A Fool with a Tool is Still a Fool — Simon Schrottner

A Fool with a Tool is Still a Fool | Simon Schrottner

“A fool with a tool is still a fool.” — often attributed to Grady Booch

I keep coming back to this quote when I watch teams adopt AI.

In my last post I wrote about shifting the engineering process left — spec sessions, autonomous agents, humans reviewing output rather than writing it.<br>A few people asked the obvious follow-up: if an agent implements and an AI reviews, why do I need a team at all?

It’s a fair question.<br>And I think the answer is in that quote.

The agent validates against your prompt.<br>That’s it.<br>If your thinking is muddled, the output will be muddled — just faster and at greater cost.<br>An agent doesn’t tell you that you’re solving the wrong problem.<br>It solves whatever problem you gave it, thoroughly and without complaint.

Most AI usage right now treats AI as a tool.<br>Which means the quality of the output is bounded by the quality of the thinking that went into the prompt.<br>A fool with a tool is still a fool.<br>The tool just makes the foolishness more expensive.

The team is the check on intent.<br>Not after the agent has burned three sprints on the wrong thing — before it starts.

That’s what mob planning actually is, when you think about it.<br>Not a meeting.<br>Not process overhead.<br>It’s the place where bad ideas get caught before they get expensive.<br>Where someone asks “wait, why are we building this” before an agent runs with it for a week.

But there’s something else happening in that room that I think gets underestimated.

It’s where the learning happens.

Not just prompting.<br>System thinking.<br>Architectural patterns.<br>How to decompose a problem.<br>Why a certain approach fits this codebase and another doesn’t.<br>How a senior frames a problem before an agent ever touches it — the mental model that makes the output actually good.

Right now that knowledge isn’t transferring.<br>Everyone is heads-down with their own tools, developing their own habits in isolation.<br>Engineer A gets dramatically better output than engineer B.<br>Nobody knows why.<br>Prompting approaches are one small part of it — but the bigger part is the system thinking underneath.<br>And that only surfaces if there’s a room where people talk through problems together before they hand them to an agent.

That conversation only exists if there’s a room to have it in.

AI is quietly doing something to teams.<br>Everyone optimises their own workflow.<br>Everyone gets faster individually.<br>And the shared craft — the thing that used to live in code reviews, in pairing sessions, in hallway conversations about why the last approach didn’t work — starts to disappear.

The mob planning session gives it back.<br>It becomes the place where system design gets discussed, where architectural decisions get challenged before the agent runs with them, where a junior watches how a senior thinks through a problem and learns something they couldn’t have learned from reading generated code.<br>Prompting is part of that.<br>But it’s the smaller part.

The artifact changed.<br>The need for the room didn’t.

I don’t think teams are going away.<br>I think the ones that skip the room will produce faster, worse work — and won’t understand why.

The ones that keep the room, and take it seriously as the place where thinking happens, will end up somewhere different.