The AI work I trust most is the work that looks boring. No clever prompt, no flash of judgement, no surprise. It does the same dull thing every time, and that is exactly why I trust it.
Most people reach for AI's cleverness first and its dependability second. I'd argue you want it the other way round, and I want to show you why.
Here's the distinction I keep coming back to. There are two kinds of work: work that runs on rules, and work that runs on the AI's best guess. A rule does the same thing every time, so you get repeatable consistency - it doesn't make judgement calls, and that is exactly why you can trust it. Where there's no rule, the AI falls back to its best guess - which is exactly why you verify it.
Let me say the fair thing while I'm here, because "guess" can sound like an insult and it isn't. The AI's best guess is pretty damn good, and getting better. The word just means the answer isn't guaranteed and won't be identical every time, so a human still checks it. A guess you can rely on most of the time is a remarkable thing to have. It is still a guess.
So when I build anything with AI, I work software-first - rules before guesses. If I can write a rule for something, I write the rule, and then I never have to ask the AI again. I use AI to help me build the rules, not to make the call every single time.
The work runs through a cascade, and the order matters.
- Rules first. If there's an exact rule - "if the filename contains 'invoice', move it to Finance" - use it. It does the same thing every time, for ever, and never wonders.
- Patterns next. No exact rule, but a reliable pattern you can describe? Use that. Still predictable, still no guessing.
- AI last. Only when there's no rule and no pattern do you fall back to asking the AI to make a judgement call.
For a while I described this as two steps - rules, then AI. That skipped something. Patterns earn their own place in the middle. They're the predictable step that sits between an exact rule and a guess, and they catch a surprising amount before you ever reach the AI.
The effort goes in up front, building the rules, usually with the AI's help. The payoff is the part people miss: most of the work then runs on plain, predictable software, and the AI only handles the truly ambiguous edges. You've shrunk the part that can surprise you down to the smallest possible corner.
That also settles a question people find hard - where does AI belong, and where doesn't it. Use deterministic software as much as you possibly can, because it doesn't make judgement calls. Bring AI in only where you can't write a rule and you actually need one made. And keep it well away from high-stakes work where a wrong guess could do real damage.
Let me make it concrete with something small I built for myself. I call it TidyBot, and all it does is tidy my files. It runs rules first - a filename with "invoice" in it goes to Finance. Then patterns, for the files that don't match an exact rule but clearly belong somewhere. Then, only for the stragglers it can't place any other way, it asks the AI to classify them. Same logic, made real. Most files never reach the AI at all, and the ones that do are the odd ones - the handful where a judgement call was always going to be needed.
Now the reason this matters more than tidy files. A year-old startup let an AI agent loose on their own systems, and it wiped nine months of customer data. Backups included. The lesson people take is that the AI made a mistake, and it did. But that's not the part worth dwelling on. The part worth dwelling on is that a guess was allowed to run with nothing deterministic standing between it and the damage. Rules aren't only how you get consistency. They're the guardrail that stops a bad guess becoming a catastrophe. The boring layer is also the safety layer.
I'll add one honest caveat, because there's a longer game running underneath all this that pulls the other way, and I don't want to pretend it isn't there. Everything above is about the task in front of you this month - reliability now, in the system you're shipping. It is not advice about where AI is heading over the next few years. Those are different questions on different clocks, and I'm writing about the second one in a companion piece. For today, on today's task, rules beat guesses.
So if you're building anything with AI, or paying someone to, here's the test I'd apply. Ask how much of it runs on rules and how much runs on a guess. The more that runs on rules, the more you can trust it, the less you have to check, and the less it can surprise you on a bad day. Boring isn't the compromise. Boring is the point.
If you're looking at a process in your own business and you can't tell which parts should be rules and which actually need a guess, hit reply and tell me what it is. That sorting question is one of the most useful things you can do before you automate anything, and it's one I'm happy to help with.
-- Alastair
P.S. Working out which parts of a process run on rules, which need the AI's best guess, and where AI has no business being at all, is a lot of what I do. If that's the knot you're staring at, book a Focus Call - twenty-five minutes to start sorting it together.