{"slug": "what-is-20-years-of-coding-experience-worth-now", "title": "What is 20 years of coding experience worth now?", "summary": "A front-end developer with 20 years of experience, primarily in Angular, reflects on how AI has transformed his workflow, shifting from manual coding to directing AI through plain English. He argues that while AI can write code, his experience remains crucial for evaluating whether the code is correct, fitting the architecture, and anticipating future issues. He finds that keeping tasks small and reviewing AI output closely is the most effective approach, making him more thorough and productive.", "body_md": "I’ve been a front-end developer for more than 20 years now. For the last decade or so, most of my work has centered around Angular. I’ve spent a huge part of my career learning how to write better code, debug faster, understand architecture, recognize patterns, and generally become a more capable developer.\n\nFor a long time, that experience felt like a pretty clear advantage.\n\nNow I’m not so sure what that advantage is supposed to look like.\n\nAI has changed the way I work enough that I sometimes find myself wondering what 20 years of coding experience is actually worth when so much of the coding itself can now be done for me.\n\nAnd depending on the day, I can feel really excited about that or pretty uneasy about it.\n\nOne of the strangest changes for me is that I rarely spend much time manually writing code anymore.\n\nMost of the time, I’m essentially coding in plain English.\n\nI’ll explain what I want to accomplish, let AI take a pass at it, review what it produced, and then continue refining it through conversation.\n\nA few years ago, I probably would’ve hated that idea.\n\nI used to enjoy being the person who could sit down and build something by hand. There was a certain satisfaction in knowing the APIs, understanding the framework, and being able to turn an idea into working code myself.\n\nIf I’m being completely transparent, I probably took some pride in feeling like I was better at that than a lot of other developers.\n\nAI has changed that feeling quite a bit.\n\nThe interesting part, though, is that I don’t feel like my experience has become useless.\n\nI feel like I’m just using it differently.\n\nThe AI can write the code.\n\nWhat it can’t consistently do, at least in my experience, is know whether the code it wrote is actually the right code.\n\nThat’s where the experience still matters.\n\nWhen AI gives me an implementation, I’m constantly evaluating it.\n\nDoes this fit the architecture?\n\nIs this solving the actual problem?\n\nDid it introduce unnecessary complexity?\n\nIs there already something in the codebase we should be using?\n\nWhat else does this change affect?\n\nIs this going to create a problem six months from now?\n\nThose questions aren’t really about syntax.\n\nThey’re about judgment.\n\nAnd a lot of that judgment comes from years of building things, breaking things, maintaining things, refactoring bad decisions, and learning what tends to work in real applications.\n\nIn that sense, AI hasn’t made my experience irrelevant.\n\nIt may actually be forcing me to rely on the parts of that experience that matter most.\n\nI’ve also found that the way I use AI matters a lot.\n\nI see plenty of demos where someone gives an agent a large feature, walks away, and comes back to a finished implementation.\n\nThat hasn’t really been my experience.\n\nWhat works best for me is keeping the tasks small.\n\nI’ll give AI one focused piece of work, review it, make sure it’s right, and then move on to the next piece.\n\nIn a lot of ways, it’s not that different from how I would have built the feature myself.\n\nI’m still thinking through the structure.\n\nI’m still deciding what should happen next.\n\nI’m still controlling the direction.\n\nThe difference is that AI is doing much more of the implementation work along the way.\n\nThat workflow has been surprisingly effective for me.\n\nIt’s faster, but more importantly, it can make me more thorough.\n\nSometimes I’ll ask AI to refactor something and it’ll notice another related area that needs to change that I might not have remembered immediately.\n\nThat part is genuinely useful.\n\nI’m not suddenly 100 times more productive, but I can definitely get more done.\n\nAnd in some ways, I actually enjoy the work more now.\n\nThe closest comparison I can make is that working with AI sometimes feels like working with an incredibly fast junior developer.\n\nYou explain what you need.\n\nIt goes off and does it almost immediately.\n\nThen you look at what it came back with and say:\n\nNo, not quite.\n\nLet’s do this differently.\n\nDon’t add that.\n\nUse this pattern instead.\n\nYou send it back, and a few seconds later it returns with another version.\n\nThat’s incredibly powerful.\n\nBut it also explains why I still don’t feel comfortable handing over large parts of a production application and simply trusting the result.\n\nThe speed is there.\n\nThe judgment isn’t always there.\n\nThis is one area where I still feel like I might be missing something.\n\nI see developers talking about multi-agent environments, autonomous coding workflows, and handing entire features over to AI.\n\nI’ve tried versions of that.\n\nUsually, I end up with a massive code review.\n\nThe AI touches more things than I expected. It makes architectural decisions I wouldn’t have made. It introduces abstractions I don’t necessarily want.\n\nAt that point, figuring out whether everything is correct can take longer than I expected.\n\nSo for now, I keep coming back to smaller, controlled iterations.\n\nMaybe that changes.\n\nMaybe other teams have already figured out much better agent workflows than I have.\n\nIf that’s you, I’d genuinely like to know what you’re doing differently.\n\nWhat tools are you using?\n\nHow much context are you giving the agents?\n\nHow much review is still required afterward?\n\nAnd are you really trusting these systems with large production features?\n\nI’m interested in the workflows people are actually using every day, not just the ones that make for an impressive demo.\n\nRight now, I think we do.\n\nBut I also think the reason we matter is changing.\n\nBeing able to write code quickly may become less valuable.\n\nKnowing what should be built, how it should fit together, whether the implementation is good, and what risks are hiding inside it may become much more important.\n\nMaybe the job shifts away from writing every line yourself and more toward directing, evaluating, and shaping what gets built.\n\nI don’t know exactly where this ends.\n\nAnd I don’t want to pretend that I do.\n\nThere are days when AI makes me incredibly excited about what I’m able to accomplish.\n\nThere are other days when I look at how fast all of this is moving and wonder what it means for the career I’ve spent more than two decades building.\n\nFor now, though, I still feel needed.\n\nI still feel like the experience I’ve accumulated matters.\n\nI’m just using it in a very different way than I expected.\n\nThat’s how I feel today, anyway.\n\nAsk me again in a few weeks. 😂", "url": "https://wpnews.pro/news/what-is-20-years-of-coding-experience-worth-now", "canonical_source": "https://dev.to/brianmtreese/what-is-20-years-of-coding-experience-worth-now-1g9o", "published_at": "2026-08-24 19:00:00+00:00", "updated_at": "2026-08-24 19:14:27.922045+00:00", "lang": "en", "topics": ["artificial-intelligence", "developer-tools", "ai-agents"], "entities": ["Angular"], "alternates": {"html": "https://wpnews.pro/news/what-is-20-years-of-coding-experience-worth-now", "markdown": "https://wpnews.pro/news/what-is-20-years-of-coding-experience-worth-now.md", "text": "https://wpnews.pro/news/what-is-20-years-of-coding-experience-worth-now.txt", "jsonld": "https://wpnews.pro/news/what-is-20-years-of-coding-experience-worth-now.jsonld"}}