Thursday, November 27, 2025
HomeStartupThe Finest Engineers Aren’t Writing Code Anymore — And That’s Precisely How...

The Finest Engineers Aren’t Writing Code Anymore — And That’s Precisely How It Ought to Be | by Jano le Roux | The Startup | Oct, 2025


AI didn’t kill coding. It killed the boring components.

Press enter or click on to view picture in full measurement

Claude Code and Zed Code Editor icon.
Illustration by creator.

I’ve been coding since I used to be 12.

Began with Weebly. Then HTML. Then CSS. Then JavaScript. Then Swift. Then no matter else I wanted to construct no matter silly concept popped into my head that what

For years, I believed being a superb developer meant memorizing syntax, debugging for hours, and Googling Stack Overflow solutions at 2 AM.

I used to be fallacious.

The most effective engineers I do know right now barely contact their keyboards.

They assume. They architect. They dream.

And AI does the remainder.

The demise of the code monkey

Final week, I watched a 19-year-old faculty dropout construct a completely purposeful SaaS product in 72 hours.

No workforce. No traders. No senior builders wanting over his shoulder.

Simply him, his laptop computer, and Claude Sonnet 4.5.

He described what he wished. Claude wrote the code. He examined it. Claude fastened the bugs. He deployed it.

Two weeks later, he had 200 paying clients.

This could have taken a workforce of 5 engineers six months to construct simply three years in the past.

Now it takes one particular person with a transparent imaginative and prescient and a weekend.

The foundations modified in a single day — and most of the people haven’t seen but.

Right here’s what really issues now

You don’t must memorize each JavaScript technique anymore.

You don’t must spend 4 years getting a pc science diploma.

You don’t must grind LeetCode issues till your mind doesn’t mind anymore.

What you want is easier — and tougher.

You should perceive how programs work.

You should know what’s doable.

You should clarify your imaginative and prescient clearly sufficient that an AI can construct it.

The engineers successful proper now aren’t those who can write the cleanest code. They’re those who can assume by means of issues, perceive structure, and talk what they need.

They’re the conductors — not the orchestra.

Its creativeness science.

The instruments that made this doable

Claude Code modified how I work greater than any instrument within the final decade. It’s a command-line interface that lets Claude write, debug, and deploy code immediately out of your terminal. You describe what you need. It builds it. You overview it. Ship it.

I’ve been bothered by a terminal awakening.

The second I requested it to scrub up a few of my outdated code, I knew it is a new stage of AI. It blew me away. What I couldn’t get proper in 100 prompts, it fastened in a single immediate. What I couldn’t get proper in 100 prompts it fastened in a single immediate. Similar to that.

It’s so out of this world f*cking good. Its so f*cking stunning to see the way it thinks.

Google CLI introduced related magic to Google’s Gemini mannequin to principally do the identical concept — AI that writes production-ready code out of your terminal.

OpenAI Codex powers GitHub Copilot and a dozen different instruments. It’s the engine behind most AI coding assistants you’ve most likely used with out realizing it.

Droid took it additional. It doesn’t simply write code — it understands your complete code doesn’t It suggests architectural enhancements. It refactors legacy legacy. It principally turns into your complete engineering workforce.

These aren’t toys. They’re manufacturing instruments that actual corporations use to ship actual merchandise.

The brand new breed of code editors

Writing code in VS Code began feeling outdated six months in the past.

Not as a result of VS Code is unhealthy. As a result of one thing higher emerged.

Cursor turned my every day driver nearly instantly. It’s not only a code editor with AI bolted on to it. It’s designed from the bottom up round AI help. You’ll be able to spotlight code and ask it questions. You’ll be able to describe options and watch them seem. You’ll be able to debug by having a dialog.

It feels much less like writing code and extra like having a technical co-founder.

Zed is my new obsession. It’s free. It’s quick. It’s stunning. And it helps you to convey your individual API keys — which suggests you’re not locked into some subscription mannequin the place you’re paying per keystroke.

I run it with Claude Sonnet 4.5, and it’s the closest factor to magic I’ve skilled in software program growth.

Press enter or click on to view picture in full measurement

Bar chart comparing AI model accuracy on the SWE-bench Verified software engineering test. Sonnet 4.5 leads with 82.0% (77.2% without parallel compute), followed by Opus 4.1 at 79.4%, Sonnet 4 at 80.2%, GPT-5 Codex at 74.5%, GPT-5 at 72.8%, and Gemini 2.5 Pro at 67.2%.
Anthropic

These editors don’t change pondering. They change typing.

And that’s precisely the purpose.

The one-person startup is now a actuality

One thing fascinating is occurring in tech proper now.

Firms that used to want 10 engineers now makes use of one engineer.

Merchandise that took months to construct now take days.

MVPs that price $50K to develop now price $0 and a weekend.

I’m watching solo founders construct and ship merchandise that seem like they got here from well-funded startups. Stunning interfaces. Advanced backend logic. Fee processing. Consumer authentication. E-mail notifications. The works.

One particular person. One imaginative and prescient. One mind.

The bottleneck isn’t technical capability anymore. It’s creativeness.

  1. Are you able to image what you need to construct?
  2. Are you able to describe it clearly?
  3. Are you able to assume by means of edge instances and person flows?

If sure, you possibly can construct it.

The hole between concept and execution collapsed.

Why understanding fundamentals nonetheless issues

Right here’s the place folks get confused.

AI didn’t make coding information out of date. AI It made it extra invaluable.

The builders who perceive how databases work, how APIs join, how authentication flows, how servers scale — they’re those utilizing AI most successfully.

They know what to ask for. They know when the AI is working. They know the way to information it towards higher options.

Those who skip studying fundamentals battle. They’ll’t consider the code AI generates. They’ll’t debug when issues break. They’ll’t architect programs that scale.

You don’t must memorize syntax anymore.

However you completely want to grasp how software program works.

Regardless that I hate the truth that I needed to spend hours and hours and days and sleepless nights debugging code on Stack Overflow. That I nonetheless went by means of that to grasp precisely how code works.

You don’t must know the way to combine concrete to design a constructing. However you higher perceive load-bearing partitions, basis necessities, and structural integrity.

AI is the concrete mixer. You’re nonetheless the architect.

The optimist’s view

I’ve by no means been extra enthusiastic about expertise.

Not as a result of AI is spectacular — although it’s.

As a result of it’s democratizing creation in a manner nothing else has.

The child in rural India with a laptop computer and web can now construct merchandise that compete with Silicon Valley startups.

The designer who at all times had product concepts however couldn’t code can now ship them.

The entrepreneur with area experience in some area of interest trade can construct customized software program with out hiring a dev workforce.

The barrier to entry collapsed.

And meaning one of the best concepts win — no matter who has them or the place they arrive from.

That is stunning.

My present setup

I spend most of my time in Zed as of late.

Claude Sonnet 4.5 handles the heavy lifting. I describe options in plain English. It writes the code. I overview it. Make changes. Ship it.

My workflow appears to be like nothing prefer it did two years in the past.

I’m not Stack Overflow-ing syntax errors. I’m not debugging for hours. I’m not preventing with package deal managers.

I’m fascinated with person expertise. About enterprise logic. About what issues want fixing and the way to resolve them elegantly.

The grunt work disappeared.

What’s left is the artistic work — the half that really issues.

The longer term is already right here

5 years from now, we’ll look again at 2025 because the turning level.

The second when software program growth stopped being about typing and began being about pondering.

The second while you didn’t want a pc science diploma to construct world-class merchandise.

The second when one of the best concept gained — not the largest engineering workforce.

We’re residing by means of it proper now.

I really feel so extremely fortunate to be alive throughout this awakening of a brand new period. That is a lot greater than something we’ve ever seen earlier than.

  • The automobile. Folks can drives from A to B.
  • The pc. Folks can sort A to B.
  • The web. Folks can talk information from A to B.

AI means to me, should you can think about it, you possibly can create it.

Each morning, I get up and take into consideration what I can construct. Not what I understand how to code.

Whereas standing within the bathe, it seems like concepts roll over me like drops of water. I can’t assist pondering of the music A Million Desires by Benj Pasek and Justin Paul carried out by P!nk:

I shut my eyes and I can see
A world that’s ready up for me
That I name my very own
Via the darkish, by means of the door
Via the place nobody’s been earlier than
But it surely seems like dwelling

They’ll say, they will say all of it sounds loopy
They’ll say, they will say I’ve misplaced my thoughts
I don’t care, I don’t care, so name me loopy
We are able to stay in a world that we design

As a result of creativeness is the one bottleneck left.

The brand new definition of an excellent engineer

The engineers I love most right now aren’t those writing probably the most code.

  • They’re those fixing the toughest issues.
  • They’re those pondering by means of edge instances earlier than writing a line.
  • They’re those architecting programs that scale.

They’re those asking the proper questions.

Code is simply the implementation element.

AI handles implementation particulars very well.

What AI can’t do — not less than not but — is dream up what ought to exist.

That’s nonetheless on us.

And that’s precisely the way it ought to be.

So what do you do now?

In the event you’ve been laying aside studying to code as a result of it appeared too exhausting — begin right now.

Not by memorizing syntax. By understanding programs.

Learn the way databases work. Learn the way APIs join issues. Learn the way authentication retains customers protected. Learn the way servers deal with site visitors.

Then seize Cursor or Zed. Fireplace up Claude. And begin constructing.

Describe what you need. Let AI write it. Study from what it creates.

One of the best ways to be taught coding in 2025 isn’t by means of tutorials.

It’s by means of constructing with AI as your pair programmer.

We’re simply getting began

The instruments I described? They’ll be out of date in six months.

One thing higher is coming. One thing sooner. One thing smarter.

This isn’t the height. That is the start.

And that’s what makes it so thrilling.

We’re watching a elementary shift in how people create software program.

  • From typing to pondering.
  • From implementation to creativeness.
  • From code monkeys to architects.

The most effective engineers aren’t writing code anymore.

They’re dreaming greater than ever earlier than — and AI helps them construct these goals.

I can’t wait to see what we construct subsequent.

RELATED ARTICLES

Most Popular

Recent Comments