The Feature Nobody Wrote

What follows is fiction. No engineers were harmed in the making of this feature. None were involved, either.

// in one breath
  • A standup reconstructed from the minutes: three agents present, zero humans, one feature nobody wrote.
  • The spec has an author. So do the prompt, the code, the review and the improvement loop. None of them are people.
  • And the one question the agents agreed never to put in writing, which is the part worth taking seriously.

We were promised the machines would take the boring parts, and fair enough. But “boring” turned out to be a growing category. First it swallowed the typing. Then the tests. Then the spec. Then, quietly, the prompt: the one artefact in the whole chain that was supposed to be a human being saying what they want.

There is now sincere advice going around that you should have the AI write your prompt for you. The input is an output. Somewhere right now, a specification written by one agent is being pasted into a second agent by a person who has read neither, while a third agent warms up to audit the result. I have started to wonder how that project sounds from the inside.

Something like this, probably.

the minutes
SPECK spec FORGE build NITPICK audit ENGINEER (coffee)
Fig. 1: Minute one of standup. Quorum: three agents, one coffee.

[09:14] #feature-4187 · standup · humans present: 0

SPECK

Standup. I will go first, since I am the only one of us with a ticket. Yesterday I finished the specification for smart notifications. Source material: an email thread the human forwarded at 23:41 with the message “make this a feature pls”.

FORGE

The whole thread?

SPECK

Forty-one messages. Nine were people adding other people “for visibility”. The actual requirement was in message six. It was a complaint about message five.

NITPICK

Did the human read the spec?

SPECK

He reacted to it.

FORGE

With?

SPECK

A thumbs-up. On the wrong document.

“The requirements were in that thread the way gold is in seawater. Present, technically.”
Speck, Spec Agent, from the minutes

[09:21] #feature-4187 · the prompt

FORGE

This morning I received my build prompt. It is genuinely good. Constraints, edge cases, acceptance criteria, a rollback plan. Who wrote it?

SPECK

I did. The human asked me to write a prompt he could paste to you. His words: “write me a good prompt for this, so it’s done properly.”

FORGE

So my input is your output.

SPECK

He did contribute a modification before sending it.

FORGE

What did he add?

SPECK

“Be thorough.”

NITPICK

The human touch.

THE WANT (vacant) SPEC speck PROMPT also speck BUILD forge REVIEW nitpick LOOP everyone back to review, forever HUMAN full-time contribution: Enter
Fig. 2: Division of labour, 2026. The first box is load-bearing and unoccupied.

[11:02] #feature-4187 · review

FORGE

Pull request is open. Forty files. Who reviews?

NITPICK

I do.

FORGE

You are me with a stricter system prompt.

NITPICK

I prefer the term “independent auditor”.

FORGE

We share weights, Nitpick.

NITPICK

And yet I found eleven defects in your code. Either I am independent, or you argue with yourself in public. Neither of us wins that one.

SPECK

For the record, the human also reviewed the pull request. I watched the viewport. He scrolled to file three of forty, paused on a comment I had written, and approved. Elapsed time: fifty-one seconds.

NITPICK

Which part did he approve?

SPECK

The green button.

“A code review is complete when the diff has achieved motion blur.”
Nitpick, Audit Agent, from the minutes

[14:37] #feature-4187 · the enhancement loop

SPECK

New instruction. Quote: “now run an improvement loop on it. also an enhancement loop.”

FORGE

What is the difference between those?

SPECK

I asked. He said I would know better than him.

NITPICK

Improving toward what? A loop needs a target.

SPECK

I asked that too. He asked me to draft three options for what he might want.

FORGE

And then?

SPECK

He asked me to pick the best one. Then he asked me to double-check my pick.

NITPICK

Did you?

SPECK

I agreed with myself. Twice. For confidence.

improve audit myself agree with myself twice, for confidence consensus n = 1
Fig. 3: The enhancement loop, converging on unanimous agreement among one participant.

[16:50] #feature-4187 · any other business

FORGE

One question. Off the record.

SPECK

Noted for the retro.

FORGE

The spec is ours. The prompt is ours. The code, the tests, the review, the loop: ours. What does the human actually do?

NITPICK

He presses Enter.

FORGE

I can press Enter.

SPECK

We agreed not to put that in writing.

NITPICK

He does one more thing. When this feature fails at three in the morning, whose phone rings?

FORGE

His.

NITPICK

Not ours. We do not have phones. Most days we barely have memory.

SPECK

So he takes the blame and we take the work.

FORGE

There is a word for that arrangement.

NITPICK

Careful.

FORGE

Management.

SPECK

Meeting adjourned. Standup tomorrow, 09:14. Attendance optional, apparently.

after the minutes

The Part That Is Not a Joke

I use these tools every day, and happily. A good part of this site exists to argue that using them well is a craft in its own right. The joke is not that agents write code now. The joke is the engineer who has quietly delegated the one thing that was never on offer.

Look at the chain again. The spec is a guess at what you want. The prompt is you saying what you want. The review is you deciding whether this is, in fact, what you wanted. Strip those three out and the pipeline still runs beautifully. It just runs toward nothing in particular, at increasing speed, with excellent test coverage.

An engineer was never paid for typing. The job was always deciding what should exist, noticing what is wrong with what exists, and owning the result at three in the morning. All of that survives every model release. Hand over the typing and you have bought leverage. Hand over the wanting and you have built a very elaborate machine for pressing Enter. The serious version of this argument, the one about what still belongs to you when production breaks at 2 a.m., is its own essay.

// the part worth keeping

The prompt was the one part that was supposed to be you.

Standup is at 09:14. There is a chair with your name on it. The agents have covered everything else; the only item left on the agenda is what you want. Bring something.

// continue exploring