JSNation is coming soon, and besides my talk (I’ll drop the link in the comments so I don’t spam you with it for the tenth time 😅), there are also discussion rooms. And somehow, I got invited to two of them.
Now, a normal person would probably stop for a second and think: “Do I even have time for this?”, “Is it worth it?”, “Should I maybe not overcommit myself for once?”. Meanwhile, in classic Sylwia fashion, I replied almost instantly: “Oh, that sounds amazing! Sure, sign me up for everything!” 😎
And that’s how I ended up in a discussion room called “The New Senior Engineer: Builder, Reviewer or Orchestrator?”.
Now, my career advisor, ChatGPT, always tells me: “Sylwia, please get your life together. And if you insist on doing ten things at once, at least reuse the content.” 😅 So instead of coming up with all the conclusions myself, I thought: why not ask the DEV community?
But before I ask the big question — what should a Senior Engineer become in the AI era — I think there’s another, more interesting one first: how are you actually using AI at work?
Not in conference demos. Not in viral Twitter threads. Not in “my AI agent rewrote Kubernetes during lunch” stories. I mean real work. Real projects. Real teams.
Of course, feel free to jump straight into the comments (you know I love talking with you all ❤️), but first, a few observations from my side.
AI Above Everything
At least that’s the image the internet gives us. Conference titles. Newsletter headlines. LinkedIn prophets.
Matteo Collina opens a 100k-line PR for Node.js and people panic.
Someone rewrites an entire React application to Svelte in two weeks. Hundreds of thousands of files.
The creator of Bun rewrites it from Zig to Rust in one evening, while casually mentioning he also went on a date that night. (Am I the only one getting weird associations here? 😅)
Armies of agents replacing development teams. Agents opening PRs for other agents to review. Everything automated. And somewhere in the middle of all this, the Senior Engineer becomes some kind of AI shepherd, occasionally checking whether the robots are heading straight into a cliff.
Honestly, it’s both fascinating and mildly terrifying. Sometimes it makes you wonder whether we should all reconsider our career choices and maybe sign up for hairdressing school before the robots learn that too 😅
But then I stop for a second and think: I actually work in this industry. I know a lot of developers. And real life often looks… very different.
From Excitement to Cost Optimization
A friend of mine works at a huge tech corporation. One of those companies you definitely know — and probably either love or hate 😄
Of course they started using AI tools very early, including Copilot. But things really escalated once they got proper coding agents — I think Claude Code.
At first, the company was completely mesmerized. They bought the most expensive plans possible and encouraged people to use AI aggressively. If someone hit token limits, management basically said: “Don’t worry, we’ll buy more. It’s revolutionary!”
My friend happened to be building a new application from scratch and honestly — he loved it. The amount of code generated was absurd. Normally, building something like that would take months with an entire team. Now? A few days and huge chunks of the system already existed.
And because he’s genuinely an excellent developer, he became very good at noticing the exact moment Claude started going completely off the rails. Interestingly, this often happened around 5 PM. Apparently the AI wanted to clock out too 😅
But after a few months, the excitement slowly started fading. Turns out that while AI sometimes makes development dramatically faster, it definitely doesn’t always.
And then came the second surprise: the company actually calculated how much all this AI usage was costing. Suddenly everyone discovered that — surprise, surprise — unlimited AI agents aren’t exactly cheap 😄
So now there are discussions about limits, optimization, and reducing token usage. At this rate, maybe hiring interns will eventually become the cheaper option again 😂
And honestly, we’re already seeing this trend more and more. Wasn’t it Meta that introduced some kind of “tokenmaxxing” culture where people were rewarded for using fewer tokens?
And Finally, My Own Story
Now let’s move to my world.
A massive international institution. An enterprise ship that takes three years to turn right. A place where privacy is treated almost like religion. So naturally, people were extremely skeptical about LLMs for a long time.
But eventually AI arrived there too, which honestly makes me think these tools are now basically everywhere 😄
So: do coding agents massively accelerate development in enterprise legacy systems?
Well… that’s where things become complicated.
Sure, there are tasks where AI is genuinely useful. Simple bugs. Small features. Boilerplate work. But on some tasks? It completely collapses.
The agent reads library code. It crawls through the application. It searches half the repository. And still somehow understands absolutely nothing 😅
Sometimes I literally have to tell it: “Maybe check that weird file written by a junior developer seven years ago.” Or: “Our UI library has some very specific legacy quirks, maybe investigate that direction.”
And honestly? After 2.5 years in this project, I’m simply faster than the AI agent in many debugging scenarios.
Not because I’m smarter. Not because AI is useless. But because enterprise systems accumulate context, history, weird decisions, tribal knowledge, hidden dependencies and architectural scars over many years. And I have that context. The AI usually doesn’t.
And I honestly doubt my project is unique here. A huge percentage of software running the world today is enterprise legacy that survived far longer than anyone originally planned — and is still actively evolving 😄
So maybe, somehow, I’ll actually survive as a programmer until retirement after all. And maybe I won’t need to learn hairdressing.
Which is probably good news for humanity, because I’d be terrible at it 😅
But now I’m genuinely curious: what does AI usage actually look like in your work?
Million-line AI PRs? Daily battles with legacy systems? Token optimization? Or maybe something completely different?
BTW, If you like my posts, feel free to follow me on Linkedin!
Top comments (235)
The greenfield vs legacy split lines up with what I see in consulting. The actual breakpoint isn't 'legacy code', it's 'code where the why was never written down'. Even modern codebases hit this within 18 months. AI doesn't fail because the code is old, it fails because the assumptions are unwritten and the original author has moved on. Which makes AI productivity at any company a leading indicator of how good the documentation discipline was three years ago.
I think this tracks. I think good specs and relatively good patterns overall are good enough here. You don't strictly need documentation, but you need a decodable "why" in general.
Interesting to see what vibe-coded codebases become over time in this regard.
Honestly, I’m actually pretty pessimistic about some of those vibe-coded apps. Sometimes I see the kind of things agents come up with, and the terrifying part is that they technically work.
At this rate, “vibe-code cleaner” might genuinely become a very well-paid profession in a few years 😄
And I’m genuinely curious what this looks like inside DEV itself though! Since it’s open source, do you already have "armies of agents" everywhere, or is it still more of a "everyone uses whatever works for them" situation?
Oh yes, absolutely! And honestly, I’m not even sure coding agents will improve this situation that much.
Sometimes they also introduce weird decisions or random abstractions, and if nobody stops to ask “wait… WHY are we doing this?”, that stuff just stays in the codebase forever.
And of course developers have been collectively crying about writing documentation since the dawn of civilization 😂
Plus exactly what you said: every team always starts with noble dreams like “this time we’ll keep the architecture clean and document everything properly”, and then 18 months later the project somehow becomes legacy again 😄
There's actually one thing agents can do that humans rarely do consistently: force the rationale into writing before the diff lands. A pre-merge agent that refuses 'why-less' changes turns the 18-month drift into something measurable. Not magic, just discipline at scale.
Honestly, this feels like a much more realistic vision of AI in software engineering than the whole “AI will replace all developers” narrative 😄
I can absolutely imagine agents consistently enforcing things that humans are notoriously bad at: documenting rationale, explaining assumptions, writing down architectural decisions, keeping conventions aligned, etc. An agent that does this relentlessly, without getting tired, without cutting corners and without the classic “ehhh, I’ll document it later” mentality could actually be incredibly useful 😂
Valentin, I have compiled an ebook exactly on some of the challenges with AI vibe coding... I will highly appreciate if you kindly read a chapter or the full book (120 pages) and give your feedback.
Hey, may I partake in this excercise?
If you're interested in my talk at JSNation, you can register here and watch it for free 😊
Here it is
The talk is called “Rewrite or Refactor? How to Safely Move Legacy Apps to Modern Frameworks” 🚀
I wrote a short post about the same topic a few months back: How Much AI-Generated Code Are We Actually Shipping to Production? My Reality So Far and my experience is very similar.
For older codebases, AI often isn’t that useful because understanding the system matters more than generating syntax.
In newer codebases, though, AI works much better when the architecture is already well established and best practices are being followed. In those cases, it can generate similar code that fits the existing solution quite well. Usually, it gets me about 85% there, and I fix the remaining 15% myself.
And then there’s the third category: hobby projects. There I use AI for almost everything 😅
But we’ll see how token costs evolve over the next few months. Maybe even hobby projects will push me back toward good old manual programming 😂
This is a fantastic post, and honestly, everything you describe fits together into a very logical pattern.
And yes, I totally agree about hobby projects too. That’s where Anthropic servers start catching fire 🔥😂 In personal projects I use AI for almost everything.
Although… I already noticed my own behavior changing a bit because of token costs 😄 A few months ago I would happily generate even boring boilerplate through an agent. Now I sometimes catch myself thinking: “You know what, the old-school CLI command is probably cheaper and faster here.” So maybe I’m already adapting to the token economy and it won’t be that bad after all 😂
And btw, I’ll actually be in the Czech Republic in October for FrontKon, so you should slowly start preparing a list of good Czech beers for me 😄
Yep, I think we’re now entering the phase where people will start learning how to use tokens more efficiently and maybe the whole AI bubble will stabilize a bit because of that.
And nice! As the leading country in beer consumption, the list of good Czech beers could get very long 😄 Not sure the DEV comment section is big enough for that 🤣
Apparently we’re already reaching peak absurdity, because I recently heard about LLMs being used to improve prompts so that other LLMs consume fewer tokens 😂 The ecosystem is slowly evolving into AI agents optimizing other AI agents.
And yes, Czech beer absolutely rules! Unlike those mysterious dumplings (knedliki) you people keep trying to convince the world are food 😂 Although to be fair, the calories saved by avoiding knedliki can then be responsibly re-consumed in the form of vitamin B-rich Czech beer, so the nutritional balance eventually restores itself 😎😂
Agreed, it’s getting ridiculous.
Oo, so you’re already an expert 😄 Knedlíky are the best side dish! Especially with goulash or svíčková, and after that, 3–4 Czech beers… that’s perfection 👌😆
And calories? Well, in the Czech Republic, you’d rather not count them when it comes to food and beer 😅 But I think it’s similar in Poland 🤣
Hahaha ok, I admit, with beer, knedlíky might actually make sense after all 😄
But wait… is fried cheese yours or the Slovaks’? Because THAT is the real masterpiece 😂 Absolute peak Central European engineering.
Ok, you’re truly an expert 😄
Honestly, I don’t know, it’s famous in both countries.
I couldn’t agree more, a true masterpiece of Central European engineering 🤣🤣
Exactly 😄 Cooking is just another branch of engineering. Sometimes with better documentation than enterprise software 😂
Go with some of the best free provider options via
Kilo Code
Cline
BlackBox AI
Thanks Ranjan 😄 For personal projects and home setups, those tools definitely look worth trying.
But you know how enterprise corporate environments work 😂 There’s basically zero chance of developers just installing random AI tooling on their own. Everything needs to be approved by security, architecture boards, compliance, probably three managers, and ideally preceded by a thousand meetings first 😅
I am totally with you on the enterprise corporate environments work
You still have this knack for writing a captivating article, whatever the topic—well, I suppose there are limits, but they're a bit like the horizon, receding as you go. Your examples are fascinating, and your story is no less so.
I agree with your observations: AI is a mindless accelerator… it allows you to code quickly and reasonably well—provided you know how to code yourself, and especially how to architect. But at the first sign of trouble, it's completely lost, it's not at a beginner's level, and solving the problem myself is far faster than asking it to fix it.
Okay, I'm not an experienced AI user, and I'm not comfortable with autonomous coding agents; I mainly use Claude and the GitHub Copilot CLI. It allows me to be more productive, but I have over 20 years of coding experience…
Thanks, Pascal! 😄
And yes, I think you're absolutely right. Senior engineers often get a huge productivity boost from AI because they already have the architecture knowledge, patterns, and debugging instincts to guide it.
What surprises me is that juniors don't always seem to benefit nearly as much. At least from what I see day to day, the gains are much less obvious there 😉
Instinct – there you have it, you've said it all… instinct and experience. And it's not so surprising that a junior makes less use of it; they're still in the learning phase, and they're using a tool that's also still learning. But while they can learn from their mistakes, an LLM, on the other hand, is stuck in their learning process – they won't get better with time – all we can do is optimize its use.
I used to worry about that too: juniors relying so heavily on AI that they would stop learning altogether.
But lately I've seen examples of the opposite. A friend of mine works as a business analyst and wanted to get into programming as a hobby. He quickly noticed the gaps in his understanding and is now taking a C++ course from scratch, that costs 3 Euro per month...
So maybe motivated people will still learn the fundamentals anyway. AI can make things easier, but it can't create curiosity or discipline for you.
Google Translate kind of betrayed me on that one 😅
What I originally meant was that AI, no matter how advanced it gets, doesn’t replace human learning. A junior improves by making mistakes, identifying gaps, and building real experience over time — whereas a LLM doesn’t “grow” from usage in that sense. It stays a tool we can optimize, but it doesn’t develop understanding through time and practice.
And I do agree with your point: motivated people will keep learning the fundamentals anyway. AI can definitely speed things up and lower friction, but it can’t replace curiosity or discipline — and those are what really matter in the long run.
I've started running scheduled scripts to elevate the most mergeable and most lwo-hanging-fruit closeable PRs which I can then gut check and look into more so I can more easily deal with the contributions at either end of this spectrum to get them out of the way to focus on the middle chunk of more nuanced PRs.
That actually sounds super sensible! And I guess it also means there won’t be a single gigantic PR rewriting the entire platform into Rust/React/Svelte (delete as appropriate) anytime soon 😂
At work, I am mostly the person saying, "let's not use LLMs for this, it's a terrible idea because..."
I have two current code projects, and one I'm doing myself, the other I'm using Opencode for. The Opencode one is significantly worse and requires me to step in and rescue it a lot. I also have to keep asking it to explain what it thinks it's done, and to tidy up things that are left behind and to not keep reinventing the wheel. Oh, and I have to start every session with, "for the love of god do not use tailwind this time".
What I am using AI for is asking questions about code, and for admin tasks like creating a changelog from the git history of a project and linking it all up with Jira, that sort of thing. I mean, you still have to spend time making sure it's not coming out with something that's actually bonkers batshit but it does save a lot of time overall for those sort of chores.
This matches very closely with what I’ve been seeing too: context is the key thing here, and no agent or model is really a silver bullet.
My experience with coding agents is very similar. They work best for relatively simple, well-scoped tasks like: “add a small feature HERE and HERE”, “split this component into smaller ones”, “generate some boilerplate”, etc. And honestly… even there they sometimes manage to completely derail themselves 😅
And BTW, as you already know, I actually like throwing Tailwind into hobby projects 😄 But I usually have to explicitly ask for it, and specify the exact modern version too, otherwise the agent starts building some terrifying spaghetti CSS monster inside a random global.css file 😂
The gap between the AI marketing hype and actual daily engineering reality is massive, and this post cuts right through it.
Most companies think developers are using AI to magically build entire features from scratch, but the real day-to-day utility is much more mundane and practical. It’s about offloading the cognitive overhead of boilerplate code, writing regex, or quickly translating syntax between languages. It hasn't replaced the core engineering mindset; it just speed-runs the tedious bits so we can spend more time on actual system architecture and problem-solving. Great reality check on how the tools are being used in the wild.
Exactly! That's one of my favorite use cases for coding agents as well 😄
I love not having to fight with boilerplate anymore. But before that boilerplate even gets written, there's usually a lot of work around understanding requirements, aligning with stakeholders, making architectural decisions, and figuring out what should actually be built in the first place.
AI speeds up implementation. It doesn't magically remove all the work that happens before it.
Developers are using AI less like a replacement and more like a second pair of hands. Drafting code, explaining errors, writing tests, reviewing logic, and cleaning up repetitive work. The real value still depends on whether the developer can judge the output.
That’s honestly my impression too. I mostly wanted to figure out how many of those mythical “armies of autonomous agents” actually exist in real-world development versus how much of it is just LinkedIn storytelling 😂
Exactly. The “army of agents” thing sounds good online, but most real teams are still using AI in much smaller ways. Draft this, explain this error, write a test, clean this function, review this logic. Useful, but not fully autonomous magic.
These stat based mammoth brute force machines are pretty good at generating demos, MVPs, small script tools and all sorts of slop content, but they are pretty bad at Software Engineering and doing consistent serious software development. That's all I can say for now.
Hahaha honestly, most of the comments here are basically saying exactly the same thing, just in a slightly less brutal way 😂
My take: You certainly don't have to go learn hairdressing 🤣 but you could still do better than an AI 🤐.
Okay for me as a researcher from day 1, i'd always refine searches when I need something even when I began using Google I sometimes click next upto page 24 after adding as much details as possible including file extensions.
I'm 2026 the research habit payed off when using AI assistants I get results faster than going through 24 pages 😂.
That’s actually a really interesting observation, and honestly, probably very true 😄 Good prompting is clearly becoming a huge skill on its own.
Now I’m curious though: how does this help you most in your actual work? Mainly for research and finding information faster, or does it also translate into giving much better prompts and directions to coding agents themselves?
I don’t see an 'AI'—I see an advanced Google, an improved computer. I don’t trust it with my life; I just know it’s faster than what I had in 2006. The answers aren't 'innovative' or 'perfect,' they’re just better filtered. My research habit is simply how I handle the filter so I get the signal without the noise.
For hallucination - Hallucination isn't something I 'prompt' away. It's something I manage. When I'm in my element, I supervise; when I'm in new territory, I research. My 'prompting' skill is really just the ability to synthesize my own research into a constraint set that the AI can't easily break.
I really like that part about “I don’t prompt hallucinations away. I manage them.”
That honestly feels like a much more realistic mindset than expecting AI to magically become perfectly reliable. More like… controlled chaos engineering for knowledge work 😂
Some comments may only be visible to logged-in visitors. Sign in to view all comments.