The Skills They Said Would Disappear
What I discovered when AI did in an hour what used to take a budget, a development team, and three months
I hear it constantly. People terrified that AI is coming for their job, certain that everything they spent years learning is about to count for nothing — and then doing absolutely nothing about it, because terror doesn’t make you curious, it makes you freeze.
I understand the fear. I just don’t share it, and I want to tell you why — because the why isn’t a theory. It’s something I found out by accident, doing something else entirely.
The hour that should have taken weeks
At my old company, getting something built — a tool, a process, a piece of automation — meant a business case, a budget request, a development queue, months of waiting, and if you were lucky, a result that mostly matched what you’d originally asked for.
I used to write those business cases. I knew exactly how long the wait was, because I’d lived inside it for decades.
Then I sat down with Claude one afternoon and built something — properly, working, doing the actual job — in about an hour.
No budget. No ticket. No development team. An hour.
And the thing that made that hour possible wasn’t the AI. The AI was just sitting there, capable, waiting to be pointed at something. What made it possible was forty-one and a half years of knowing exactly what the thing needed to do, how to describe a requirement precisely enough that nothing got lost in translation, and how to tell good output from output that only looked good.
That’s not a skill AI replaced. That’s the skill that made AI useful in the first place.
What I actually discovered
I went looking, half-jokingly, for the edges of what AI couldn’t help me with.
I’m still looking. I haven’t found them yet — not because AI is magic, but because the things I’m good at (the things four decades as a project manager and business analyst beat into me) turn out to be almost exactly the things AI needs from a person to do its best work: clear thinking, precise requirements, the judgment to know when an answer is right and when it’s just plausible.
I didn’t become less necessary the day AI got capable. I became, if anything, more dangerous in the most useful sense of the word — because the gap between “having an idea” and “having a working thing” had just collapsed from months to an afternoon, and I was the one who knew how to walk through it.
But I need to be honest about something
I had forty-one and a half years to draw on when I found this out. I want to stop here and say that plainly, because it would be too easy to write the rest of this post as if everyone reading it has the same depth of experience I had to fall back on, and that’s not true, and I don’t want to pretend otherwise.
If you’re two or three years into a job — an analyst, someone doing data entry, someone early enough in their working life that “decades of accumulated judgment” isn’t something you have yet — the fear you’re carrying is a different, harder thing than the fear I’m describing. You haven’t had time to build the deep well of knowing-what-good-looks-like that I’m telling you is the real asset here. You don’t have the mid-life vantage point that lets you see the other side of something terrifying, because you haven’t been on the other side of much yet. That’s not a flaw in you. It’s just where you are.
So let me say the thing that actually matters underneath all of this, for you specifically as much as for anyone with decades behind them:
AI is just a conversation.
That’s it. That’s the whole barrier, and it’s smaller than it looks from where you’re standing. You don’t need forty-one years of experience to start one. You need to open something and talk to it, the way you’d talk to a colleague who’s patient, doesn’t get tired of questions, and has no opinion about whether you’re “senior enough” to ask them. The two or three years you do have — whatever they taught you about your actual job, the parts that are tedious, the parts you’ve already half-automated in your head out of sheer repetition — that’s a real starting point. It’s smaller than mine. It’s still real.
You don’t need to already be the expert to start the conversation that makes you one.
The part that should actually reassure you
If you’re afraid AI is coming for your job, here’s the thing nobody’s telling you while you’re frozen:
The skills you’ve built doing that job — even two years’ worth, even the ones that feel too small to mention — are very likely closer to what makes you good at directing AI than you think. Knowing what “done properly” looks like in your specific corner of the work. Knowing which questions actually matter there. Knowing when something’s almost right and that’s not the same as right. Nobody hands AI that judgment, no matter how junior you are. You already have some of it. AI is one of the fastest ways I know to build the rest.
I’ve watched dozens of former colleagues go through redundancies — different circumstances to mine, their own stories, ones I don’t fully know. But from what I’ve seen since, on LinkedIn and elsewhere: the ones who kept moving landed somewhere decent. I don’t think that’s despite their experience, however much or little of it they had. I think it’s because they kept moving.
The fear says: everything I know is about to be worth nothing.
What I actually found was the opposite. Everything I knew turned out to be the one thing AI couldn’t do without me — and that’s true whether your “everything” is four decades or four hundred days.
So, do something about it
Not a course. Not a certificate. Not a waiting period until you feel “ready” or “experienced enough.”
Just a conversation. Open an AI app, a large language model like ChatGPT or Claude or Gemini or any of the free tools available to you, and point whatever experience you do have — large or small — at an actual problem you already understand better than you’re giving yourself credit for. That’s how mine started too. It just happened to start forty-one years further down the track than yours.
You might be surprised what’s already yours, and how much it’s worth.
Sandi is a Melbourne-based problem-solver, crisis-averter, and translator of the technical into the human. She spent decades being the person everyone called when something was broken, confusing, or just needed explaining properly — earning a reputation that preceded her wherever she went. Now she’s channelling that same instinct into AI: making it accessible, practical, and genuinely useful for people who think it isn’t for them.