The internet went wild! This was the most advanced thing ever; we’d never seen anything like it.

“Now add another button next to it. Make it bigger and red, with the label `Cancel.`”

And it did.

For most of us, it truly felt like magic (to be honest, it still does for me; like, how does it know?! I added it to my mental list of human-created wonders, like how heavy metal planes fly, or cruise ships don’t sink).

But the hype never faded. It evolved.

I remember how excited I was when I got early access to GitHub Copilot.

“Look, it knows what I want to do. It even uses the correct variable names that I used in this other file! You just need to press Tab, and it fills it out for you! No, it’s really smart!”

Like a child getting a new toy.

Then, we started chatting to our code. We started calling it an agent.

Sure, it made mistakes, but it helped us so much with our work. I haven’t had to remember the parameter order of the substring() method or how to do array chaining. I’d never have to open Stack Overflow again! And it could even fix my TypeScript linting errors!

And it kept getting better. New models and new tools kept showing up like crazy.

And the AI chat, which started as a sidebar, took over the main interface of code editors. Because why would we have the code view as the default when we spend most of the time talking to the agent and prompting??

Because we were prompting more than manually writing code. First, only the more curious people. Companies were reluctant for a short while to give access to these new tools to work on their codebases.

But the speed of adoption was unseen in human history.

No one wanted to be left behind, and the frontier models offered 10x speed with 10x less human effort.

We saw headlines about AI taking millions of jobs with self-driving trucks or automation in assembly lines. But as overconfident software engineers, with our comfortable, high-paying jobs and perks no other industry provides, we thought this wouldn’t affect us—for a time.

Until it did.

The general mood started shifting.

If AI can do so much more with so little human input, why would companies need to pay for us? Companies thought the same: a wave of massive layoffs swept across tech in the name of AI efficiency.

Suddenly, a generic sense of existential crisis reached all software engineers. I had several conversations with folks about how they feel about their job security and what their “Plan B” is if AI takes their job (surprisingly, many answered with growing vegetables on a farm; I guess that’s the furthest from computers).

Lately, I’m not hearing many of these concerns. We collectively agreed that AI - for now - won’t take all our jobs. Sure, it’ll make it damn hard for new engineers to enter the job market, because AI can easily do all the tasks juniors did, but that’s not “our” problem (I’m being super sarcastic here).

Then, on September 23rd, David Heinemeier Hansson walked on stage at Rails World.
The creator of Ruby on Rails, who used to be one of the loudest defenders of writing code by hand (with his famously strong opinions), opened the conference with: “It’s pencils down, people.”

His company, 37signals, stopped writing code by hand. He says he hasn’t written a line himself since around March.

If I look at my work, I haven’t either.

Our jobs have changed, forever.

We’re not spending our time on cracking some interesting coding challenge by looking at our code.

We’re writing instructions for our agents (usually multiple at a time, because who has time to wait for Claude or Cursor to finish one task? That’d be so inefficient!).

We’re writing skills so they automatically do the work we used to do.

We let our agents review code that others’ agents wrote.

No wonder social media is full of memes about how we interact with AI (often self-reflecting, mocking our new behaviors).

So in this new reality, when we don’t have to remember algorithms or how to write unit tests, and we can forget about the manual steps of git rebase, what is left to do?

What is expected from software engineers?

And how can we still be good software engineers when our whole job description has changed in just four years?

Who Is A Software Engineer?

It used to be easy to answer this question: a programmer, developer, someone who writes code that makes the computers do their thing.

Of course, that was never the real answer; coding was only one step in the process.

According to trustworthy sources (Wikipedia):

A software engineer is a technology professional who applies engineering principles and programming expertise to design, develop, test, and maintain software systems and applications.

Cambridge Dictionary summarizes it even more tightly:

Someone whose job is to create computer programs.

Neither definition mentions coding.

That’s already reassuring, because coding is what AI solves out of the box.

This isn’t a new idea.

Already back in 1985, Peter Naur wrote that programming is really about building a theory: a mental model of how the program solves a real problem. The code is just a byproduct.

While there can’t be one universal way to describe software engineers, we can use these previous definitions to see that neither mentions code written or algorithms, and both focus on the output, the result: creating software.

In fact, years before AI, this trend was already common: we weren’t required to remember everything by heart; Stack Overflow articles helped with our issues, UX libraries helped us make prettier software, and smart linting rules reminded us of missing semicolons.

We aimed to make code simpler to write, more robust, and safer. We built out-of-the-box frameworks and ready-made open-source packages we could reuse in our projects. Our job was to piece these puzzle pieces together in a way that makes sense for a computer and build a functioning program that (hopefully) addresses a business need.

In 1986, Fred Brooks (IBM, author of The Mythical Man-Month) split software difficulty into two types: accidental, which comes from our tools and syntax, and essential, which comes from the problem itself.

And since computers exist, we’ve been tirelessly working to remove the first.

But you can’t take away the essential part. It’s the work of figuring out what the software should actually do: the rules, the edge cases, and thinking ahead to what’s coming later.

There are many anecdotes about lazy programmers who automated half their work, and I think it is true in general: we, software engineers, have always wanted to simplify coding, write less, and lean on existing artifacts.

What Makes a Good Software Engineer

Let’s go back to first principles.

If software engineers are expected to create (and maintain) computer programs, then a good software engineer delivers them.

They are expected to make sure that what they build works as designed.

Or we can go even one step further: really good software engineers are expected to build things that solve actual problems, and those products work as designed.

When AI writes all the code, what is the human Moat? That machines can’t do.

Taking full responsibility for the product.

I really like this idea, as it circles back to my blog’s name: high agency dev.

It means that, as a software engineer, you can be outstanding if, instead of just executing the tasks that are listed in your Linear, you take initiative at all steps and own your work:

• You contribute to conversations about what to build (push back if needed, since you represent the technical side).

• You deliver to the highest standards, making sure your work doesn’t degrade others’ work.

• You proactively unblock your work; don’t wait for others.

• You take full ownership, responsibility, and accountability for the code and configurations you do, even if it’s written by your agents.

• You make sure, with the utmost care, that releasing your work to production goes smoothly, without breaking anything (and you do it confidently).

• You help follow through on the impact of your work.

• And you make sure everyone on your team is well informed and always up to date.

You don’t wait for others to tell you what to do. You take initiative: you notice things only you can spot early on; you find the right people to make decisions; you bring technical expertise to the table; and you make sure what’s promised gets done.

No matter who (or what) writes the code, someone has to answer for it.

IBM figured this out back in 1979. A slide from an internal training said: “A computer can never be held accountable. (…)”

Karpathy said the same at Sequoia in April 2026: you are still responsible for your software, just as before.

Antisocial Reality

It might be harsh, especially if you’re the kind of person who used to love coding, being in the zone. Sorry, but this is the new reality.

DHH loved it too. In 2025, he said that if he stopped writing code himself, he would turn into “a project manager of a murder of AI crows.”

A year later, he’s the one saying pencils down.

You might hope that some part of the job will stay technical: writing code and not talking to people. Designing architectures, configuring servers, tweaking databases.

And while you should know about these things, the truth is: agents can already do them too. Your understanding is more important than your skills to manually go and implement them.

There are flame wars in the tech scene about how AI can and will do all your work. You don’t have to agree with either side, but if you pay close attention to the direction and speed, I think you can see where things are going.

Even if there are current limitations, it’s only a matter of time before newer, better models solve them too.

So your new work becomes figuring out what to deliver, working with the team, and directing your agents to implement it correctly.

Building Is Easy

If the agent writes the code, what is hard now?

Knowing what to build.

Historically, as a software engineer, you had little impact on which features got prioritized.

But a feature nobody needs is still a feature nobody needs. You just ship it faster.

So speed stopped being your advantage.

Your technical expertise is still needed elsewhere: managing complexity (don’t let AI go rogue; you still want to understand it well and hold the steering wheel), thinking ahead for the future (so the current solution doesn’t introduce changes that’d make future work more difficult), considering alternative, more optimal solutions, and keeping the overall context end-to-end in your head.

And what’s left is deciding (or helping decide) which problem is worth solving. And for that, you need a business hat on top of your engineering one.

Think Like a Product Engineer

This idea isn’t new, but AI has popularized it in recent years.

In 2019, Gergely Orosz wrote about the product-minded software engineer. He described engineers who care about the users and the business, not just the ticket. They ask why a feature exists. They suggest cheaper ways to test an idea, and they follow the results after it ships to see whether it helped.

Back then, it was like going the extra mile. Those engineers often became team leads. Proactive, communicating directly with business stakeholders.

But now it’s the job.

When an agent can write the code, solving tickets won’t put you ahead.
You can stand out by doing everything around them.

Who asked for this? What problem does it solve? How will we know it worked? What happens if we don’t build it at all? What can go wrong? Who should I involve?

Product decisions might seem to be made above your level. But questioning these things can bring you more visibility in the team and new angles that only you could see. And if you’re working in a healthy environment, these questions and pushbacks are embraced, as everyone’s trying to make the product better.

This is where high agency comes back in:

A product engineer doesn’t wait for a perfect spec to land in Linear. They go and find out what the spec should say.

But enough of the philosophizing. What does it look like in practice?

A Day In The Life of a Good Software Engineer

Grow your own context

We like to keep AI context small to perform better.

But you’re a human, not a company, and your advantage is you can have a much broader overview than AI does. You don’t have to know all the details; that’d be overkill.

But go and talk to a lot of people:

The PM, the designer, QA, fellow engineers, the on-call person.
Each of them knows something about the ongoing projects that aren’t in the tickets, and they might give insights about future directions and upcoming initiatives that can expand your context.

Keep everyone updated

With agents, work moves fast. Often way too fast for the people around you to follow.

Keep everyone up to date.

A three-line update every day beats a perfect report every two weeks.

I learned throughout my career that even if you’re breaking bad news early on (e.g., delays or blockers you weren’t aware of before), the team can handle it. It’s much better than trying to figure it out quietly on your own, behind the scenes.

Remember: you are the one who has access to the code and who knows about the progress. Other stakeholders have to take your word for what’s going on. Don’t keep them in the dark.

Give frequent updates to build trust and also to increase your visibility.

Write instructions like they’re the product

Because they are now.

Not gonna lie, I’m also not a fan of writing tech specs and PRDs, and I just want to jump into coding.

But your job is now to translate between the business and computers. Take the requirements and phrase them in a way your agent can understand.

Your deeper knowledge of the overall context is extremely useful here: you can think of unwanted side effects and long-term expectations.

Hold the theory

I’ve found that agents try to solve the problem in the most efficient, simplest way. But that often doesn’t consider other requirements and limitations that you, as a well-informed engineer, would automatically incorporate into your solutions.

For example, if you’re implementing a new feature while another team is removing legacy code, you shouldn’t use it in your solution. AI might jump at it and use it, since it’s how it’s been used elsewhere. But you should know better.

Your agent doesn’t have this overall context of how things are going in your company. But you do (or you should have).

Writing those documents is how you add the extra information: the business rules, the states, the edge cases, the trade-offs, and instruct your agents to do things the right way.

Your 90% and your 10%

In April 2023, Kent Beck (the creator of TDD and Extreme Programming) tried ChatGPT for the first time.

His verdict: the value of 90% of his skills just dropped to $0. The other 10% got 1000x more leverage. “I need to recalibrate.”

But he couldn’t answer the questions: which skills were which.

It took him two years to name the 10%: having a vision, cutting the path into milestones, and keeping the design under control so complexity doesn’t explode.

Once again, none of it is typing.

Coding Was Never the Job

Can you think about the best engineer you have ever worked with?
Do you remember how fast they typed? Or do you remember the question they asked in planning that saved the team a month of work?

That’s the job. It always was.

And we just couldn’t see it, because the code was in the way. It took most of our time. It was the loud, visible part. The part with green checkmarks and merged PRs.

Now that AI took that loud part, what’s left is the part that could make you stand out in the first place.

Honestly, I think this is good news. 😁

An orchestra conductor doesn’t play a single note during the concert. But nobody asks if they’re doing any work. They know the whole piece. They keep everyone in time, and they hear the wrong note before the audience does.

You have your own orchestra now.
Your agents play, your team listens, and you conduct.

The café is 200 meters from my front door. I have walked past it most mornings since I moved to Barcelona in 2016. And every time, I ordered in Spanish, because three years of daily lessons had not given me the one sentence I actually needed to order my large oat latte.

So the problem was not that I skipped days. In fact, I never skipped a day.

What the streak was actually measuring

Duolingo is well made. The streak, the leagues, the little owl guilt-tripping you at 9 pm. All of it works. That is why I opened it 1,200 times.

But the app never knew anything about me.

It did not know I live in Catalonia. It did not know that I get the past tense wrong in the same way every single time. It did not know that I need to ask for a table for two, or explain to my coworking receptionist that the aircon makes the office freezing cold.

It fed me sentences that were built for nobody in particular. The internet is full of jokes about them.

The streak was measuring my attendance. It was not measuring whether I could speak.

The 30-minute replacement

“Scratch your own itch,” they say. So I rebuilt the thing as a Claude project.
No code. Nothing to install, apart from one iPhone app at the end for the streak.

It comes down to two tools, one job each:

Claude is the teacher. It writes the lesson, asks the questions, corrects me, and explains why I was wrong.

Notion is the teacher’s memory. Claude on its own forgets. It has some built-in memory, but a language course is too much to hold there: a curriculum, every word I have learned, every mistake I have repeated, a log of every session. Notion is built to store that, and Claude can read it and write to it.

That connection is the entire trick. Everything else is detail.

If you would rather watch me build it, the video above is the whole thing, start to finish. If you would rather read, keep going. The written version has all the prompts and the script.

Setup

You need a Claude account and a Notion account. The free tiers are enough to try it.

1. In Claude, open the settings and connect Notion. Approve the permissions it asks for.

2. Create a new project. I called mine “Catalan tutorial”.

3. In the project, ask Claude to build the Notion workspace for you.

That is it. You do not create a single Notion page by hand. Claude does it, because it now has access.

It will get some things wrong on the first pass. Mine came back with a Canadian flag as the icon, which I assume is because Canada and Catalonia both start with CA. 🙄 It also built a curriculum that was too thin to use.

Both were fixed by asking.

The four pages, and why they are separate

This is the part worth copying, even if you never touch Claude.

Curriculum and progress. The path through the language, plus where I am on it. Without this, every session starts from zero, and I get taught “hello” for the fourth time.

Mistake tracker. Every error, with the correction. This is the page that matters most. It is what makes tomorrow’s lesson different from today’s, and it is the thing no app was doing for me.

Vocabulary. Words I have met, and how well I know them.

Lesson log. What happened in each session, and the date. The streak reads from here.

Four pages instead of one big page, because Claude reads them separately. When it starts a lesson it pulls the mistakes and the vocabulary, not the whole history of my learning.

You can use the exact prompt I used to create my language learning setup in Notion.

The instructions

Here is where the personality goes. This text lives in the project instructions, so every new chat in the project already knows how to teach me.

You can download all instructions here:

Setup Instructions

Copy it, change the language, change the pace. Mine says to start every session with a warm-up on old material, and to show me one exercise at a time instead of dumping ten at once.

That last rule came from using it. The first version gave me four exercises in one message, and I could see the answers to questions I had not reached yet. So I opened a chat and asked it to change the rule.

And that’s the cool part: whenever the tool is wrong, you can go and fix it with one sentence. Try that with Duolingo.

What 15 minutes looks like

I open the project on my phone. I say “let’s start today’s lesson”.

It takes a few seconds to read Notion. Then:

• Warm up on what I already know

• Rehearse yesterday’s mistakes

• Learn one new thing

• Drill it until it sticks

The exercises are set in my actual life. “You walk into a bakery on Carrer d’Enric Granados at 9 am. How do you greet the person behind the counter?”

I answer bon dia.

When I am done, Claude writes the session to Notion: progress, the new words, and the mistakes I just made. Tomorrow those mistakes come back in the warm-up and practice.

Bringing the streak back

I did not miss the leagues. I missed the number on my home screen.

So I built it back with an app called Scriptable, which runs a small script as an iPhone widget. It reads the lesson log in Notion and shows the streak.

You can download the script here.

To make it work, you need two values from Notion:

1. An integration token. In Notion, open any page, click the three dots, go to Connections, then the developer portal. Create a connection, name it, and copy the token that starts with ntn_. Then give that connection access to your learning hub.

2. The page ID. It is the last part of your Notion page URL.

Paste both into the config at the top of the script, between the double quotes. Press play. If it errors, the message tells you which field name did not match, and you can paste the error straight back to Claude.

Then long-press your wallpaper, add a Scriptable widget, and choose the script.

If you’re a visual person, setting this up is also in the YouTube video so that you can follow along.

The part that is not about Catalan

I am a developer, so your easy reaction might be “of course he built that”.

But I wrote no code. The Scriptable script came from Claude too, and the only technical step was copying a token from one screen into another (heck, Claude even gave me the instructions on how to obtain those API keys).

The whole build took 30 minutes, and most of that was me changing my mind about the curriculum.

The language is not the point. The point is that you can stop accepting a tool that treats you like everybody else.

Something you do every day, that almost fits (but not quite perfectly): that is the thing to rebuild first.

Mine was a streak. What is yours?

The instructions and the widget script are above, free to copy, you can download them at https://johnnyfekete.com/language. If you build a version for your own language, I want to see it.

And then I open a new tab (automatically, almost unconsciously), and I’m already looking at a stranger’s kitchen renovation on Instagram.

The agent will not ask me for some unknown minutes. The machine is the bottleneck, and it has no plan for the minutes it hands back to me.

The new “wait”

I have waited for computers my whole career. Builds, test runs, deploys, migrations. But those waits had a shape. A progress bar, a rough number, it told you how much’s left.

Agent waits do not have that predictability. A small refactor comes back in 30 seconds. A multi-file change takes four minutes. But you can never know.

And then there’s the other kind. Working towards a goal. I hand over a prepared PRD, the agent runs on its own, and I do not hear from it for 20 or 30 minutes.

The waits come in different sizes, but one thing’s common: there is no progress bar or countdown.

And there is nothing else to do with that time. The next task depends on output that does not exist yet. There is no diff to review, because nothing has been written.

Research on this is older than any of these tools. David Maister wrote The Psychology of Waiting Lines in 1985, about restaurants and airports, and one of his eight rules is that uncertain waits feel longer than known, finite waits. When you cannot see the end, anxiety fills the gap, and anxiety is what makes you just quickly check something.

Forty years later, this is still being tested. A CHI 2026 paper put 425 people through a task with a forced wait in the middle. The group that got no timer felt the wait as significantly longer than the group that got a countdown. In the free-text answers, the no-timer group was the one writing things like I thought there might have been an issue at first.

(The authors are careful here, and I will be too. Their waits were 10, 30, and 60 seconds, and everyone knew the wait would end. They say straight out that the results should not be stretched to unpredictable delays, which is exactly what we have. So take it as a hint, not a proof.)

That was still a relief to read:

My doomscrolling habit is not a character flaw.
It’s my progress bar replacement.

So the question should fill that gap instead.

What everyone tells you to do

I’m a sucker for optimization, so naturally I went looking for what other people do with this time.

There are two main groups.

The first one is: run more agents. Git worktrees, parallel sessions, five branches at once. One post claims that if you run one agent at a time, you are using about 20% of what is available to you.

This got popular fast, and worktree support is now built into the tools instead of something you script yourself.

The second one is quieter. Stay next to the work. Johannes Millan’s guide says to re-read your prompt, scan the code around the file, and draft your next instruction. He argues against context switching, even into other work tasks.
“Reviewing someone else’s PR” sounds productive but loads entirely different codebase context. Save code review for dedicated blocks, not AI waits.”

Based on my experience, running multiple parallel workstreams comes with huge productivity gains.

Running four agents at once does move four things forward instead of one. But you still wait. You are now waiting for one of four to finish, or for one to ask you for the next clarification and prompt.

The only test I use now

I thought the rule was about screens. Get off the laptop (and don’t pick up my phone instead), do something physical.

But that turned out to be wrong, because some of the best things I do during these waits are on a screen.

That is why the test is the two questions and not the device.

The one-second test: can I put it down in one second?

The fuller-or-emptier test: does it leave me fuller or emptier?

Instagram fails both. I cannot put it down (it is built so I cannot), and I come back more tired.

Slack fails the one-second test. You cannot put it down in one second. A message pulls you into a thread, the thread needs context, and by the time you are useful there, your own review has gone cold.

Reading the news will make me anxious, and let’s not even mention X.

What is actually on my list

Saved articles, read out loud. I keep a backlog in Readwise Reader that used to grow. Now it is what I open first. I read on the screen and even let it read the articles out loud. It is slower, which is the point, and it uses a completely different part of my brain than reviewing a diff. It keeps my focus on one thing at a time.

The boring task beats rest. Baird and colleagues ran a creativity experiment in 2012 where people took a break in the middle of a problem. Some did a demanding task, some did an easy one, some rested, some got no break. The easy, boring task beat all of them, including rest. Simple work that lets your mind wander is better for the problem you left behind than sitting still is.

So the drying rack is not a chore I squeezed into a work block. It is the task that does something rest cannot. Simple work lets your mind wander, and the wandering goes back to the problem you left.

Which is a strange thing to learn about a drying rack.

Nintendo Switch. Sean McRae made a video about swapping doomscrolling for a few minutes on his Switch. I have not done this yet, but I can see it working, especially with Nintendo games, which are charming and slow (wandering in Hyrule, collecting fossils in Animal Crossing).

The guitar. It sits on a stand behind me. Three minutes of the chords I keep failing at is three minutes I would not otherwise spend on them. Over time, it stops being three minutes and becomes actual practice.

You might not be playing guitar, or any instrument, but I’m sure you can find something in your life that could benefit from small bursts of practice time. Maybe a new language?

Posture. I have been sitting like a shrimp all my life. Curled forward, shoulders up near my ears, neck at an angle no physio would sign off on.

Every stretch anyone has ever recommended to me takes about 90 seconds. That is the entire reason I have never done one. Not the difficulty. The 90 seconds.

And now I have 90 seconds, over and over, handed to me by a machine. Chest opener in the door frame. Chin tucks. Standing up straight for as long as it takes the agent to finish reading a file.

Years of damage, and it turns out the repair schedule was waiting for me to start using AI. 🙄

Look into the distance. While you’re up, look at something far. Your eyes need this.

Watch a video. Not any video; then we’d be back to Instagram territory. But these moments are perfect to train yourself. I have Udemy courses, and I follow YouTube creators who talk about new AI workflows, models, or other topics that are useful for my life.

Two things that make all of this easier

Turn on sound notifications.

This is the small one, but with a big impact on your mental peace. If you have to keep glancing at the terminal to see whether the agent is done, you never really leave. You are not folding laundry. You are folding laundry while checking Claude “Flibbertigibbeting”.

Most agent tools have built-in notification sounds for when the agent finishes. So you don’t have to keep checking them periodically.

Then make the gaps bigger.

Small holes are great in Swiss cheese, but not so much in your productive workday. Even if you fill every one of them well, you have still been interrupted numerous times.

But what if you’d make those gaps bigger and less frequent?
I suggest you do exactly that.

I use Matt Pocock’s workflow, which splits work into two kinds of tasks: human in the loop (HITL), and away from keyboard (AFK). He is blunt about which is which: planning and alignment have to be human, and implementation can be turned into an AFK task.

So you spend the first block of your work getting aligned, writing it down, and cutting it into small issues. Each issue gets labeled. Then the agent takes the AFK ones and goes on its own. Subagents go wroom wroom, and there’s no pinging every couple of minutes.

It works, and I like it not only for the code quality (though that is better too). It is what it does to the shape of the day.

All the decisions land in one block at the start. Then the agent runs for 20 or 30 minutes, and I don’t need to babysit.

And there are so many more opportunities to do in these extended periods: go on a walk, update your Linear tickets, clean up your Slack messages. That’s time for a proper guitar rehearsal or a walk long enough to think.

You end up with the same total waiting, but the allocation is optimized for you.

Can I get rid of small gaps?

I wish.

But there are just so many tasks a day that require back-and-forth. And as long as AI can’t reply immediately, like a conversation, those gaps will stay.

Matthew Dicks wrote a whole book about this called Someday Is Today. He argues that the random minutes scattered through your day are real time, and that people who get a lot done are simply people who use them. He wrote novels in car parks while waiting to pick up his kids.

And although I don’t treat every unused minute as a waste, I like parts of his idea: waiting times are there anyway, and it’s up to you how to use them. Small gains add up, and you can achieve more if you make use of them.

The difference between his version and mine is one word. He wants those pockets to be productive. I want them to leave me better than they found me.

Your flinch is out of date.

Pick up a guitar in the middle of a coding session, and something in you flinches. It looks like the thing that’ll slow you down and pull you away.

But that flinch runs on an old model of the day.

One where the machine was slow and I was the fast part.

That is reversed now. The agent is faster than me, and the work still ships. Probably more work than was ever possible before.

A meta-analysis of micro-break studies found they raise vigor and lower fatigue, with the clearest effects on exactly the kind of work you are about to go back to. It also found that the longer the break, the bigger the effect.

So stepping away while your AI is working is not time you lose.
It’s time your agent handed to you and has no plan for.

Everyone on your team is teaching their AI the same things. Over and over again.

How the tests work. What the conventions are. What not to touch. Fifty engineers, fifty private setups, the same lessons, every single day.

Nobody notices, because it’s invisible work. There’s no ticket for “explained our mocking pattern to Claude again.” Nobody mentions it in standup. It just quietly eats hours across the whole team while everyone assumes their AI setup is their own business.

But your AI isn’t the problem. The fifty private copies of the same lesson are. And you can fix it without forcing everyone to work the same way.

This article expands on a presentation I gave at Claude Meetup for Builders in Barcelona, you can download the presentation slides here:

Claude Code Team Scale

2.13MB ∙ PDF file

Download

Download

One repo, three layers

Every AI coding tool can read instructions straight from your repository.

Claude Code looks for a file called CLAUDE.md.

Cursor has its rules files, Copilot and Codex have their own formats.

These files tell the agent how your project actually works: how to run the tests, which patterns the team follows, which parts of the codebase are load-bearing and shouldn’t be touched casually. Without them, the agent walks in with zero context and guesses. Those guesses are exactly what you keep correcting in chat, session after session.

So the question isn’t whether to give your AI context. You’re already doing that, manually, every day. The question is where that context should live.

My answer is a three-layer structure, that scales form individual contributors all the way to teams with 100+ engineers.

The first layer is a file called AGENTS.md, at the root of the repo.

This is the shared truth for the whole team, and the reason it’s called AGENTS.md and not CLAUDE.md is important: it’s following an open standard, not a vendor file. Cursor, Copilot, and Codex all read it natively.

More than 60,000 open source projects use it, and the standard was donated to the Linux Foundation. So when a teammate says “sounds nice, but I use Cursor,” the answer is: same file. You write the team’s knowledge once, and every tool picks it up.

What belongs in it? Anything that’s true for everyone.
How testing works in this codebase. How experiments are structured. What the code style is beyond what the linter enforces. The stuff you’d tell a new hire in their first week.

This file should be a summary, a constitution, not a wiki. Try to keep it under 60 lines, not 600.
This feels wrong at first, because once you start writing down team knowledge, you want to write down all of it.
But language models don’t follow long rule lists the way a compiler follows code. The more rules you stack into one file, the less reliably the model follows any single one of them.

A short file of principles gets respected. A long file of edge cases gets skimmed.

The second layer is a shared folder of skills, docs, MCPs.

There’s another annoying practical problem here: the tools disagree about where these should live.
Cursor wants a .cursor folder, Codex wants .codex/skills, Claude wants .claude.

That’s fine for a solo developer and painful for a large team, especially if your company lets people choose their own AI tools.

The good news is that a consensus is forming in the agent standards discussions around a vendor-neutral .agents directory, and Codex already recognizes it.

Until the rest catch up, there’s a simple bridge: use your AGENTS.md to point at the folder and explain what’s inside. The agent won’t discover the skills automatically the way it would in its default location, but it will go look for them and use them as expected.

The third layer is your gitignored personal workspace.

These are local instruction files that never get committed. Your shortcuts, your preferences, the workflow quirks that work for you and would start an argument in a team meeting. They are all yours!

Things that I put in my local agent rules:

• state & memory (PRDs, notes, issues)

• instructions about my personal working style (tone of voice, PR description style)

• collaboration rules (aim for smallest working change, don’t run migrations without asking)

• personal shortcuts (eg. I use port 5432 instead of 3001)

• aliases (“when I say widget, I refer to the daily score card”)

These local instructions can be tested, and if you think they are applicable to the whole repo, you can eventually move them to a permanent place).

Git worktrees do not copy over gitignored files! This might cause some surprises, but you can easily fix it by setting up git hooks for worktree creation and setting up symlinks.

The entire CLAUDE.md

So what happens to CLAUDE.md? How does it look like after all this.

Here it is, complete and unabridged 😁:

@AGENTS.md

That's the whole file. Yes, just one line.

The @ syntax is Claude's import mechanism: it tells Claude Code to go read AGENTS.md and treat its contents as its own instructions. Cursor, Codex, and Copilot read AGENTS.md natively, and Claude pulls it in through the import.

One source of truth that every tool sees it.

Judgment goes in markdown, law goes in hooks

AI is costly and can hallucinate. Not everything should be done by it.

Everything in AGENTS.md is advisory. In practice the model follows it maybe 80% of the time, weighing your rule against the situation in front of it, a bit like a colleague who knows the guidelines and occasionally deviates.

But hooks are different. They run automatically at fixed points, before or after the agent acts, and they runs 100% of the time.
No judgment, no interpretation, no exceptions.

So the split should be like this:
Judgment goes in instructions, where the model can weigh it.
Law goes in hooks, where it’s enforced without discussion.

Formatting, linting, blocking secrets from being committed: those are laws, put them in hooks.

“Prefer this pattern, here’s why”: that’s judgment, put it in markdown.

Deciding what’s judgment and what’s law is a negotiation between humans.
Negotiate the shared stuff together. Testing standards, code style, what counts as done.
And leave room for individuals.

Context is a team sport. Shared project context, plus individual workspace

I created a cool landing page in 2018. It was a fun, creative experiment, where my head “turned around” the topics that were relevant to me at that time.

And I added animations (a lot) that started playing on mouse trigger.

But I haven’t used it for much. No content, no updates. Not really mobile-friendly.

The most you could do was find my email address.

It was never a priority, despite receiving a few hundred visitors every week.

But lately, I’ve been thinking of stepping up my online presence. And after seeing a post from one of my friends who was also working on her personal website, I took it as a sign.

So I decided to revamp johnnyfekete.com, bring it to 2025 while keeping its essence.

Do you remember the MTV show “Cribs”?
Well, this is my new corner of the internet. Let me show you around.

The home page

This page is the showstopper part of my website.

I wanted to keep the idea with the topics around my head, and turn to the selected one.

But I changed the five areas to new ones that are more relevant for my current self:

• Creator

• Product Engineer

• Founder

• Educator

• Actor

I didn’t want to be too engineering-focused, as I do a lot more than that.

Instead, I took a deep breath and chose the areas where I’m trying to expand my impact.

The “actor” one was a particularly hard decision: I contemplated whether I should include it, or keep it focused “on work”.

But just like the coolest apartments reflect the owner’s personality, I also wanted to pour my whole self into it without filtering.

The old animations had to go. They felt outdated, and I didn’t want to just replace them with new ones.

Instead, I came up with this effect where once you move the mouse over any topic, the page gets covered with stripes of text running across the screen.

This felt a lot fresher, more modern, and honestly, more cheerful. Much closer to my identity.

The sad part is, I couldn’t keep the same functionality for mobile devices. The vertical layout and lack of mouse cursor don’t permit the head-rotation mechanism, but I think I managed to still bring over some of the magic by showing the text strips on tap event before navigating away.

Detail Pages

I am a perfectionist.

And perfect is the enemy of done.

So I consciously decided to go with big letters, bold colors, and not get lost in pixel-perfect designs.

I wanted to focus on having good, up-to-date content and publish the website instead of polishing it forever.

The five sub-pages cover key interest areas in my life.

Each one with examples, references. Full of small interactions, but I tried to find the balance and not overwhelm the users.

I found a design language through trial and error, and it felt like it was matching the style of the home page, with its colorful text highlights or rectangular card components.

I added some effects on page transitions, the interactive glow behind the face in the bottom corner, and whimsical hover states for the blog posts.

Really tried not to overdo it (be my judge).

These pages all work well on mobile; there were no challenges with implementing their layout on smaller screens.

And as they have a lot more content (well, the old website didn’t have any content, so the bar was pretty low), I hope that these pages will be useful for showcasing what I do.

Contact Page

I checked a few personal landing pages.

One thing stood out: the ones I liked didn’t have a boring contact form. Instead, they simply linked their social links and had their email address publicly visible.

I was evaluating if it’d lead to spam, but I felt that it’s more authentic if I also add the direct contact info instead of setting up an impersonal contact form.

So that’s what I did. I can always adjust it in the future.

How Did I Build It

It all started with the pictures. I re-did the photoshoot three times 🙄 (perfectionism, get out of my head)

With Photoshop’s magical ✨ background removal, I could get the transparent background with literally a single click (in my old website, I had to use lasso tools to get to mediocre results).

Then came the coding part. I am a software engineer with strong opinions, but I’m also lazy in typing a lot.

So instead, I used AI to write the code, instructing it step-by-step, reviewing the changes.

It was like having a personal assistant, doing everything as I asked them to do.

It was a good learning process also: bigger tasks failed more often than not, but if I always asked for tiny, incremental changes, it did an outstanding job.

So our cooperation looked like this: I was the one with the big picture and overview, and AI was my “Santa’s little helper” who did all the tasks for me.

It took about ~15-20 working hours to build it from scratch, once I had all the photos and text content.

Keeping It Live

Now that I have my new corner on the internet, it’s my task to keep it up-to-date.

Adding new articles, links, videos, and curating them.

So that in 7 years from now, I don’t have to look again at a stale, outdated website, but rather one that grew together with me.

Josie has just wrapped up a major project at work. The quarterly market analysis for Westeria is complete, the numbers check out, and her recommendations are solid. She closes her laptop with a sigh of relief.

Time for a well-deserved break. She walks to the coffee machine where she meets Taylor - who's notorious for her color-coded notes, and who has also just finished the same quarterly market analysis but for the Eastlund region.

The core requirements are identical—same data sources, same objectives, same deadline. Both regions face similar challenges and opportunities.

But while Josie had already mentally checked out and started scrolling through emails, Taylor spent just ten more minutes on her project. She added a simple visual comparing Eastlund's performance to the previous three quarters. She created a one-page executive summary highlighting the three most actionable insights. She even took a moment to send a note to the regional sales team with specific callouts relevant to their territory.

Two weeks later, during the department meeting, it's Taylor's Eastlund analysis that gets mentioned by the VP. "This is exactly the kind of work we should all strive for," he says.

Josie is puzzled. Her Westeria data was just as accurate. Her analysis was equally insightful. What made the difference?

It wasn't some innate talent or working twice as hard. It was those ten minutes of thoughtful finishing touches—the extra mile that felt almost effortless after completing the real heavy lifting.

What happens with Josie and Taylor plays out across every field and project in life, whether we're finishing a work assignment, wrapping up a home renovation, or completing a creative passion project. The biggest impact often comes from the smallest investment at the finish line.

Poached Eggs

Have you ever wondered why restaurant food often tastes better than the same dish made at home?

I recently made poached eggs for breakfast—perfectly fine eggs, cooked in water until the whites set.

Later that week, I ordered poached eggs at a café. The core product was identical, but the experience was entirely different.

The restaurant's eggs arrived on a warm plate. The bread was artisanal sourdough. A few delicate herb leaves added color. There were no drips or smudges.

The fundamental cooking process took exactly the same time. Those final one-minute flourishes justified the price difference and created a completely different experience.

Where Small Touches Create Big Impact

After that breakfast revelation, I became a bit obsessed. I started mentally cataloging examples, and it turns out it can be applied to most things in my life:

Learning guitar taught me that simply strumming the correct chords won't sound as enjoyable. Adding small variations—a hammer-on here, a palm mute there—transforms mechanical playing into music people want to hear. These tiny techniques take seconds but make the difference between sounding like a beginner and a musician.

When writing long texts, taking just three minutes to proofread elevates the entire piece. The writing might take hours, but that final quick review takes almost no time while dramatically improving how readers receive your message.

At the gym, wiping down equipment after use requires maybe 15 seconds. Yet this small gesture separates considerate gym-goers from those everyone silently judges. (If you're the person who leaves a sweat angel on the bench press, we need to talk.)

When coding, adding clear comments and organizing functions logically might add five minutes to development time. But when someone needs to understand that code later (including your future self), those five minutes save hours of frustration.

And if you have ever prepared pasta for friends, you know the difference it makes to present it nicely on clean plates with freshly cut basil. Feels like fine dining right at your dinner table.

The extra mile gets your work noticed.

Not Perfectionism, Not People-Pleasing

"But wait," you might think. "Isn't this just another form of never-ending work?"

Nope.

While perfectionism keeps you trapped in a cycle of endless revisions, driven by fear, the extra mile is a conscious choice to add specific value in a limited time.

People-pleasing exhausts you as you try to meet everyone's expanding expectations.

The extra mile is about your personal standard of quality.

What's the difference? Boundaries and intention. You decide exactly what small touches matter most and exactly how much time you'll spend on them.

The Five-Minute Mindset

I watched how the extra mile transformed my work, but the real challenge was making it consistent.

I don't have some fancy name for this approach—it's just a mental pause I've tried to build into my workflow. Sometimes I remember, sometimes I don't.

The beauty of the extra mile isn't in complex systems or detailed checklists. It's in the pause—that brief moment where you choose to give something just a little more care before moving on. Don't think big, usually 5 minutes is more than enough.

Not every project deserves the extra mile treatment. Sometimes good enough really is good enough. That quarterly report that nobody reads? Maybe just hit send.

The Greatest Return on Investment

What fascinates me most is how disproportionate the impact can be. Those final touches can transform entirely how people experience your work.

A small visual addition becomes the talking point in meetings. A thoughtful follow-up note leads to new opportunities. A clean, well-organized deliverable builds trust that leads to bigger projects.

The irony? The hardest part of any project is already behind you. The extra mile is the easiest distance you'll travel, yet it's where the magic happens.

Your Turn

Like Josie and Taylor, we all face the same choice countless times each day. We can declare our work complete the moment the essential elements are done. Or we can take one more small step.

The next time you're about to call something "done," pause for just a moment and see if there's anything that could make your work truly stand out.

I still haven't figured out where to draw the line between worthwhile polish and diminishing returns. Maybe that's the real skill—knowing exactly when to stop.

The extra mile is the easiest one you'll ever travel. And somehow, it's the one that takes you furthest.

If you missed it, he embraced AI and encouraged employees to use it (more than that, it's now an expectation from everyone). Not only that, he introduced a new hiring policy, which says they need to justify every new hire that the task couldn't have been done by using AI instead.

As you would expect, the internet went bunkers. Everyone has an opinion. Traditional news outlets called it shameful, others had already projected the end of the traditional workforce.

We might argue about the morale of this decision in a company that generated $8.88B in revenue in 2024, but I want to point out some implications for solo founders, and micro startups with limited resources.

They can benefit from AI more than anyone else. And – agreeing with Tobi on this one – they can start businesses with a lot less effort, initial costs, and field expertise than ever before.

While access to unlimited information shifted the work landscape some decades ago, using AI can enable even more people to get creative and start something on their own.
Because they will never be alone alone.

The number of conversations I have with ChatGPT and his little friends (Claude, Perplexity, Gemini) is already colossal, and only increasing.

They help me in so many aspects, from writing marketing articles, doing market research, designing social media content plans, and helping with rewriting emails to sound more professional.

Copilot helps me write code twice as fast as before (even without vibe coding).

Photoshop's AI helps me design pretty illustrations for social media, removing unwanted objects from images.

There are amazing AI services to clean the voice in video calls and podcasts, to take automatic notes from video calls, and even to train you to speak to others in a more confident way.

And there are so many tools out there that I haven't even tried yet, but could speed things up 10x (think of sales automation software, accounting platforms, lead generation agents).

Traditionally, as a solo founder, you had to learn all these skills from scratch, which is - let's face it - impossible for a single person.

But with the help of these technologies, you can be a marketer, growth hacker, writer, sales rep, and programmer at the same time.

I have no idea, what is the final outcome of AI.

Will it help make the world a better place or will be the doom of humanity 😅?

But I believe right now it's a great opportunity for solo founders to achieve more on their own, which was never possible by a single person before.

[disclaimer: no AI help was involved in writing my opinions 😅]

I mean, everything pulls our attention in 5 million different directions, from flashy advertising banners to public transport announcements and having hundreds of people all around us, all at the same time.

We're living in dense buildings, sharing space with other people.

I'm not saying it's bad: living in cities is fantastic (that’s why most cities are growing), and I'm also a city boy.

But going out in nature, and touching grass still has a fantastic impact on our mind.

You might say: "hey, but I live in the center of the city, how would I be able to reconnect with nature?"

But the thing is, it's possible, you just need to be conscious about it.

Here are a couple of examples of what can help and how to do it.

Visit Nearby Parks

Every city is designed in a way that in between a concrete jungle, you can find small oases of nature: these are called parks, and even the most dense city has many of them.

Try to make it a habit to visit these parks: sit on a bench, have a picnic, read a book, listen to the birds, and just try to disconnect.

It's perfectly okay to go on your own. You can even leave your phone behind, and try to be in an environment where preferably you don't see the buildings surrounding the park, only green, like trees, grass, flowers, and local animals.

Make Your Home Green

The second thing that you can do is surround yourself with plants at home.

I'm not saying to become a plant lady, but have a couple of plants that you take care of.

It's also good for your mental health to have a feeling of responsibility, even if it's only for taking care of a couple of succulents. Adding a touch of green to your life can transform your mental health and have a positive impact on it.

And it's decorative, so it will add to your interior aesthetics 😉

Focus With Nature

Try to incorporate listening to nature sounds into your focus work time. Birds chirping and crickets cricketing (I don't know the name of the sound crickets make 😅) also trigger those calming effects that were developed throughout the millennia of human evolution.

You will notice how your mind slows down instead of ticking and you can focus better.

I mean, no surprise that all meditation apps have these nature sounds as available options because they just work.

Go on Nature Walks in the Gym

The next one is a very unconventional tip: when you go to the gym to do some exercises - when you're on the cardio machine: go on a nature walk. Most of these machines have screens built in and almost all of them let you watch naturewalks.

So while you're doing your elliptical or you're on the treadmill, instead of watching Netflix, try to slow down your mind.

You can take a virtual excursion to the Yosemite National Park or the Australian Outback.

You can visit exotic places this way: you're walking, so you're doing good to your body and you're watching nature at the same time.

And I promise you it has this surprising relaxing effect on your mind.

Escape for the Weekend

And finally, even if you live in a city, that's no excuse to not escape from the concrete jungle for a weekend, or whenever time allows.

Just hop on a bus or get in your car and leave the city behind. Just one hour and you can be in untouched nature with lush forests or beautiful fields.

Escaping from the city even only for a day can recharge you. One day of looking at the distance, being surrounded by green, and not distracting your mind with information flooding from five trillion different sources: just one day can already have a massive impact on your mental well-being.

So yes, it's awesome to live in the city, but be smart about it and connect with nature. Because in the end, that's where we're all coming from.

Photo by Joanna on Unsplash

But working a 9-5, in a cloudy place wouldn't give me much chance to bask in the sunshine. It just wasn't enough, so decided to engineer my life so I could have plenty of it 😎

My story

I did my uni studies in Denmark. Not famous for its good weather 😅

So right after I finished, I looked around Europe and moved to Spain (for being the sunniest country on the continent).

Best decision of my life 🤩

But I still worked from an office, so there was more engineering to be done.

Eventually, I found jobs that allowed me to work during the evenings, so I could spend my daytime as I wanted. Avoiding the rush hours, and living life at my own pace.

And again, years passed and now I manage to travel to the Northern Hemisphere for 1-2 months every winter, to get even more of what I like

Chasing the sun - quite literally.

Life Engineering

Knowing what you want in life sounds so obvious.

Yet, I find many people never think it through.

Identifying the things that make you happy and fulfilled should be your priority. Then you can start making adjustments in any area of your life until you get to the desired point.

It's a long process. It took me years, maybe a decade to get to where I am now. And it's a never-ending one, as there are always new things to add.

Easy? Most definitely not.

The things you truly desire in life might require big sacrifices: changing countries, the people around you, even a complete career shift.

But it's totally worth it.

But Johnny, I Can't Do It

Are we talking about excuses?

Of course, there are life situations that might make it more difficult. Seemingly impossible. But that's exactly what I'm talking about: it's not a short process with a magical outcome. It's a process of decades. You can get there at your own pace.

No matter your current life situation, you should be striving to improve it day by day. And that, everyone can do.

So How To Get Started?

Find what are the most important things to you, that bring true joy.

Start thinking: what could you do, how could you engineer your life so you can achieve them?

If you run into "but it's not possible": find out why, and how could you get over it. When you think about long-term goals, everything is possible.

It's a very long process, but rewarding.

And one day, you'll wake up in your perfectly engineered life, doing the exact things you love doing.

At that moment, all the work and sacrifices will be worth it.

(Photo by Patrick Robert Doyle)

When was the last time you were so deep into a project that hours flew by and time felt still? Or so absorbed in a book that you forgot to eat? You were in the flow state.

And that is where magic happens.

"Flow" - What?

Some call it being in "the zone."

Your deepest focus on a task or activity. When the world stops existing around you. Reading a gripping novel or getting lost in your work, it's just you and the task at hand. No room for worries or distractions.

It's an ecstatic state where your brain's chatter begins to fade away. Your mind stops wandering, and it's hyper-focused on your craft.

The Muse and the Flow

Steven Pressfield, in his book The War of Art, talks about summoning the muse.

The muse is your flow state—a magical force that helps you create without distraction. It’s not just for artists; it's for anyone who wants to produce their best work.

You don't need to wait for flow to happen by chance; with a few preparations, you can invite the muse and spark the flow state yourself.

Tips to Find Your Flow

1. Eliminate Distractions: Turn off notifications. Yes, all of them.

2. Choose the Time: Don't sacrifice the best hours of your day to respond to emails and run errands. They can wait. Your focus can't.

3. Create a Ritual: Have a specific setup or routine that signals it's time to work.

4. Focus on the Journey: Don't worry about the outcome of your work. Instead, concentrate on actually doing the work.

5. Mindfulness: Take a few deep breaths before starting. Clear your mind.

So the next time you want to get some deep work or creative activity done, just call for the muse and let the flow state take over.

(cover photo by Matt Hardy)

But it's best to know when to throw in the towel early, change course, and find alternative routes to your goals.

Here are 3 stories of "giving up" that moved me forward:

I thought I would never enjoy driving. However, to go hiking in the mountains, I needed to get better at it. But starting with the parking brake on a steep slope gave me anxiety. If you know, you know.

At one point, I just realized: it's a pointless self-torture. I don't need to learn how to drive a stick-shift car (which is the common way in Europe). I gave up on it, and since then I actually enjoy road trips with automatic cars.

My favorite fantasy book - Mistborn - has 7 books, and it takes place in two different eras. I was obsessed with the first 3 books, the storyline, and its universe. These books were the kind that you just can't put down.

But the 4th one started the new era, and I couldn't connect. Somehow it was off. But I kept reading it, giving it another chance day by day, until I was halfway in.

It was at that moment that I asked myself: "Why am I reading this? The whole point of reading fiction is to enjoy it". So with that, I gave up on finishing the saga, giving time and space for other books.

My previous startup was doing great when I quit. We had new customers, investors, potential to keep growing more and more.

But it also came with a lot of stress (not the kind that is sustainable for a long time) and a lack of freedom (I couldn't travel the world like I do now).

So after years of hard work, I just gave up, and left. Looking back, I waited even for too long.

But that's how the sunk cost fallacy works. We stick to ongoing activities, because we feel we already invested time/effort/money, and we don't want them to go to waste.

So here's my advice: when you notice that there's anything that's not giving you joy anymore: find your overall objective and see if you can get there by following different paths.

How?

By setting boundaries for my digital life.

On the second date with my (now) fiancé, we went to climb the hills of Barcelona.

It was a romantic walk: him, me...
and all the constant work notifications on my phone 😵

It buzzed up every minute with a Slack message or an email.
People were asking things from me - all urgently.

And I had to respond. Couldn't leave them waiting.

Are you familiar with this experience? When all the messages keep coming at the worst moment.

It was supposed to be our time, and not shared with colleagues, clients, or anyone else.

So I did what every over-dramatic person would do: I deleted my Mail and Slack on the spot, and put my phone into "Do Not Disturb" mode. And just forgot about it for the rest of the day 🧘‍♂️

It's been more than 5 years since then, and my phone is still unavailable to anyone except my mum, boyfriend, and two friends. It goes straight to voicemail.

I downloaded Mail and Slack again, but the apps are hidden in a folder, with all notifications turned off (even the little red dot).
So I can choose when to open them.

I'm not behaving reactively anymore to others' agenda.
Instead, I choose when to respond.
And I do respond, I promise, just not on the spot.

"Do Not Disturb" mode is the best invention since the selfie camera! 😜

So use it generously!

Because taking back the control over your availability is freakin' liberating.

(Photo by Jonas Lee on Unsplash)

But just because you woke up on the wrong side of the bed, it doesn't have to ruin your whole day.

I mean, in the grand scheme of things, our planet keeps spinning and it's not really a bad day. Only in your head 🧠

That's a good thing. It means, you also have the power to shift your mindset and turn it around!

Here are 8 tips, how:

Notice That You're Tense

As in any mindfulness practice, start by noticing your state. That you're uneasy, annoyed, grumpy.

You can't fix it unless you're aware of it.

Breathe

Really. A couple of conscious breaths can relax your body in less than a minute.

Combine it with a short meditation, if you prefer 🧘

Laugh at it

You know how you laugh in comedies when bad things happen to the characters? It's funny because it's happening to them, not you.

Well, now you're the main character, so laugh at your unfortunate situation 🤭

Set intention

Have a conversation with yourself that you're gonna turn your day around, and from now on it'll be awesome.
Do a little pep-talk in front of the mirror 🗣️🪞

Use gratitude

Chances are, even on your worst day you're more fortunate than many others. List in your head things that you're grateful for, and embrace them 🙏

Keep on adding to the list, and the bad mood will fade away.

Get out

Even if the weather is sh*t, you can still benefit from being outside. If possible, go for a little walk to recompile yourself.

Be kind to people

It often helps to snap out of a bad mood to talk kindly to the people around you.

Have small talks with the barista, your colleague, the security guard, and the cashier.

These quick interactions will fill you with positive emotions.

Dance

Some of movie history's best scenes are about the actors dancing on their own, in privacy, while nobody's watching.

It is sooo powerful to shift your mood. And you can do it literally anywhere.

Put on your favorite jam in your earphones, and have a mini silent disco party 🕺🪩

(cover photo by Amy Gatenby on Unsplash)

They are disciplined, adaptable, and always learning.

But I've noticed that the most successful solo founders, in particular, have this one habit in common:

Talking to customers

I have a theory on why:

Talking to customers 💬 helps solo founders build what users really need.

By engaging directly with their audience, indie hackers gain a constant stream of feedback and ideas.

This direct line of communication allows them to quickly pivot their project based on real user input, ensuring their product evolves in the right direction.

This habit also involves building a community around the product. Successful solo founders create strong relationships 🔗 with their customers.

That's the recipe for gaining loyalty and growing their products' fanbase - who can help spread the word.

In the end, talking to customers:

• reduces guesswork,

• maintains clarity, 

• and drives product development in the right direction,

turning a one-person operation into a thriving business.

This habit is the secret sauce 🥫 that often sets successful solo founders apart from the rest.

Well, connecting, for sure.

But conversations matter more, according to the book "Digital Minimalism" by Cal Newport. And we have a lot to improve in that area.

Connection vs conversation

Cal describes connections as interactions that occur through digital media. Such as liking 👍 someone's baby pictures instead of taking a visit.

Or commenting on a post, instead of giving a call.

They might seem like acts of kindness but are actually low-effort ways to keep up with others' lives without fostering a sense of true understanding or closeness.

On the other hand, conversation is a richer, more engaging form of communication. Conversation typically involves face-to-face 👥, uninterrupted dialogue where participants can pick up on non-verbal cues and invest more emotionally and cognitively. Newport argues that conversations are crucial for true relational depth and are much more fulfilling.

But we live in the XXI. century

So, of course, we should take advantage of modern technologies 🤳
Staying up-to-date with the lives of friends and family who live far away is easier now than ever.

When COVID hit, I got separated from my friends–even my boyfriend–for several months, but they could stay as part of my life, thanks to social media.

Just try to be very picky on how and with who do you connect.
And always prioritize richer communication forms, even if through a digital channel.

Pick up the phone, or make a video call. It will be much more fulfilling for both parties.

Don't treat connection as an alternative to conversation but as a supporter of it.

It's obviously not an ideal situation, and you should totally look for the underlying reasons.

But for now, I'm here to give you three quick stress-relief methods, that you can do, right now.

Take a step back and shift your body

Easier said than done. I know, I know.

But chances are, you're already spiraling, keeping yourself in a stressful mindset.

So please stand up and leave your computer for a few minutes.

• Move! Go out.

• Walk around your block.

• Do jumping jacks.

• Take a shower.

• Do a breathwork routine.

If you're already thinking: "Dude, what are you talking about!? 🙄 I'm overwhelmed with work. Going on a walk is the last thing I have time for"—think again!

I'm only asking for 10-minute breaks. It's the same time it'd take to prepare a coffee or (god forbid) smoke a cigarette.

Shifting your position and moving your body will clear your mind and release a lot of tension.

Look forward to the time when it's over

Soldiers are sometimes trained to visualize an end to their suffering, which helps them maintain their psychological health during difficult times.

Now, I trust you're not being physically tortured at work - even if it feels like that sometimes 😅.

If you're dealing with a particularly difficult task or an annoying project, try to define to yourself when will it be over.

Reassuring yourself that these stressful times won't last forever can immediately lift your mood and give you some hope to look forward to.

Remember, why you started

What causes this stressful situation is usually:

• the mismanagement of time,

• annoying colleagues,

• unexpected technical challenges,

• or a difficult client.

It's seldom related to what's in your job description, your craft.

So, try to focus on doing your best work, that once got you all so excited. 

See the good parts of it, and remember why you started doing it in the first place.

And if you say: "I'm in only for the money," that's BS, my friend. You could be doing a million other things, but somehow you still chose this, so there must be aspects of your job that you like).

---

Is the stressful situation ongoing?
Try to come up with a long-term strategy to change.

But in either case, there's no point in spending your days stressing out.

Your work has to be done either way, so why not try to do it with a little bit less anxiety?