Software Engineering is back

Coding agents have replaced every framework I used

I don’t post a lot. But when I do, it’s because I think few people are saying out loud what I’m noticing.

I’ve been building a product from the ground up. Not the “I spun up a Next.js template” kind of ground up. I mean from network configuration to product design to pricing decisions. Truly end to end. And I’ve been doing it using frontier models and coding agents for hours and hours every single day, both on this project and in my full time work. I’ve been trying to stay away from the chaos and the hype, filtering hard for what is actually valuable.

Since December 2025, things have dramatically changed for the better. Many have noticed. Few are drawing the right conclusions.

Automated Programming

Antirez likes to call it “automated programming”, and I really like that framing. It captures the essence far better than the shallow, almost dismissive label of “vibe coding”. Automation was at the core of most of the work and cultural revolutions of human history. The printing press, the loom, the assembly line. This one doesn’t differ much.

Most of my work is still there. I still have to deeply think about every important aspect of what I want to build. The architecture, the trade offs, the product decisions, the edge cases that will bite you at 3am. What’s gone is the tearing, exhausting manual labour of typing every single line of code.

At this point in time, models and tools, when put in a clean and maniacally well set up environment, can truly make the difference. I can be the architect without the wearing act of laying every single brick and spreading the mortar. I can design the dress without the act of cutting and sewing each individual piece of fabric. But I can do all of this with the experience on my back of having laid the bricks, spread the mortar, cut and sewn for twenty years. If I don’t like something, I can go in, understand it and fix it as I please, instructing once and for all my setup to do what I want next time.

Automated programming especially allows me to quickly build the tools I need so fast that every blacksmith that ever existed on this earth would envy me deeply. Finally able to really focus on the things they have in mind. Finally dedicating more time of their craft to the art they conceive, not the sweat of the forge.

Epiphany

It’s been months now that I have this thought crystallized in my mind. It is so clear to me that I genuinely don’t understand why everyone is not screaming it to the world.

We can finally get rid of all that middle work. That adapting layer of garbage we blindly accepted during these years. A huge amount of frameworks and libraries and tooling that has completely polluted software engineering, especially in web, mobile and desktop development. Layers upon layers of abstractions that abstract nothing meaningful, that solve problems we shouldn’t have had in the first place, that create ten new problems for every one they claim to fix.

Think about what happened. We, as an industry, looked at the genuine complexity of building software and instead of sharpening our thinking, we bought someone else’s thinking off the shelf. We wrapped everything in frameworks like wrapping a broken leg in silk. It looks nice. The leg is still broken.

The three problems frameworks solve (or claim to)

In my mind, besides the self declared objectives, frameworks solve three problems. Two explicit and one obvious but never declared.

“Simplification”. Software engineers are scared of designing things themselves. They would rather accept someone else’s structure, despite having to force fit it into their product, rather than taking the time to start from the goal and work backwards to create the perfect suit for their idea. Like an architect blindly accepting another architect’s blueprints and applying them regardless of the context, the needs, the terrain, the new technological possibilities. We decided to remove complexity not by sharpening our mental models around the products we build, but by buying a one size fits all design and applying it everywhere. That is not simplification. That is intellectual surrender.

Automation. This is the only point I can actually, more or less, understand and buy. Boilerplate is boring work. I hate it. And I especially hate using libraries that I then need to study, keep updated, be aware of vulnerabilities for, just for the purpose of removing the creation of duplicated but necessary code. Think about ORMs, CRUD management, code generation, API documentation and so on. The grunt work that nobody wants to do but everybody needs done. Fair enough. But hold that thought, because this is exactly the point where everything changes.

Labour cost. This is the quiet one. The one nobody puts on the conference slide. For companies, it is much better having Google, Meta, Vercel deciding for you how you build product and ship code. Adopt their framework. Pay the cost of lock in. Be enchanted by their cloud managed solution to host, deploy, store your stuff. And you unlock a feature that has nothing to do with engineering: you no longer need to hire a software engineer. You hire a React Developer. No need to train. Plug and play. Easy to replace. A cog in a machine designed by someone else, maintaining a system architected by someone else, solving problems defined by someone else. This is not engineering. This is operating.

Software Engineering Is Back

In my opinion Software engineering, the true one, is back again.

I am not speaking out of my lungs only. I’ve been developing this way almost flawlessly for over two years at this point. But the true revolution happened clearly last year, and since December 2025 this is obvious to anyone paying attention. From now on it will be even more so.

We have the chance again to get rid of useless complexity and keep working on the true and welcome complexity of our ideas, our features, our products. The complexity that matters. The complexity that is actually yours.

Automation and boilerplating have never been so cheap to overcome. I’ve been basically never writing twice the same line of code. I’m instantly building small tools I need, purpose built, exactly shaped around the problem at hand. I don’t need any fancy monorepo manager. A simple Makefile covers 100% of my needs for 99% of my use cases. When things will get very complicated, and if they get very complicated, I’ll think about it. But only then. Not a second before. This is engineering. You solve the problem you have, not the problem someone on a conference stage told you that you’ll eventually have.

Agents are really well prepared when it comes to basic tools. Tools that have been around not for months, but literally for decades. Bash was born in 1989, just preceding me by two months. The most mediocre model running at this time knows bash better than any person in the world. Bash is the universal adapter. It is not a coincidence that coding agents are shifting from complex and expensive MCP configurations to a simple agent loop with bash as a way to interact, literally, with the world. The oldest tool turned out to be the most future proof. There’s a lesson in there if you care to listen.

Think about it

Really think about it.

Why do you ever need, for most of the use cases you can think of, a useless, expensive, flawed, often vulnerable framework, and the parade of libraries that comes with it, that you probably use for only 10% of its capabilities? With all the costs associated with it. From the “least” expensive: operational costs like keeping everything updated because they once again found a critical vulnerability in your Next.js version. To the most expensive one: the cost to your Design Choices. The invisible cost. The one you pay every day without even realizing it, because you’ve been paying it so long you forgot what freedom felt like.

If you keep accepting this trade off, you are not only losing the biggest opportunity we’ve seen in software engineering in decades. You are probably not recognizing your own laziness in once again buying whatever the hyperscalers have decided for you. You’re letting Google and Meta and Vercel be your architect, your designer, your thinker. And in exchange, you get to be their operator.

The tools are here. The models are here. The revolution already happened and most people are still decorating the old house.

Stop wrapping broken legs in silk. Start building things that are yours.