for me.

Here is the uncomfortable part.

You actually have to use the system. If you did not capture anything about her, this does not magically save you. You cannot retrieve what is not there.

This system compounds effort. It does not create it.

But when you do capture, casually and consistently, your life becomes queryable.

And this is not just useful for saving your relationship.

Your meeting prep is reactive because you rely on memory.
Your study prep is chaotic because you rely on willpower.
Your travel planning is 17 tabs peppered with hope.
Your writing process mostly consists of staring at a blinking cursor.

You keep trying to think harder in the moment instead of remembering better over time.

Obsidian holds the raw material of your life.
Claude lets you interrogate it in plain English.
Together, they give you leverage.

Systems create asymmetry. Memory does not.

You can build a system that makes you look unfairly prepared in life.

Or you can keep outsourcing your life to Gary.

What steps do I take next?

If you want to set this up properly instead of half-installing it and hoping for the best, there are three ways to work with me:

1. Hands-on Workshop
Small groups. We install and configure everything on your device and work through real use cases immediately.

2. 1-on-1 Consulting
For people who want a custom setup tailored to their vault, workflow, and business.

3. Obsidian Demo Vaults
If you prefer to reverse-engineer systems at your own pace, my demo vaults show the exact structure I use.

If this article made something click, pick your level and start there.

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Newsletter

I’ve been running hands-on Claude + Obsidian workshops. Seeing what actually works, and where people get stuck, shaped the last 30 days.

A Warm Coffin

Most knowledge systems don’t fail because they’re bad.
They fail because they’re comfortable.

They work just well enough that you never feel an urgent need to change them, even as they slowly stop helping you learn, think, or adapt. There’s no dramatic breaking point. Just gradual stagnation.

That’s what I mean by a warm coffin.
Something comfortable enough to stay in while it quietly restricts you.

That’s also why people defend bad systems so aggressively. Not because they’re good, but because they’re familiar.

Knowledge management evolved roughly like this:

oral stories → writing → computers → folders → search → databases → networks

Each step was a genuine leap forward. Each one also reframed the previous approach as a polite historical artefact.

Computers gave us scale.
Folders gave us containment.
Search gave us hope.
Databases gave us structure.
Networks give us relationships.

Obsidian lives in that last shift.

People still stuck at the folder, search, or database stage are essentially cave painting, just with better fonts and recurring billing. Obsidian already escapes that trap by treating knowledge as a network instead of a filing system.

But that’s a low bar.

Compared to how people will be using Obsidian once AI is properly integrated, you might already be falling behind. You might feel technically savvy compared to your parents. Compared to people actively using AI to learn better, you’re still operating inside familiar limits.

What’s different now isn’t the tools themselves. It’s the rate at which they evolve.

We’ve seen transformative tools before. But they spread slowly enough that falling behind was temporary.
Today, the pace of change is accelerating.
When change compounds, falling behind gets harder to recover from.

The silver lining is that these are also the most powerful tools we’ve ever had for learning faster.

The irony is that the faster you learn these tools, the faster you can learn everything else. The advantage compounds.

That’s why the most important skill over the next five years isn’t a specific technology. It’s learning how to learn, and these tools finally make that practical instead of aspirational.

And uncomfortably, the only real defence against AI isn’t avoiding it.
It’s wielding it properly.

I wrote about my first 48 hours with Claude Code. Then my first 14 days. Now it’s been a month.

I wish I could say the novelty is gone and the honeymoon phase is over. But I’m still the guy cornering strangers at dinner parties to explain how fucking sick my Claude + Obsidian system is.

What stuck

Daily logging without the admin hell

Everyone loves talking about “building a second brain.” Nobody loves manually creating notes, linking people, tagging projects, formatting timestamps, and choosing the correct emoji.

That’s not thinking.
That’s data entry.
And I refuse to do data entry in 2026.

Claude does it now

I say, “logged meeting with Dan at 9:30,” and Claude handles the timestamp, tags, emojis, and links. Even when the actual filename is “Dan Blonde stocky pierced nipples marathon gym sauna guy.” It matches by first name and carries on with the level of professionalism and lack of eyebrow-raising I would expect from a loyal personal assistant.

Unlike some of you.

What used to take minutes now takes seconds. Capture stopped being optional. My vault went from patchy to embarrassingly detailed. My future biographer is going to need a lot of hugs.

The most valuable thing Claude does isn’t clever.
It’s clerical.

What evolved

From capturing to producing

This surprised me.

At first, Claude was purely for input. Logging. Formatting. Organising. Then that became normal. With speech-to-text dictation (thanks, Wispr Flow) feeding straight into my Claude personal assistant, capturing felt effortless.

Then it clicked.

When I sit down to work now, I don’t start with a blank page. I start a work session and ask Claude to surface everything I’ve already thought about the topic. Relevant notes. Previous work sessions. Old arguments. Half-formed ideas I forgot I had. All of it appears directly in the note I’m working on.

Instead of asking Claude to generate ideas, I ask it to resurface mine. This article came together that way. Nothing here was invented. The raw material already existed.

Writing feels easier because the hardest part was never writing. It was locating your own thinking. Now I start from my past work, decide what matters, and assemble the argument.

I’m not starting from other people’s information.
I’m starting from mine.

The same applies to sources

Instead of letting articles, videos, and threads pile up and radiate low-grade guilt, I process them as they come in. Key points are extracted, tagged, and stored.

“I’ll read this later” is a lie.
“This is already processed” actually ships work.

The thinking is mine. The organisation is automated. When I sit down to produce something, I start from my material, not a blank page and not something generated for me.

I’m building on my own knowledge, not outsourcing my brain.

Speed via a vault graph

I asked Claude to generate a simple JSON graph of my vault to speed up note lookups. It’s essentially an index. Instead of searching through files every time, Claude checks the graph first.

This came from a comment on the previous article, and it turned out to be a clear improvement over the default “go search the vault” approach. Faster lookups. Fewer broken trains of thought.

Security concerns didn’t magically disappear

One thing that hasn’t faded with time is my discomfort around security.

Using AI like this means sending personal context to a large corporation. Not abstract data. Your notes. Your work. Your thinking. That’s a real concern, and it should be treated as one.

Most setups today involve some level of external processing. That’s the tradeoff. There are people running fully local or hybrid systems where sensitive data never leaves their machine. I haven’t settled on my own version of that yet, but I’m actively looking into it.

For now, it’s a conscious tradeoff. You’re trading some privacy risk for very real upside in leverage, speed, and learning. That doesn’t make it reckless. It does mean you should understand what you’re opting into.

The point isn’t to ignore the risk.
It’s to be aware of it and decide whether the reward-to-risk ratio makes sense for you.

For me, so far, it has.

What I dropped

One massive CLAUDE.md file

Long instruction files fail for the same reason terms and conditions exist: they’re technically correct and functionally ignored.

Claude behaves exactly like a human here, just with a slightly better memory. The longer the instruction file, the more slips through the cracks. Past a certain length, you’re not giving guidance. You’re just yelling into the void.

The fix was to compartmentalise.

Specific Claude Skills for specific actions. Small, focused instruction files loaded only when needed. Claude follows these. The monolith never stood a chance.

The four I use constantly:

Daily Logging
Handles timestamps, tags, emojis, and links. Used constantly. Losing this would hurt emotionally.

Process Meeting
Turns raw transcripts into summaries, action items, and follow-up emails. An 80-minute call becomes something usable in minutes.

Process Source
Extracts summaries and key points from articles, videos, and threads. My source folder went from graveyard to tool.

Claude feels like a very fast intern who never complains and never questions why I saved a hobby horsing video tagged #bachelor-party-idea.

Week Review
Reads all seven daily notes, summarises the week across life areas, and selects three photos prioritising people, experiences, and milestones. What I used to skip now takes 90 seconds and actually happens.

What 30 days taught me

The compound effect is real.

When logging takes no effort, you log everything. When reviews are automatic, you actually review. When sources are pre-digested, you use them. When connections take seconds, your vault stops being a graveyard and starts being useful.

The biggest shift wasn’t any single feature. It was the collapse of the gap between thinking something and having it captured, connected, and retrievable. My vault went from storage to a thinking aid. That’s what everyone promises. Almost nobody delivers.

I’ve used Obsidian for three years. Capturing was never the problem. Producing was. Having your own processed material changes that completely.

If you want to learn this setup properly

I’m running small, hands-on workshops for people who haven’t touched Claude Code yet, or who want to move past “I installed it” into actually using it.

We set everything up on your device, and immediately work through real use cases:

• Daily log automation

• Project and meeting creation

• Pulling web content straight into your Obsidian templates

If this article made something click, this is the fastest way to make it stick.

Sign up here

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Newsletter

The Setup (Minutes, Not Hours)

I wasted hours searching for “Claude Code + Obsidian” tutorials. Found nothing. Everyone’s using it for programming, not note-taking.

So I stopped searching and just installed it. Pointed it at my vault. Started talking to it.

It worked immediately. Setup was the only hard part, and even that took minutes.
(A short setup video will be live on YouTube sometime next week).

The Magic Glue: CLAUDE.md

Claude is brilliant, but forgetful. Every conversation starts fresh.

The fix is a file called CLAUDE.md. It’s not documentation. It’s an instruction manual for your personal assistant.

When Claude makes a mistake, you teach it. Add a rule. It doesn’t make that mistake again. Claude can even update the file itself.

My CLAUDE.md started with three lines. It’s now 370+ lines covering:

• Where my daily notes live

• My exact logging format with emojis and tags

• How to create projects, work sessions, meetings, etc

• How projects link to work sessions

• Patterns for gym visits, social interactions, content creation

Every correction became a new rule. Every repeated explanation became documentation.

(You might hear about “Skills”, separate instruction files for specific tasks. For Obsidian workflows, CLAUDE.md alone works fine at the beginning. Start simple.)

Teaching Your 80/20

Most of what I ask Claude to do doesn’t change much from day to day.

Log something. Capture a meeting. Create a project. Update today’s note.

Instead of teaching Claude everything, I taught it those few actions first.

The teaching loop is simple. I ask for what I want. If it’s wrong, I correct it once. The correction becomes a rule in CLAUDE.md. The mistake doesn’t happen again.

After a few days, the interaction stopped feeling like “using AI” and started feeling like talking to my system.

Now I’ll say something like:

“Had a catch-up with Stefan about the Q1 roadmap”

Claude knows where meetings live. It creates the note, links Stefan, adds today’s date, fills the metadata, and connects it to the right project.

I don’t think about structure. I don’t think about format. I just describe what happened.

That’s the 80/20. Teach the handful of actions you repeat every day, and let the system handle the rest.

Some other findings…

Once the basics were set up, I discovered what Claude is also useful for.

Metadata at scale.
You can update a lot of notes at once. I no longer write summaries. Claude reads each note, summarizes it, and fills the field. I batch this at week’s end: “Check all meetings and fill missing summaries and tags.” Housekeeping in seconds.

Tip: having a base file where you can see all your meetings at a glance makes this oddly satisfying. You can watch Claude fill it in.

Search replacement.
I ask Claude instead of Googling. It knows my vault. It’s a personalized search engine.

I can ask it to find a super simple salmon recipe online, create the note using my recipe template, and add a cooking log to today’s note.

It beats the back-and-forth of copying, pasting, refining, choosing templates, and linking everything manually.

Embedded in Obsidian.
I run Claude inside Obsidian using the Terminals plugin. It lives in the sidebar. No extra window. Oddly cozy.

The Real Shift

The real gain isn’t speed. It’s friction removal.

When logging takes three seconds instead of two minutes, you actually do it. More notes. More connections. More ideas captured.

Parkinson’s Law says work expands to fill the time available. The reverse is true too — remove the busywork and time appears.

It feels good to hand off a task, let Claude run for a couple of minutes, and go grab a coffee.

Fourteen days in, I can’t imagine going back.

The Elephant in the Room: Privacy

Before you point an AI at your personal notes, know what you’re signing up for.

Your data leaves your machine. Claude Code feels local, but files go to Anthropic’s servers. Your notes travel over the internet.

Claude explores. It reads files you didn’t explicitly mention to understand context. It might stumble into your journal, your client notes, your half-written thoughts.

Things to consider before you do this:

• Passwords, API keys, credentials

• Client or patient confidentiality

• Personal information

• Compliance (GDPR, HIPAA)

What I do:

• Keep sensitive files outside my vault

• Use .claudeignore to exclude folders

• Review changes before confirming

• Keep regular backups

Is it worth it? For me, for now, yes.

The worst that could happen is Anthropic gifting me a few free therapy sessions after reading my journal.

But here’s the irony. The reason I love Obsidian is that your data is yours. Plain markdown on your machine. No cloud unless you want it. No company reading your notes.

AI tools strip that away. The data lives on corporate servers. It might leak. It might train models. It might be used against you.

So be cautious. Know what you’re sharing. Decide if the benefits outweigh the risks for your situation.

I’m digging into offline Claude Code options. When I find these sandboxed solutions, you’ll be the first to know how to set it up.

Want to Learn?

I’m running small, hands-on workshops for people who haven’t touched Claude Code yet.

We’ll set it up on your device and immediately run:

• Daily log automation

• Project and meeting creation

• Web scraping into your templates

Just setup and real use cases, right away.

Sign up here

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Newsletter

That number means nothing on its own.
Here’s why it matters to me.

Why 0.94 Matters to Me

I rate my days on a scale from -2 to 2.

I don’t remember where I picked this up, but it stuck because it solved a recurring problem for me.

The Problem With Most Rating Scales

Most rating systems quietly lie to you.

On a 0–10 scale, an average day almost never becomes a 5. It becomes a 6 or a 7. Five feels like failure. Seven feels polite. Over time, everything drifts upward.

A 1–5 scale isn’t much better.
1 feels bad.
5 feels great.
But 3 also feels good, even though it’s meant to be the middle.

What Each Number Actually Means

• -2: awful day

• -1: bad day

• 0: neutral. Nothing good, nothing bad

• 1: good day

• 2: a genuinely great day. The kind you feel in your body

A 2 is rare. It is reserved for days that feel almost euphoric.
Not perfect. Just deeply right.

Half Points and Friction Days

Sometimes I use 0.5 steps.

Some days are clearly positive, but with friction.
Others are good overall, even though a few things went wrong.

The scale allows for texture without adding complexity.

This Is About Felt Experience, Not Performance

The rating is based on felt experience.

Not productivity.
Not outcomes.
Not how impressive the day looks in hindsight.

Just how it actually felt to live inside it.

Calibration Happens Over Time

Yes, at first it feels arbitrary.

But over time, that arbitrariness disappears.

You calibrate against yourself.

Your -1 becomes consistent.
Your 1 becomes meaningful.
Your 2 earns its place.

The scale stops being theoretical and becomes personal.

How I Got a Yearly Number at All

So how do I know my rating for 2025 was 0.94?

Because I rated every single day.

When you average those out (thank you, Base), you do not just get a story.
You get a signal.

What 0.94 Actually Tells Me About 2025

And 0.94 tells me something concrete.

On balance, it was a good year.
Not easy.
But clearly on the right side of neutral.

Which, honestly, is more information than
“pretty good, I guess”
ever gave me.

If You’re Curious

If you are interested in doing something similar,
I offer a fully built-out Obsidian journaling system for daily to yearly note-taking.
There is also a short YouTube walkthrough if you want to see it in practice.

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Newsletter

I’ve worked in the corporate world for a long time.
Which means meetings.
A lot of f*cking meetings.

Every now and then, something valuable is actually said.

When information starts flying around, one of three things needs to be true:

• You have an excellent memory

• You’re not lazy

• You have a system that remembers things for you

I don’t have an excellent memory.
And I’m extremely lazy.

So I went with option three.

The system handles the mundane and allows knowledge to compound naturally over time. You stop relearning and you stop forgetting. Anything discussed years ago remains instantly retrievable.

This only works because the structure is consistent. The project templates below are what enforce that consistency. They remove decision-making, capture the boring details automatically, and keep projects legible long after they are finished.

I’ve also packaged this into a fully built Work Setup for anyone who prefers to start with everything already in place.

How This Works in Obsidian

The system relies on three components working together.

Bases

I use a single project.base with relative views reused across projects and contexts. Instead of rebuilding tables per project, the same base adapts based on where it is referenced.

This means every project looks familiar, even years later.

This keeps structure consistent while allowing each project to surface only what is relevant.

The base only handles notes:
projects, meetings, work sessions, people, and general notes.
It does not manage tasks or logs.

For a deeper breakdown of the base and the thinking behind it, see The Last Project Setup You’ll Ever Build, or download the base file here.

Dataview

Dataview manages tasks and logs as individual lines of information. It handles timelines, progress, and actions without turning notes into dashboards or bloating project pages.

Templater

Templater activates and executes templates at the moment a note is created. It pre-fills metadata, enforces structure, and removes decision-making during capture.

In short:

• Bases define reusable views for notes

• Dataview manages tasks and logs

• Templater ensures consistent capture

The project.base works seamlessly with the templates below.

Templates I Use

Each template has a single responsibility.

• Project Template

• Meeting Template

• Work Session Template

• People Template

• New Note Template

Nothing too complex.

Project Template

This template is used for all projects, including sub-projects.

A project becomes a sub-project when it has an up property pointing to its parent. The project.base automatically detects this relationship and displays it accordingly.

There is no hierarchy to maintain. No folders to reorganise. No restructuring when things grow.

If it’s a project, it uses this template.

Here’s what it looks like using a Project — Italian Cooking example:

Now that we’ve seen what a project looks like, let’s look at the templates that populate it.

Meeting Template

The meeting template is used for meetings with people: stakeholders, clients, or colleagues.

Each meeting:

• Links to a project using the up property

• Captures outcomes, decisions, and follow-ups

• Lists attendees in the participants metadata field

• Appears automatically inside the relevant project view

• Appears automatically on each participant’s person page

Anyone added to participants gets the meeting linked to them automatically. Project context and relationship context stay in sync without duplicating notes.

Anything that happens in a meeting and matters later gets captured here.

If it doesn’t make it into this note, it may as well not have happened.

Work Session Template

Work sessions represent focused effort done alone to move a project forward.

Examples:

• Preparing for a stakeholder meeting

• Reviewing documents

• Writing or planning

Separating work sessions from meetings makes it obvious where progress actually comes from.

People Template

Each person I interact with gets their own note.

This template tracks:

• Who someone is

• Which projects they are involved in

• Which meetings reference them

Because meetings store attendees in the participants field, a person’s page becomes a running history of real interactions tied directly to real work.

New Note Template

Notes are information created from work sessions or meetings.

They are the byproduct of thinking, discussing, deciding, and learning. Over time, these notes compound into personal knowledge you can actually reuse.

Thoughts, insights, references, or conclusions that emerge during a meeting or work session are captured as notes. If they connect to a project, a person, or another idea, they get linked. If not, they remain available for future reuse.

Below is the Knife Skills note. It was created in this project, but it doesn’t belong to it. The project is just where it was born.

Once captured, it’s reusable knowledge you never have to recreate.

This is how projects create knowledge instead of just closing tasks.

Why This Works

I don’t rely on discipline or memory.

I capture information once, in the right place, and let the system handle recall and visibility.

The result is a project view that shows:

• What exists

• What has happened

• What still needs attention

Without having to remember any of it.

Lazy people, unite.

Don’t Want to Build This Yourself?

Don’t feel like building this from scratch? There’s a fully built Work Setup ready to go. If you want to move even faster, book a consulting call and we’ll build it together. Many people use their training budget for this.

This is best suited for people doing knowledge work who live in meetings, documents, and long-running projects.

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Newsletter

—-

First try. Perfect.

That’s when I accepted that the near-future me would be tired, but informed.

→ Watch the full video walkthrough on YouTube

So What Is This Thing?

Claude Code is an assistant that has access to your Obsidian vault. The actual folder behind it.

It can read your notes, update them, create new ones, and remove old ones. Ask it to create a project using your template and it does. Ask it to log a meeting with the correct metadata and it’s done.

You give the command. It executes.

Sounds like fun? It is. I checked.

The Problem

A good knowledge management system needs two things: easy capture and easy retrieval.

Obsidian gives infinite flexibility to impose your own structure: daily notes, projects, people, logs. Structure, as we know, must be earned. That turns out to matter more than it sounds.

But retrieval only works if capture is disciplined.

Correct tags.
Correct parent links.
Correct naming conventions.
The right template.
The correct “up” link.
A clear summary.

Miss one field and your system starts to show signs of weakness.
Skip it because you’re tired and good luck finding it later, Future You.

Multiply that by dozens of notes per day.

That friction adds up.

The Magic: It Just Knows

I have two contacts named Lucas.

One is “Lucas engineer dutch guy.”
The other is “Lucas Burger.”

I told Claude to add a gift idea for Lucas dutch to my daily note.

It picked the right one.

Same with projects, meetings, recipes.

The hit rate is high enough to raise questions about how irreplaceable we actually are.

The Secret: It Learns

This is where it gets interesting.

You create a markdown file. Mine is called CLAUDE Instructions. Claude uses it as a living guide.

Every time it learns how you want something done, it updates that file.

Discipline it once. Never again.

New workflow? A minute of back and forth. Then perfect execution going forward.

An assistant that gets smarter about your vault every day.

Could this be my perfect match?
“Claude, lock my doors, dim the lights, put on something romantical.”

What I Actually Use It For

Daily logging

“At 10am I went to the gym, trained biceps, had a sauna, and chatted with Oscar about South Africa.”

Done. Logged. Linked. Timestamped. Tagged.

Project management

“Create a work session for the newsletter project, tag it claude-code, add last week’s newsletter to related.”

Note created. Metadata filled. Daily note updated.

Web scraping

I want to cook lemon zest pasta. Claude finds a recipe online, pulls it in, reformats it into my template, and fills the sections.

Chef’s kiss.

What’s Next

My goal is a fully voice-operated knowledge management system. No typing unless I want to.

The accuracy is already there. With the instruction file, any mistakes are on me. I’m the bad teacher.

I also want this running locally. No data living in the hands of greedy corporate giants. But that’s chapter two.

Why This Matters

Claude Code isn’t just another AI tool.

A year and a half ago, plenty of people were still not using ChatGPT. Now even your technically challenged mom is. Not because it’s exciting, but because it became unavoidable.

Claude Code feels like the next step of that curve.

For Obsidian users, this is a very practical skill. Your thinking already lives in your vault. Claude Code works inside it, cutting the distance between thinking and output.

The longer I use this, the more convinced I am that this will become a crucial skill.

If other people have a personal assistant that understands their vault and you don’t, it won’t matter how hard you work. You’ll be slower.

I’m curious, sure. But I’m also lazy. I don’t want to work harder if there’s a tool that makes this easier.

Want to Learn?

I’m running small, hands-on workshops for people who haven’t touched Claude Code yet.

We’ll set it up on your device and immediately run:

• Daily log automation

• Project and meeting creation

• Web scraping into your templates

Just setup and real use cases, right away.

Sign up here

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Newsletter

A project has many moving parts.
When even one of them lacks a clear system for capturing and retrieving information, overwhelm creeps in fast.

Information spreads across notes, meetings, and tasks, until the project is no longer visible as a whole.

This applies equally to work projects and personal ones.
Delivering a report. Running a campaign. Buying a house. Planning your next trip.

Despite their differences, most projects share the same underlying structure.

They consist of:

• sub-projects

• work sessions and meetings

• child notes

• related notes

• tasks and questions

• logs

You can download the Project.base file used here for free. It’s one part of a larger, fully configured project system.

Buying a house as an example

Let’s use a concrete example:
[[project - buying a house in amsterdam 2025]]

This example is deliberately mundane. That’s the point.

Sub-projects

Sub-projects are parts of a project that are complex enough to track independently.

• [[project - property search & viewings]]

• [[project - financing & mortgage]]

Each sub-project groups its own work sessions, notes, tasks, questions, and logs while still rolling up to the main project.

Work sessions / meetings

Work sessions and meetings are the primary thinking spaces of a project.
This is where work happens, information is gathered, and important notes are created.

• [[2025-11-03 work session - listings review]]

• [[2025-11-05 viewing - churchstreet 69-3]]

That brings us to child notes.

Child notes

A child note belongs to one specific project.

It exists because this project exists.
If you removed the project, the note would have no obvious place to live.

For that reason, child notes link up to the project as their parent.

Child notes answer:

• What happened in this project?

• What did we decide for this project?

• What information do we need to continue this project?

Child notes include anything the project needs to function, such as:

• work sessions and meetings

• documents produced for the project

• reference material specific to the project

• links, credentials, access details, or accounts used only for this project

This is where execution and context live.

Examples

• [[2025-11-03 work session - listings review]]

• [[2025-11-05 viewing - churchstreet 69-3]]

• [[note - shortlist apartments]]

• [[link - apartment website listings saved]]

• [[doc - purchase agreement]]

All child notes point up to the project.

Related notes

A related note is a note that may help the project, but does not belong to it.

It provides context, reference, or supporting information, without being owned by the project itself.

A related note:

• can exist before the project starts

• can be created during the project

• remains useful even if the project ends

Related notes answer:

• What information might help this project?

• What context should be visible while working on it?

• What references does this project depend on?

This is where supporting knowledge lives.

Examples

• [[note - property search websites]]

• [[note - buying vs renting tradeoffs]]

• [[note - what matters more than square meters]]

• [[note - questions to ask at any property viewing]]

These notes remain useful even if the project ends, the location changes, or the purchase never happens.

Child vs related

• Child notes are owned by the project

• Related notes support the project without belonging to it

This keeps projects focused and prevents them from turning into knowledge dumps.

Practical rule when unsure:

If the project were deleted tomorrow, would this note still make sense on its own?

• No → Child note

• Yes → Related note

All that remains is a way to surface the right notes, in the right place, at the right time.
That’s exactly what Bases are for.

Project.base

We use Obsidian Bases to retrieve notes.

Think of your vault as one large list of notes:

• some are projects

• some are meetings

• some are work sessions

• some are general notes

A Base lets you filter that list into smaller, meaningful views.

That’s it.

How a Base works (in practice)

We create a Base that contains all notes.
Then we create views that filter this list based on simple rules.

For example:

• a Projects view shows notes where type = project

• a Meetings view shows notes where type = meeting

• a Work sessions view shows notes where type = work-session

This already covers most use cases.

To make it dynamic per project, we add one more rule:

• Only show notes where up = this.file.name

That single condition makes the Base context-aware.

It means:

• the same Base view can be reused everywhere

• each project only sees notes that belong to it

This is what makes the system scale without becoming heavier.

Creating the Project.base

Create a new Base and name it Project.

Inside this Base, create four views:

Sub-projects

• type = project

• up = this.file.name

Work sessions / meetings

• type = work-session OR type = meeting

• up = this.file.name

Child notes:

• up = this.file.name

Related notes:

• related = this.file.name

Each view filters the same underlying note list in a different way.

Pulling the Base into a project

In your Project template, you reference the relevant Base view under each section:

• Sub-projects

• Work sessions / meetings

• Child notes

• Related notes

Every new project uses the same Base.

You build the structure once.
Every project benefits from it.

You’ve now built a project surface that grows without becoming heavier.

Projects don’t just consist of notes.
That’s where tasks, questions, and logs come in.

Tasks, questions & logs (Dataview)

Write tasks, questions, and logs where they occur.
Link them to a project.
The project page pulls them in automatically.

Tasks & questions

Use tasks for anything unresolved that belongs to a project.

Rules:

• - [ ] → makes it detectable by Dataview

• #task / #question → to specify what it is

• [[project - …]] → destination

- [ ] #task sign the contract before 2025-12-31 [[project - buying a house in amsterdam 2025]]
- [ ] #question is the churchstreet house out of budget? [[project - property search & viewings]]

Project page query

TASK
WHERE icontains(text, this.file.name)
AND (icontains(text,”#task”) OR icontains(text,”#question”))
AND !completed
GROUP BY file.name as filename
SORT filename DESC

Logs

Logs record effort, not outcomes.
They are written on daily notes and linked to a project.

Rules:

• - [ ] → makes it detectable by Dataview

• [[project - …]] → destination

- [ ] working on [[project - property search & viewings]]
  - [[2025-11-03 work session - listings review]]

Project page query

TASK
WHERE icontains(text, this.file.name)
GROUP BY file.name as filename
SORT filename DESC

Logs are optional, but they make progress visible over time.

Remember

• Tasks & questions → what’s still open

• Logs → what already happened

• Projects collect both

In Closing

You’ve seen the system.

One structure that fits how projects actually work and removes friction by design.

Most people don’t struggle with the ideas.
They struggle with setting it up cleanly and making it fit their real projects.

You can buy the complete system, fully built.
Or we can build it together in three focused sessions.

We sit together and build your projects inside this system, step by step, until it’s fully adapted to how you think and work.

Either way, the outcome is the same:

Less time managing projects.
More time finishing them.

Much love,
Dee
Construct by Dee

Website | YouTube | X / Twitter | Newsletter

It’s a few days into the new year.
I’m sitting by a pool in Sri Lanka with a couple of friends.
No plans. No schedule.

Someone says, “We should do a yearly review.”

Everyone opened their laptops and got started.

Photos were opened.
Calendars were scrolled.
Old messages, trips, and half-forgotten moments resurfaced.

For a brief moment, the energy is high.

Then, about ten minutes in, it slows.

Postponed.
Interrupted.
Abandoned.

What stuck with me wasn’t that people gave up.
It was how predictable it felt.

Everyone likes the idea of a year-end review.
Very few actually finish one.

And the reason isn’t what most people think.

I’ll share the prompts and system I use later in this article.

The real reason year reviews fail

Reconstructing a year from memory is brutal.

A proper year review asks you to do three hard things at once:

• Remember an entire year

• Make sense of it all at once

• Decide what actually mattered

That’s a heavy cognitive load.

So people postpone it.
And then they abandon it.

If you didn’t journal, you’re not stuck

You can still do a meaningful year review.

Open your photo gallery.
Open your calendar.
Scroll week by week.

Trips will stand out.
Major events will surface.

This works.

But it comes with friction.

You’re reconstructing instead of reviewing.

It’s like trying to understand what happened by interviewing witnesses,
instead of watching the security footage.

Reconstruction is slow, fuzzy, and mentally expensive.

What actually makes year reviews easy

The easiest year reviews are not done at the end of the year.

They’re assembled quietly throughout it.

The closest thing to an honest year review is small snapshots captured in real time, before you forget why things mattered.

My journaling rule (and why it works)

I’ve journaled consistently for three years for one reason:

I removed effort.

Every day I make sure these three things are filled:

• Three photos

• One short summary

• A day rating

Nothing else is needed.

This is the bare minimum that delivers the highest return.
The 80/20 of journaling, in practice.

No essays.
No pressure to be profound.

At the end of each week, I don’t reread everything.

My weekly note automatically pulls in:

• All daily summaries

• All photos

• The day ratings

I scroll through a single table, pick the three images that best capture the week, write a short summary, and move on.

That’s it.

The work is small, contained, and finished while the week is still fresh.

And I don’t just get one review at the end of the year.
I get fifty-two chances to check whether my ship is still heading in the right direction.

What this changes at the end of the year

When the year ends, I don’t struggle to remember it.

I review it.

I create a note called “2025 — Year in Review”, and it automatically pulls in all my weekly notes.

Fifty-two rows.
Each with images, summaries, and ratings.

Instead of trying to remember an entire year, make sense of it all at once, and decide what mattered after the fact, the work is already done.

I scroll.
Patterns emerge.
The story is obvious.

My yearly review takes about an hour,
because fifty-two past versions of myself already carried the weight.

Why next year’s review can be completely different

Here’s the part most people miss:

Your first proper year review is always the hardest.

Every one after that gets:

• Faster

• Clearer

• More rewarding

It will feel as addictive as scrolling through social media.

For once, a healthy doom-scroll.

The prompts I use (free)

I answer prompts only after reviewing the year week by week.

The order matters.

The prompts don’t help you remember the year.
They help you make sense of it.

Download the exact Year Review & Year Start prompts I use. Free.

A contract you sign with yourself.

Want the system that makes this effortless?

Physical notebooks get lost.
Word files get buried.
Notion turns into clutter.

Obsidian is the only reason I stayed consistent.
It connects your notes and makes reviewing effortless.

I built a complete journaling setup for Obsidian:

• Daily note template

• Automatic weekly, monthly, and yearly roll-ups

• Zero maintenance

You open it.
You fill it in.
The system does the work of connecting everything for you.

👉 Get the Obsidian Journal Setup here

Don’t wait for January

Today disappears regardless.

Future-you either gets clarity
or gaps.

Start today.

Products and Services

🔗 Weekly Email Newsletter

🔗 Obsidian Consulting

🔗 Obsidian Setups

🔗 Obsidian Courses

🔗 YouTube Channel

🔗 Website

🔗 Twitter

I’m damn proud of how it turned out.

The Obsidian Study Setup

A Better Way to Think About Your Study System

Most people upgrade their study space the wrong way.

They start at a tiny desk. When it fills up, they upgrade to the kitchen table. For a week it feels spacious, then the papers, binders, and loose notes spread until the table looks exactly like the desk did.

People upgrade because they hope space will create clarity, but space without structure just multiplies the mess and spreads the shit.

It’s the same cycle as creating another folder or switching to a new app: the mess just expands to a bigger surface.

Obsidian is the upgrade from the kitchen table to a whole house for studying — and this house comes with a friendly ghost whose only job is to keep everything perfectly organized.

Each course becomes its own room.
Each module gets its own corner or shelf.
Everything has a clear place, and nothing gets lost in the chaos.

But the real upgrade isn’t the size of the house.
It’s how you move inside it.

In a normal study setup, if your notes lived in separate rooms, you’d have to walk around to find things. Module notes in one binder, formulas in another, examples somewhere else.

In Obsidian, you don’t walk.
You teleport…

Every note becomes a portal.

• Click a concept and you jump to the lecture where you learned it

• Click a formula and you jump to the examples where you used it

• Click the module summary and you jump to all the knowledge notes that feed into it

You can stand in the “Statistics” room and open a portal straight into “Algebra” to see how the ideas connect, without leaving your spot.

It’s a mansion where any wall can open to exactly the idea you need, exactly when you need it.

How the Study Vault Works

(Capture → Structure → Retrieve)

The core loop of the Study Vault is simple:

1. Log your study session on the Daily Note

2. Create a Study Event inside the correct Module

3. Generate Knowledge Notes as you learn

4. Let the tags and structure place everything into the right Knowledge Base

5. Retrieve anything later in perfect context

This loop is the 80/20 of high-quality studying.

Flow 1: Daily Note → Study Event → Knowledge Notes → Knowledge Base

Let’s walk through it.

Step 1: Log on the Daily Note

You begin by writing down what you plan to work on today.

Your goal is to create a history of all the times you studied Math 101, Algebra, or any module inside them.

Your course homepage might look like this:

The “Logs” section gathers every moment you worked on the course.
These breadcrumbs come directly from your Daily Notes.

This is a simple entry, for example:

That’s enough for the system to track the chronology of your effort.

Step 2: Create a Study Event from the Module

To keep your structure clean, always create a Study Event directly from the Module note.

Why this matters

When you click “Create New Study Event” (1):

• The Study Event is automatically linked to the correct Module and Course (2)

• The Study Event appears instantly inside the Module’s Study Events table (3)

• You avoid manual metadata mistakes that break retrieval later

Inside the Study Event, you take your actual lecture notes and document what you’re learning.

As you go, you may create new Knowledge Notes (4) for concepts, formulas, or questions.

Step 3: Knowledge Notes Flow Into the Knowledge Base

Every Knowledge Note uses simple, consistent tags like:

#on/math/math-101  
#on/algebra

These tags tell Obsidian exactly which Course, Module, and topic the note belongs to.

Because your Module has its own Knowledge Base note, all Knowledge Notes automatically collect there. In the diagram, you can see the Knowledge Base gathering these notes in the table view (5).

What this gives you

• every concept you learned in the module

• grouped cleanly and consistently

• instantly retrievable

• with backlinks to the exact Study Events where the knowledge came from

This completes the full loop of the Study Vault:

Daily Note → Study Event → Knowledge Notes → Knowledge Base → Instant Retrieval

What You End Up With

A system where:

Daily Notes

Track the when: the chronology of your studying.

Module Notes

Track the where: the structure of your learning.

Study Events

Capture the what: the actual content created while studying.

Knowledge Notes + Knowledge Bases

Unlock the how: the connections between ideas and the ability to retrieve them instantly.

This is the foundation of the Study Vault — the system that turns studying into something clean, connected, and, dare I say… very nice.

Curious about using this system yourself?

The Obsidian Study Setup

Products and Services

🔗 Weekly Email Newsletter: A short weekly message about what I am working on, what I discovered recently, and some exclusive offers…

🔗 Obsidian Consulting: Quick results with your Knowledge Management setup or I don’t get paid…

🔗 Obsidian Setups: Journal, Work, Study, Writing…

🔗 Obsidian Courses: Obsidian 101, Study, Writing…

🔗 YouTube Channel: Free tutorials baby…

🔗 Website: Website to everything else…

Website | YouTube | X / Twitter | Newsletter

One of my consulting clients asked for a simple way to capture articles and YouTube videos straight into Obsidian, without breaking focus or adding extra steps.

Good news. You can automate the entire thing.

With Obsidian Web Clipper and Obsidian Bases, you can create a smooth little pipeline that pulls in videos, thumbnails, descriptions, and links, all neatly organised and ready to revisit later.

This is one of those setups that feels small but compounds massively over time. It turns random online discoveries into a growing library of knowledge inside your vault.

And if you’re building a serious PKM system or you want your Obsidian to feel more like a personal search engine than a pile of notes, this is a perfect place to start. (I build systems like this for clients every week, so if you want a done-with-you setup that saves you dozens of hours, you’ll know where to find me.)

Here’s how the workflow works at a glance:

• You find a YouTube video worth saving

• You tap the Obsidian Web Clipper

• It recognises the page and uses your YouTube template

• It sends the video to your vault as a fully formatted note

• Your Source.base automatically detects it and pulls in the thumbnail and the other metadtata properties for instant visual scanning later

Simple. Yet quietly powerful.

Now let’s build it.

The setup

This whole system only needs three pieces:

1. Install the Obsidian Web Clipper

2. Create a template for your captured sources

3. Build a Source.base to pull everything in automatically

Once this is done, every YouTube video or article you save becomes a structured, searchable asset instead of a forgotten bookmark.

(And if you want the exact versions of these templates and Bases that I use in my own vault, they’re included in my Obsidian Evergreen Vault)

Let’s break it down.

1. Install Obsidian Web Clipper

Open the Obsidian Web Clipper site and install the extension for your browser.

You’ll now find a handy obsidian icon to press whenever you want to send a web page to your Obsidian.That icon becomes your capture trigger.

Any time you want something inside your vault, you hit it and it goes straight in.

2. Create a Template for Your Captured Sources

Click the Obsidian Web Clipper icon, then tap the little gear to open the settings. This is where you control everything, including the templates you’ll use for videos, articles, and other capture workflows.

Create a new template and name it something like YouTube Template.

Here’s the structure:

Note Name:

(S)(YouTube) {{title}} - {{author}}

Note Location:
Pick the folder where you want your saved videos to live.
I just send mine to the main Notes folder.

Vault:
Select Last Used. The extension will automatically detect which vault is active.

Template Triggers:
These make the Web Clipper recognise that you’re on YouTube.

https://www.youtube.com/watch
https://youtu.be/

Properties (YAML):
These appear at the top of your captured note.

Here’s the thumbnail formula that lets your Source.base display the actual YouTube thumbnail right inside your table:

https://img.youtube.com/vi/{{ url | replace:"https://www.youtube.com/watch?v=","" | replace:"https://youtu.be/","" | split:"&" | first }}/hqdefault.jpg

Body of the Note:

{{description}}
![]({{url}})
[Watch on YouTube]({{url}})

This gives you a beautifully structured source note:
description, embed, and link.

(If you’re already imagining how this could work for articles, podcasts, books, and research, that’s exactly what I help people build in my consulting sessions.)

3. Build a Source.base to Auto-Collect Everything

Back inside Obsidian, create a new Base and call it Source.base.

You can do this from the Command Palette or by right-clicking in the folder sidebar.

Your Base only needs two filters:

The only column that requires a formula is the cover property.

This will surface your thumbnails directly in the Base so you can visually browse every video you’ve saved.

And that’s the setup.

Once you do it once, you never have to touch it again.

Importing a YouTube video!

Time to try it.

Go to YouTube and find a video that piques your interest and deserves a cozy little home in your Obsidian vault.

Click the Web Clipper icon.
Select your YouTube Template.
Add any tags or a short summary if you want.
(For multiple tags, separate them with commas: #tag1, #tag2.)
Then hit Add to Obsidian.

A new note will appear in your vault almost instantly.

Now open your Source.base.
Your new video should already be there, thumbnail included.

No sorting.
No renaming.
No dragging notes into folders.

Just one click and it’s structured, categorised, and ready when you need it.

This is how a PKM system becomes useful instead of overwhelming.
You build momentum one workflow at a time, and each one quietly supports the next.

Free Source.base file

Here is the free Source.base file if you are feeling a little lazy today.

If you want to take this further:

• I’ve built complete Obsidian systems for journaling, work, and study that use workflows exactly like this

• I teach people how to build custom setups during consulting sessions

• And for students, I’m releasing a study vault with a mini-course that turns your vault into a learning companion rather than a folder full of notes

If this workflow saved you time, you’re going to enjoy what comes next.

And if you ever want help building a system that feels effortless to use, I’m one message away.

Strength and honour, Dee.

Products and Services

🔗 Weekly Email Newsletter: A short weekly message about what I am working on, what I discovered recently, and some exclusive offers…

🔗 Obsidian Consulting: Quick results with your Knowledge Management setup or I don’t get paid…

🔗 Obsidian Setups: Journal, Work, Study, Writing…

🔗 Obsidian Courses: Obsidian 101, Study, Writing…

🔗 YouTube Channel: Free tutorials baby…

🔗 Website: Website to everything else…

Website | YouTube | X / Twitter | Newsletter

Here is a link to the Journal.base file if you don’t feel like writing out all the code yourself.

Why journaling matters

Can you remember what you were doing five years ago?
Five months?
Five weeks?
Five days?

Probably not.

The real question isn’t whether you can remember. It is whether you want to.

Why bother writing down what you did, how you felt, what you were thinking about, the challenges you faced, or the small joys you had?

I sat with that question and started listing some of the benefits I’ve derived from it.

The benefits of remembering

• You offload the boring admin that clogs up your brain.
  Admin tasks, passwords, logins, travel details, company processes… all the stuff that steals mental energy you could use for something actually creative.

• You avoid relearning things you already figured out.
  Future you can stop reinventing the wheel every six months.

• You stop repeating the same mistakes.
  Relationship patterns, old injuries, that life advice you promised you’d follow next time.

• You start understanding yourself better.
  Patterns appear. Trends make sense. You realise you’re less random than you thought.

• You resurface the good moments.
  Tiny wins, memories, small joys. Like borrowing a little ray of happiness from your past self. I use this to reconnect with people I haven’t spoken to in a while.

• You build a record of your life that becomes valuable simply by existing.
  A quiet archive that grows one day at a time.

I’ll write a separate piece that digs deeper into the philosophy behind this. In this article I want to show you how I built my daily to yearly journaling setup in Obsidian, and why it has quietly become one of the most important systems in my life.

Why Obsidian Base Changes Journaling

Before Base existed, journaling in Obsidian was powerful but a little messy.

You could create beautiful daily notes, but retrieving the information across your weeks, months, and years took effort. Queries worked, but they were slow, fragile, or needed plugins that weren’t beginner friendly.

Base removes all of that friction.

It lets you build clean, fast tables that pull specific data from your notes and present it in a way that actually helps you revisit your life.

You capture today, and your system handles the remembering.

The Daily to Yearly Journaling Method I Use and the Base Queries Behind It

Here is a quick overview of how my journaling system works.

I created a Base called Journal, and it holds all the Base tables that power my daily to yearly setup. Everything flows through this single Base.

Daily Notes: The Injection Point

Your daily note is where your life enters the system.
It is the injection point for everything you want to remember.

I fill it in as I move through the day: a few photos, some metadata, a short summary, and a rating.

That’s it. Nothing heavy. Nothing complicated.

You capture today once. Obsidian does the rest.

Weekly Notes: The First Rollup

At the end of the week, you open your weekly note and you are greeted by two b-e-a-utiful Base views that pull everything from your daily notes without any extra work from you.

View 1: Weekly Note
This table shows each day with its summary, rating, and pictures. It gives you a clean snapshot of your week at a glance.

View 2: Weekly Stats
This table takes the fields you care about and turns them into a simple scorecard.
I use a rating system from -2 to 2.
A 2 is a great day.
A -2 is a rough one.

The table summarises the full week and gives you your overall score at the bottom.

Monthly, Quarterly, and Yearly Notes: The Big Picture

These notes work the same way as the weekly note.
More days, bigger tables.

The yearly note adds one extra feature that makes it feel special.

Base lets you group all daily entries by month, which turns your entire year into a clean scrolling timeline:

• all 365 days

• all your pictures

• all your summaries

• all your statistics neatly grouped

It feels like a highlight reel of your life that you built without even trying.

Don’t want to set this up yourself?

I offer demo vaults with all this functionality built in, but honestly, the best results come from a one-on-one session.

In a single call, we set everything up for your workflow, not a generic one.
If you want the fastest path to a clean, personalised Obsidian system, book a consulting call.

Plugins We Will Need

• Obsidian Base

• Templater

• Journals

These three are the heart of the system. Base gives us the rollups, Templater gives us the dynamic metadata, and Journals makes daily notes effortless.

In this article, we won’t go into the setup of Journals. I have another article on the exact topic.

The Daily Note

I use the Daily Notes First method. Each day starts with a note named after today’s date. If today is 2025–11–25, the note is 2025-11-25.

During the day you add whatever matters.
A few lines.
A couple of pictures.
Small details that tell the story of the day.

Before you close the note, you fill in a few metadata fields like sleep, energy, healthy eating, day rating, and a short summary. It takes less than a minute.

Keeping it simple helps you stay consistent, so I follow the KISS (Keep It Simple Stupid) principle here.

This daily note is the entry point for the whole system. Everything you capture here rolls up automatically to the weekly, monthly, quarterly, and yearly notes.

Here is the template:

The daily note is not only for capturing. It also gives you a way to look back. I include two Base views:

• Today Years Ago

• Notes Created on This Day
  

1. Today Years Ago

This Base view shows what your life looked like on this same date in previous years. This brings me so much joy every morning, and it only gets better the longer you keep journaling.

To make it work, we create a calculated property that checks whether a note shares the same month and day as today. For a note titled 2025-11-25, it will look for notes like 2024-11-25, 2023-11-25, and so on.

I also add three simple calculated columns to preview the first three images from each past note:

first_image: image(file.embeds[0])
second_image: image(file.embeds[1])
third_image: image(file.embeds[2])

The result is a compact table that shows each previous year’s version of today, with a few pictures to jog your memory. It feels surprisingly meaningful.

2. Notes Created on This Day

You open today’s daily note and instantly see anything your mind produced on that date. Ideas, drafts, project notes, study notes, whatever you happened to create that day.

It is a simple way to connect your daily life with the work you produced on that exact day. If you want to see past years, you open the earlier daily notes for those dates.

The filter we use to get this base:

The Weekly Note

Your weekly note pulls everything from your daily notes automatically. You simply open the page and see your entire week at a glance.

It contains two Base views:

1. The Daily Overview

A table showing each day of the week with:

• rating

• summary

• pictures

• whatever else you want to pull in from your daily notes…

It gives you a clear snapshot of how your week unfolded.

The filter that makes this base possible:

2. Weekly Statistics

A table that pulls in the metadata fields you track, like:

• sleep

• energy

• healthy eating

• day rating

• whatever other statistics might be interested in…

Base adds up the full week and gives you your average score at the bottom.

It becomes a simple weekly report card, made automatically.

The filter that makes this base possible:

Monthly to Yearly Notes (Summary)

The monthly, quarterly, and yearly notes all work exactly the same way as the weekly note.

Each one pulls in your daily notes automatically and displays them in clean Base tables, with a second table that summarises your tracked statistics.

The only difference is the dynamic date filters. A weekly note filters by week number, a monthly note filters by YYYY-MM, a quarterly note filters by the quarter, and a yearly note filters by YYYY. Everything else is identical, just at a larger scale.

Here are some screenshots for the monthly, quarterly, and yearly filters if you feel like digging in to them:

Putting It All Together

You capture your life once each day and the rest builds itself. Your daily note becomes the source of truth.

Every weekly, monthly, quarterly, and yearly note updates automatically. You never copy information or rewrite anything. You simply live your life, capture the highlights, and let Obsidian Base assemble the bigger picture.

The result is a journaling system that grows in value the longer you use it.

Products and Services

🔗 Weekly Email Newsletter: A short weekly message about what I am working on, what I discovered recently, and some exclusive offers…

🔗 Obsidian Consulting: Quick results with your Knowledge Management setup or I don’t get paid…

🔗 Obsidian Setups: Journal, Work, Study, Writing…

🔗 Obsidian Courses: Obsidian 101, Study, Writing…

🔗 YouTube Channel: Free tutorials baby…

🔗 Website: Website to everything else…