Sandi’s Principles
An hour, and a question I shouldn’t have asked out loud
A quick orientation if you’re new here: I’ve spent the last few months building apps with AI — and discovering, along the way, that building something and deciding what to do with it are two entirely different questions. This post is where those two questions collided.
Capability is one thing. What you decide to do with it is another. This is the story of where that gap caught up with me.
I’d been ridiculously productive since that winter lifted — the planner, the memory tool, the game, all of it built because I finally had somewhere to point forty-one and a half years of solving problems. Most of that building has been joyful. Uncomplicated.
This one wasn’t.
The wish I’d carried for years
I was chatting with my old team on our WhatsApp group — the same chat where one of them told me AI hadn’t reached Operations yet. Somewhere in that, an old, familiar wish surfaced. I’d wanted the company to fund a tool for years: something that could quiz our clients and turn their answers into a specification, automating the repetitive 80% of the job that ate hours every week and never required the actual skill they’d been hired for. I used to put in budget requests for exactly this. They never got approved.
So I opened a blank screen and built it myself. An hour later, I had a working specification builder, doing the exact thing my old team did manually, every day, for years.
An hour. After years of wishing.
The question I asked half as a joke
I was pleased with myself — the way you are when something that used to be hard turns out to be easy, and you built it yourself, on an ordinary afternoon, with no budget approval and no IT ticket. I told my old team, half-laughing, that a few refinements and this could be perfect for them.
And then I actually heard myself.
If I built this out properly, polished it, took it to their manager — there’s a real business in it. Considerable money, for not much more work than I’d already done.
And it would put one or more of them out of a job. Eighty percent of their day, automated. The thing I’d wanted for years, built in an hour, would put my old colleagues in the crosshairs for the next round of redundancies.
The thing I built, and what it cost me to notice
This is the part of the building that doesn’t get the joyful music underneath it. I’d spent an hour solving a problem I’d genuinely wanted solved for years, for people I genuinely care about, using a skill I’m genuinely good at. Everything about that should feel like a win.
It mostly does. But sitting underneath the satisfaction is something less comfortable.
The PagerDuty 2026 Shadow AI Survey found that two-thirds of office professionals have used AI tools at work despite believing they were not permitted under company policy. Not a fringe behaviour — two in three workers, across Australia, Japan, the UK and the US. What I built that afternoon sits squarely inside that pattern. I — one woman, one ordinary afternoon, one good question — built in an hour what would have taken my old employer a procurement process, a development team, and a budget line they never had.
I built it that afternoon. The next day, I stopped.
I didn’t delete it. I didn’t pretend it didn’t exist. I just stopped working on it — stopped polishing it, stopped picturing the pitch to their manager, stopped imagining what it could become if I kept going. Building something and deploying something turned out not to be the same decision at all, and I hadn’t realised until that moment that I’d been treating them as one.
The gap nobody’s drafted a policy for
I’m not going to fully resolve that tension here. I don’t think it resolves. But I’ll name it plainly, because this is the part that matters beyond my own WhatsApp group.
Enterprise AI Governance reporting in 2026 puts it directly: “By the time a company’s legal team finishes drafting its generative AI acceptable use policy, a meaningful percentage of its engineers, analysts, and product managers have already moved past it. Not deliberately. Not maliciously. Just practically.” Only 37% of organisations have policies to manage AI at all.
Organisations move in years. Individuals move in afternoons. The gap between what one motivated person can now build alone and what a company has officially sanctioned is wider than it’s ever been — and it’s growing every day. Research confirms the governance gap will keep widening before it narrows. AI capability is not slowing down. Which means the decision I made — to sit on the tool rather than deploy it — is not a permanent resolution. It’s a pause.
I have the ability to close that gap for my old team. I’m choosing not to, for now — and that distinction is the whole point of this post.
Power isn’t about what you can do. It’s about what you choose to do.
I don’t know yet what I’ll do with what’s sitting on my hard drive. That’s not false modesty — I genuinely haven’t decided. But I know the decision is mine to make, slowly, rather than the tool’s to make for me the moment it finished building.
More on this story:
The Worker Who’s Waiting for Permission
and
The Manager Who Built the Tools
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.