💬Comments welcome. To leave a note, select any text and click the note / highlight button that pops up — or open the panel with the tab at the top-right (‹). Notes are visible only inside our private review group.

22.20 Under the hood: prompts, patterns, and verifiers

The appendix How this book was created gives the methods overview; this companion goes one level deeper, into the machinery of the collaboration itself — the recurring prompt patterns that made an AI a dependable co-author rather than a fluent fabricator, and the verifier suite that catches the specific ways such a collaboration goes wrong. It is written for the reader who wants to reproduce the method, not just hear that it happened. None of it is magic; most of it is the unglamorous discipline of grounding, isolating, and checking.

22.20.1 Prompt patterns that made it work

A large language model will happily write fluent, confident, subtly wrong text all day. The whole game is arranging the work so that the model's strengths (drafting, bookkeeping, code) are used and its failure modes (fabrication, drift, plausible-but-wrong) are structurally prevented. A handful of patterns did most of that work.

22.20.2 The verifier suite

The verifiers are the book's immune system: a numbered set of checks, some mechanical and scriptable, some expert-judgment reviewer passes, run at outline time (a GO / NO-GO gate before a section is written) and again post-draft. They encode, as runnable checks, the specific failure modes of AI-assisted authoring. The current suite:

#VerifierWhat it catches
V1encoding claritya histogram, average, or operation whose space (linear / gamma / log) is left ambiguous
V2notation consistencya symbol used with two meanings, or undefined in Notations
V3prerequisite coveragea concept used before (or without) being introduced
V4language isolationPython and C++ snippets leaking into the same edition
V5outline readinessa section's scaffolding tags (prereqs, figures, equations, sources) present before writing
V6missing assumptionsa claim whose conditions are unstated or too weak
V7text ↔ outline consistencydrafted prose that drifts from, or drops, what the outline specified
V8problem-set consistencya pset that contradicts the chapter it tests
V9technical accuracy & equationsa wrong statement, a sign/factor/unit error, an undefined symbol, an over-broad claim
V10pedagogical claritymath-first or intuition-free explanation; a missing picture or worked intuition
V11single-author voicea tonal seam where the prose stops sounding like one person
V12ready-to-write gatethe aggregate GO / NO-GO verdict per section (rolls up the pre-generation checks)
V13CS-undergrad background fitbackground assumed beyond the stated audience and not built upstream or in an appendix
V14figure opportunitya visual concept that has no figure but should
V15text ↔ figure fitprose that names an element a figure lacks, or a figure the prose never leverages
V16outline source coveragethe outline missing a point its slides / transcript / references make
V17text source coveragethe prose silently dropping a source's point, or replacing the author's framing with a generic one
V18citations & referencesa missing, wrong, or mis-attributed citation; a dangling reference (never invent one to fill a gap)
V19big-lesson coveragea recurring "big lesson" used but not registered, or registered but not surfaced in the recap
V20figure legibilityoverlapping text, sub-floor fonts, clipped labels — checked at every figure build
V21outline ↔ draft structure paritya chapter's section structure diverging between outline and draft
V22acronymsan acronym used without a first-use expansion and not in the curated Acronyms list
V23concision & point-first prosepadding, hedging, or gratuitous cuteness ahead of the point
V24wikilink resolutiona link to a page or anchor that does not exist

Two things about the table are worth saying plainly. First, the mechanical checks (V1–V8, V18–V24, in part) are scripts that run on every build and can fail the build — they are not advice, they are gates. Second, the reviewer checks (V9–V11, V13, V15, V17) produce warnings for a human, never silent edits — because the whole premise of the project is that the editorial judgment, the deciding of what is right, stays human. The verifiers make that judgment cheaper and more reliable; they do not replace it.

22.20.3 Why this is the interesting part

It would be easy to read "written with an AI" as either a boast or a confession. It is neither. The model wrote fluent first drafts and tireless bookkeeping; the patterns and verifiers above are what made that output trustworthy enough to keep — the grounding that stops fabrication, the isolation that stops drift, the registries that stop incoherence, the checks that turn house style into something enforced rather than hoped for, and the human sign-off behind all of it. If there is a transferable lesson in this book's own making, it is that the value of an AI collaborator is bounded almost entirely by the scaffolding you build around it — and that the scaffolding, not the model, is where the craft lives.