WritingYour AI is a junior, not an oracle

Your AI is a junior, not an oracle

The 90%-vs-100% argument has a simple answer once you stop treating AI as a finished system and start treating it as what it is: a fast, capable, occasionally-wrong junior who needs managing.

The wrong yardstick

Most arguments about AI accuracy start in the wrong place. One camp is disappointed it isn’t right 100% of the time and writes it off. The other trusts it to be right 100% of the time and gets burned when it isn’t. Both made the same mistake: they treated AI as a finished system that is either correct or broken. It’s neither.

It’s a junior, not an oracle

AI behaves like a capable junior employee. It’s fast, tireless, and handles the bulk of the work well. It is also occasionally, confidently wrong, usually about something it hasn’t seen before, and it won’t tell you when it is. You already know how to work with someone like that, because you’ve managed juniors. You’d never send their first draft to a client unchecked. You’d never fire them for not being flawless on day one. You brief them, you check their work, you learn what they tend to get wrong, and you give them more as they earn it. AI is the same hire. Manage it the same way.

With a junior, you……so with AI, you
Brief them properly before they startGive the model the context and examples it needs to get it right (that’s the next question)
Don’t send their first draft straight to a clientPut a check before anything irreversible or customer-facing
Notice what they keep getting wrongGroup the failures into named patterns, not a vague “it’s sometimes off”
Tell the team what they can’t yet be trusted withMake the AI’s strengths and limits explicit so people check the right things
Give them more rope as they prove themselvesExpand scope as the system earns trust on real work
Don’t expect 100% on day oneTreat 90% as success; the missing 10% is a process to manage, not a flaw to fix

So 90% isn’t the problem

Seen this way, 90% stops being a disappointment and becomes roughly what a good junior gives you. The 10% it misses isn’t a technology problem to solve — it’s a management problem to design for. The real question was never “how do I get this to 100%?” It’s two better questions: which 10% does it get wrong, and what’s my process for catching it? Match the checking to the cost of being wrong — spot-check the low-stakes work, and check every customer-facing or irreversible output the way you’d read a junior’s letter before it went out under your name.

And it’s how you win the team over

This framing does something else: it gets the work adopted. A team will never trust a black box that claims to be infallible — the first mistake kills it. They will trust a junior they’re supervising, because they know exactly what that means. “This handles the first 90%, you do the senior 10%” is a sentence people accept. It is also, not by accident, how the AI workflows I ran at Meta actually held: the model did the volume, a person stayed on every decision that touched a customer, and trust grew because everyone knew where the line was.

What this sets up

A junior is only ever as good as the brief you give them — which is the next question: what you’re actually sending the model, and what you can reasonably expect back. And a junior who never learns from a mistake unless you make them is one who quietly drifts — which is the question after that. Treat AI as a junior worker, and the rest of running AI well falls into place.

So, what should you do?

If you’re putting AI into real work and want a straight answer on where the checks belong — what’s safe to spot-check, what should never go out unread — that’s the conversation. Getting that line right is the difference between a junior who makes you faster and one who embarrasses you in front of a client.

It’s the same posture I set up for clients: a review layer between the model and the customer, sized to what a mistake actually costs — in place before the junior gets near anything that carries your name.

Talk to me →