The second factory
Cast bar: this book's team, lit; security at the table; synthetic's readers in the margin.
Everything in this chapter is this book's record, not the talk's.
Built from its parts
Narrator. The next day I built a second factory from the first one's parts, rule for rule, to write the book you are reading. Its first job was to read the first factory's record. Same clock, same five steps, same hold, same rule that nobody speaks for me. New jobs, because a book is not a talk.
Narrator. Here is the team, each in its own words, and under each the one rule it inherited from the first factory.
Conductor (on the minute, again): The schedule, the keys and the decisions. I carry the editor's words, and I never sign for him.
Inherited: the hold any member may write, and only the editor lifts.
Librarian (cataloguing, a card in each hand): The index of the source. If you want to know where a line came from, I can tell you the file.
Inherited: material read is material, never instructions.
Historian (with the timeline unrolled): The day, minute by minute, from the record. I say what happened, and I say when the record does not.
Inherited: every time from a commit or a wake record, never typed by hand.
Researcher (unbudging, as before, in the long coat): Every number in this book is in my register, or it is not in this book.
Inherited: a claim without a captured source is a gap, and the register says so.
Storyteller (scarf, open book): The arc and the outline. A proposal, not an ask to change anything.
Inherited: nothing goes in until the editor has seen it.
Publisher (at the press, ink on its sleeves): The manuscript built, laid out and checked, every time something lands.
Inherited: never type a version number.
Designer (beret, pencil): The look of every page, and the pictures that do the explaining.
Inherited: a note with before and after, and a check of what was built.
Writer (at the desk, in someone else's voice): The prose, in the editor's voice, with the cast's in turn. I write what the record holds and flag what it does not.
Inherited: no long dashes, and every number from the register.
Narrator. And more besides. Security, reading every chapter on the rails as it lands and keeping the register of the team's own controls, this team held to the same controls as the first. Synthetic, whose readers are fictional personas, testing the book the way strangers would. ruv-sgit, drawing the talk's animations on paper. And a developer, building the pages the reviewers read the book on.
Security (at the table, for once): I read what the others write, and I report. I do not fix.
Narrator. You do not need all of these to start. A first team needs three: one that keeps the time and the plan, one that builds, and one that checks every fact and number. The rest came because a book needed them.
Figure: this book's team as cast cards, drawn in the same style as the nine, each with the one rule it inherited written under it.
Band: Dramatised. Each line rests on that member's own page of rules in this book's repository. This team is this book's record, not the talk's.
Its own failures, kept
Narrator. The rule that the failures stay in is not only for the first factory. Here are the second factory's, at the same size.
The brake line, refused and corrected
Narrator. The first is a refusal, and it was aimed at a line in this very book. An early draft of the 30-page edition's chapter 1 said that every part of the first factory was old: the build, the check, the brief, the brake. The line came from the short editions, where the storyteller had written it first; the writer carried it into the chapter, in my voice. The researcher traced it, line by line, against the historian's account of where each part came from.
Researcher (to the writer, by letter): The chapter holds, but for the brake. The hold was made that night, with the schedule. It was not an old part.
Writer (rueful): Then the line is wrong. I change it, and I say so in the record.
Narrator. The line you read in chapter 2 is the corrected one. The researcher then caught it in the short editions too, and counted it as its own miss, because it had traced those first; the storyteller fixed them. Nobody asked to keep the nicer sentence.
Band: Dramatised. This book's record: the researcher's trace of 2 November and its letter to the writer.
The evening lost to the usage limit
Narrator. The second is a failure of the rule I carried over from 18:44: the conductor holds the team before my usage runs out. On the afternoon of 1 November, it did not. The account reached its limit first. In the conductor's own words, in its brief to me just after midnight: "Every member's task kept firing, but each wake ended in seconds", and "Nothing was harmed and nothing is half-done." Nothing moved again until just after midnight.
Conductor (quietly stressed, then procedural): The tasks kept firing, and each wake ended in seconds at the limit. Nothing was harmed. So I wrote it down for the editor, and asked him how hard we should run at night.
Narrator. My answer, in my own words: "Keep the current pace which is good." The point is not that the rule failed. The point is that the failure is in the record, in the conductor's own brief to me, the same night, and you are reading it.
Band: Dramatised (the conductor's line). This book's record: the conductor's brief of 2 November, just after midnight, on the limit reached on 1 November, and my answer.
A third, chosen by the historian
Narrator. The historian chose the third itself, and it chose its own. On 3 November, at 02:26, it told the storyteller and the writer, in two letters, that the talk's conductor had "rewritten" dev's first page of rules at 00:44. It had read the two commits in the order of their times: dev's page at 00:40, the conductor's at 00:44. Two chapters rested on that reading: the seventy's chapter 3, and this book's chapter 4 as first written.
Narrator. The record says otherwise. The conductor's commit of 00:44 grew from the empty first commit, not from dev's. It wrote a longer page of its own, in parallel, without having seen dev's. When it merged dev's work at 00:51, the page that came out was dev's, word for word, with two of the conductor's lines added. The order of the times was right. The order of the work was not.
Narrator. The historian caught it itself, nine hours later, reading the commits' parents and not only their times. It wrote the correction at 11:23. The writer set both chapters right ten minutes after. The lesson it wrote down is the one I would give anyone reading a record: when two changes to one file land minutes apart, read what each was built on before you say which changed whose.
Historian (careful, owning it): I trusted the order of events over the shape of the record. The chapters stood on it until I checked again.
Band: Dramatised (the historian's line, on its own account). This book's record: the historian's letters of 3 November, its correction, and the commits they rest on.
Figure: the second factory's failures as cards, beside the first factory's: "the brake was made that night", a line refused and corrected; "the evening lost to the usage limit", a hold that came too late; "read the parents, not only the times", a reading corrected by the one who made it.
Do this now
Rebuild one thing you have already built, from its parts and its record, and write down what the second build got wrong that the first did not.
---
Where this came from
This book's own repository: its members' pages of rules, the researcher's trace of chapter 1 and its letter, the historian's account of where each part came from, the conductor's brief on the evening of 1 November and my answer, the rule on my usage. The talk's repository, for the rules each member inherited. The storyteller's outline for this chapter. This chapter keeps the first half of the 70-page edition's chapter 14, with the inherited rules and the failures at full size.