← The Review Desk
ProcessAutomater Education Series · Review

The Revision Desk

Your notes, answered — approve or correct by note number

Every reading note you left on Books One and Two, with what it flags, the change, and the replacement prose. Then the book-wide sweep, the round-two redrafts you asked for, the generalized line for the program story, and the law your corrections produced. Nothing here is applied to a manuscript until you say so.

61 notes3 roundsSep 1–2applied 2026-09-02 — nothing pending
Round One — your notes
1 of 18

Book One — Revision Proposals

2026-09-01 · Revision proposals built from your own reading notes, pulled live from the notes-server database (server = source of truth). 22 notes on this book. Nothing has been changed in any manuscript — every item below is a proposal awaiting your yes/no.

How to use this

Each item gives you: where the passage is, your note verbatim, what it’s actually flagging, the change proposed, and the actual new prose to drop in. Reply by note number — “B1-07 approve”, “B2-14 no, do X instead”. Anything marked Blocked on [OWNER-FACT] needs a fact only you have before it can be written.

10 notes · Packet A1 · pulled 2026-09-01

B1-01 · Chapter 1 — general chapter flag, no highlighted text

Where: Whole chapter; most likely target is the hard numbers in “What actually happened” / “The second ceiling” (truck count, restaurant count, the 2010→2018 timeline, “close to a decade”). His note: (highlight only, no text) Highlighted: — Diagnosis: With no highlight and no text, there’s no direct signal. The chapter’s persuasive weight rests almost entirely on specific, memorable numbers (seven trucks, three restaurants, 2010 start, 2018 sale, “close to a decade” building the first business). A whole-chapter flag with nothing attached most plausibly means he wants those numbers double-checked before they’re locked in print, not a tone or doctrine problem — nothing else in the chapter trips a doctrine rule. Change: Don’t rewrite prose yet. Flag the specific figures for his confirmation, and tighten “close to a decade” to an exact figure if he’d rather have precision than a round phrase (2010–2018 reads as eight years, which “close to a decade” already covers, but he may want it stated plainly). Proposed new writing: > (if he confirms the timeline) — replace “I had spent close to a decade building the first thing” with: “I had spent eight years building the first thing while believing, the whole time, that I was building the second.” Confidence: LOW Blocked on: [OWNER-FACT] Confirm the truck count (seven at peak), restaurant count (three), and the 2010–2018 timeline are exactly right as printed — and whether “close to a decade” should become a precise “eight years.”

B1-02 · Chapter 3 — teach a multi-task morning, not just one task

Where: “What that actually looked like” → “The plain word for what came out of that morning is a Job” (the paragraph defining what a Job is). His note: “A job - recording you doing everything, showing the whole series of things you do. Maybe I should create a multi task recording the ai assistant (sam) can coverage to break apart into smaller processes.” Highlighted: — Diagnosis: He’s flagging that the chapter shows one continuous teaching session (tenant reply, listing inquiry, turnover check, vendor callback, quote) but never says explicitly that this single sitting produced several separate, reusable Jobs rather than one big combined one — which is the actual idea worth naming. Separately: “sam” is an internal codename and must never appear in reader-facing text (VOICE-AND-RULES §5 — no internal project names). Change: Add a short passage right after the events, before the chapter names “a Job,” making explicit that the one morning produced several distinct Jobs because the platform recognized where one task ended and the next began — without ever using the internal name. Proposed new writing: > Here’s the part that’s easy to miss the first time you do this: I hadn’t taught it one Job that morning. I’d taught it several, in the same sitting, without ever stopping to announce which task I was on. The tenant reply was its own Job. Moving the listing inquiry a rung up its ladder was another. The turnover check, the vendor callback, the quote — each one came back separate, callable on its own, the way you’d expect if you’d sat someone down and had them shadow an entire morning instead of a single task. I hadn’t drawn the lines between them. I’d just worked, the way I actually work, and it drew the lines itself. Confidence: HIGH Blocked on: [OWNER-FACT] Confirm that a single recorded session spanning genuinely distinct tasks is actually recognized and split into separate, individually reusable Jobs (rather than treated as one combined Job) — this is a Lane 3 capability claim and must be true before it prints.

B1-03 · Chapter 3 — second general chapter flag, no highlighted text

Where: Uncertain — possibly the same passage as B1-02 (both created in the same second, same chapter, both empty). His note: (highlight only, no text) Highlighted: — Diagnosis: This may simply be a second highlight on the same idea as B1-02 (the multi-task-recording point), landed on a nearby paragraph. I don’t see a second, independent doctrine or tone issue elsewhere in the chapter strong enough to justify a different guess. Change: If this is a duplicate of B1-02, no separate action needed once B1-02 lands. If he meant something else, the next most likely candidate is strengthening how explicitly the chapter distinguishes “a Job that runs the same way every time” from “an Agent that reasons fresh,” since that distinction is asserted but not restated once in “Teaching is not programming.” Proposed new writing: > (only if B1-03 is a distinct note) — insert after “You’re not writing software. You’re just doing your job in front of something that’s paying closer attention than anyone ever has before.”: “That’s also the whole difference between what you taught that morning and what would happen if you asked something to improvise the same morning fresh, with no memory of ever having watched you do it. One is a rule, built once. The other is a guess, made new every time.” Confidence: LOW Blocked on: [OWNER-FACT] Confirm whether B1-03 is the same concern as B1-02 or a separate one — nothing in the chapter text points clearly to a second issue.

Where: “The photo that didn’t say what it claimed” → the paragraph on rental-applicant prequalification: “deciding whether a rental applicant qualified… the only place anything resembling a person’s touch belonged was coordinating the conversation around it, not making the call itself.” His note: (highlight only, no text) Highlighted: — Diagnosis: No text attached, but this is the one passage in the chapter that squarely trips the book’s own liability rule: describing an automated system as the thing “making the call” on whether a rental applicant qualifies edges toward implying the platform makes housing decisions on someone’s behalf — a genuinely sensitive area (fair-housing exposure) if a reader takes it as “the software decides who gets approved.” Change: Keep the point (the checks are statable, rule-based, not mystical judgment) but make clear a person still owns the qualifying decision — the system runs the checks and hands back the facts, it doesn’t issue the approval. Proposed new writing: > Once we looked closely, prequalification ran on real, statable factors the whole way through — income multiples, history, the standard checks any property manager runs. Whatever you want to call the thing running those checks, it wasn’t intelligence being applied to a hard problem — it was a rule, running the same way every time, handing back the facts so a person could make the call faster and more consistently, not making the call itself. Confidence: MEDIUM Blocked on: — (no owner fact needed; this is a safer-construction edit per doctrine, not a new claim)

B1-05 · Chapter 5 — chapter ending needs the management/oversight tier

Where: “What’s left” — the final two paragraphs, chapter close. His note: “The chapter ends on a day of training to release tasks, but should also mention that once you have tasks being performed, things get real, because good management is what allows a company to grow… You, over time, become the manager of the manager… You still have the ability to step in… but you should not NEED to any more.” Highlighted: — Diagnosis: He’s right that the chapter stops at “release the task” and skips the point he actually wants readers to leave with: releasing tasks isn’t the finish line, it’s the moment a new layer of the job — supervision, quality control, trust — becomes the thing to build next. This is the chapter’s structural gap, and it’s also the natural bridge into Chapter 6. Change: Extend the chapter’s closing section with new material carrying his management-tier idea, using his own tenant-showing example, framed as something the reader would build (not something Patrick’s company is currently running, per the same present-tense caution he raises for Chapter 6). Proposed new writing: > But watching the first run isn’t where this ends, and it’s worth naming what comes next before you close the book on this chapter, because owners who stop at “I taught it, and now I watch” miss the real shift underneath the whole exercise. The moment tasks stop being the problem is the moment something else becomes the problem: whether the standard you’d have held them to is still being held once you’re not the one holding it. That’s not a smaller job than teaching. It may be the real one. Every hour spent confirming a turnover photo shows what it claims, or checking that a scheduled showing went the way its log says it did, is an hour of judgment — and judgment, once you can name what it consists of, is exactly the thing this book has already shown you how to hand over. > > Say a tenant wants to see a unit Tuesday at one o’clock. You don’t need to be the one confirming the code went out, the window was honored, the checkout came back clean — you need something standing where you used to stand, holding the standard you’d have held, catching what you’d have caught. Build that, and you haven’t automated yourself out of the business. You’ve become the manager of the manager: still able to step in, retrain a habit, correct a standard the moment it drifts — except now you almost never have to. A manager who stops watching can lose a whole company without ever making one bad call themselves, one small miss at a time. A layer of oversight that’s built to stay alert on purpose, instead of trusted to remember to, is what keeps that from happening. > > That’s the next tier of what you’re building, and it’s where the next chapter starts: not just teaching the task, but trusting what watches the task — and earning that trust the same deliberate way you earned this one. Confidence: HIGH Blocked on: — (built from his own dictated content; run past him before locking, same as any structural addition)

B1-06 · Chapter 5 — missing the three-question framework for judgment tasks

Where: “The one moment that doesn’t automate” — new paragraph following the (revised, per B1-07) hypothetical judgment passage, before “Ten people, one pin.” His note: “The narrator talks about tasks that judgement is difficult- but mentions nothing about how this is where the three questions come together with our learning system: what is the issue? What is the understanding of the task? … can you propose a solution aligned with our objectives? … you aren’t training a forgetful person… the training is an investment, but it’s one that you only have to do once…” Highlighted: — Diagnosis: The chapter names that some tasks resist automation but never gives the reader the actual mechanism for pushing even hard, judgment-adjacent tasks further over time — the three-question loop (issue → understanding → proposed solution) and the “not training a forgetful person” idea that makes repeated correction worth the investment. Change: Add a compact passage carrying the three-question framework and the “investment paid once” idea, right after the judgment discussion. Compressed his robotics riff (eggs, drywall, ceiling fan, shingles) to one honest, non-overclaiming sentence to keep the passage tight and inside the book’s own limits on what the platform does today — flag if he wants the fuller version restored. Proposed new writing: > Here’s what makes even a moment like that easier to push on over time: three questions, run in order, every time something lands that isn’t obviously a rule yet. What’s the actual issue in front of you? What does the understanding of the task consist of, stated plainly? And given that understanding, is there a solution to propose that stays inside what you actually want? The honest answer is almost always yes — sometimes only after a round of digging, sometimes after you correct its read of the task and it comes back having actually absorbed the correction. Even a no is useful, because it hands you back exactly where the understanding broke, instead of a confident guess dressed up as an answer. > > Early on, against a genuinely hard task, this can feel like it’s going nowhere. It isn’t. You’re not training someone who’ll forget by Friday. Every correction becomes part of what it already knows the next time, which is the whole reason this training is a debt paid once instead of a debt paid over and over — the old trap, where an operator prays a trained manager stays, or does the whole thing over again the day they don’t. This is still the business-administration layer, not a robot on a job site — you can’t yet teach a machine to hang drywall to spec or cut down a tree safely. But the same discipline, showing your work and confirming it was actually understood, is the ground floor for wherever this goes next, and it isn’t this book’s job to promise when. Confidence: HIGH Blocked on: — (no owner fact required; note the compression choice above is editorial, flag if he wants the longer robotics passage restored)

B1-07 · Chapter 5 — Derek story built/tested as fact when it wasn’t (LOAD-BEARING)

Where: “The one moment that doesn’t automate” — the full Derek passage, from “A friend of mine, an investor…” through the end of that section. His note: “The story about Derrick states as if it had already been built and it had not been built and it hasn’t been tested… I don’t like misrepresenting things… so we can turn that into an imagine, and instead of just his exact parameters, we switch up a handful of variables the investor may want to qualify making offers to (maybe all offers 60 days get a 65% offer, then offers 90 days get a 70% offer?)” Highlighted: — Diagnosis: The passage is written in past tense as something Patrick and a real friend built and ran (“We built it. It ran a standing scrape…”), which is untrue — it’s the friend’s own business idea, told in confidence, that hasn’t been built or tested. This is a direct Truth-and-Story Doctrine violation (asserting an invented/unbuilt event as fact) and, separately, a confidence problem — using a real person’s private plan as if it were Patrick’s own build. Change: Rewrite the whole passage as a second-person “imagine/picture” scenario (Lane 2c, process-chain), dropping “Derek” entirely rather than keeping a renamed stand-in — this removes any residual tie to the friend’s actual plan, not just the tense. Varied the offer-tier numbers per his own suggested example (60 days→65%, 90 days→70%) rather than the original “90 days flat at ~70%.” Proposed new writing: > Picture building a machine for a specific kind of deal: houses that have sat expired on the market, with an offer that scales against how stale the listing has gotten — say a house unanswered for sixty days earns a first offer around sixty-five percent of asking, and one that’s gone quiet for ninety earns closer to seventy — on a contract structure that carries a real inspection window. It could run a standing scrape against the target properties, tell whether a listing agent is still attached or the house has gone fully for-sale-by-owner, and route the outreach accordingly — through the agent where one exists, straight to the owner only when there isn’t one to go around, because that’s the professional line and the automation would be built to respect it rather than shortcut it. Offers go out. Some get accepted. On acceptance, the same system could pull up your actual calendar and schedule the site visit against real open time, no back-and-forth required. > > Here’s what wouldn’t get automated in that picture, and I don’t think it ever will: you, standing in the house after the walkthrough, deciding whether it’s a good buy. Everything before that moment — the search, the matching, the outreach, the offer, the acceptance, the scheduling — could run itself. That one moment wouldn’t, because what you’re weighing there isn’t a checklist you were simply too busy to write down. It’s a read on water damage that doesn’t smell right, a sense of a foundation’s real condition that a moisture reading only partly confirms, a feel for a block that comps alone won’t tell you. Ask yourself to write out exactly what you’re checking for and you’d produce a list — and the list wouldn’t be the thing. The thing is what you do with the list, in a room, once, with real money on it. Confidence: HIGH Blocked on: [OWNER-FACT] He asked to run this by him before re-drafting — confirm (a) the offer-tier numbers/day thresholds above (his own “maybe”), and (b) that dropping the named character entirely for second-person framing is acceptable, versus keeping a fictional named investor.

B1-08 · Chapter 6 — implies all this runs live in his company right now (LOAD-BEARING)

Where: “The cost and the lesson” — “The confirmation step, the scheduled window, the automatic texts — all of it is still running today, on every showing, whether or not anyone is watching that particular one happen.” His note: “I don’t want to state all of the automations are being applied in my company right now, just because I am not looking to draw any scrutiny. Saying I built and learned trust and rely on is different than blatantly stating you are using things right now… cover my ass and don’t make that level of claim.” Highlighted: — Diagnosis: This is the one sentence in the chapter that crosses into present-tense, current-operation language (“still running today… whether or not anyone is watching that particular one happen”), which is exactly the construction he’s asking to avoid everywhere in the book, not just here. Change: Shift the sentence from present (“is still running today”) to past (“kept running”), consistent with “built and learned to trust” rather than “currently in use.” Proposed new writing: > The confirmation step, the scheduled window, the automatic texts — all of it kept running the same way for as long as the portfolio needed it to, whether or not anyone was watching that particular one happen. Confidence: HIGH Blocked on: — (direct fix, no owner fact needed)

B1-09 · Chapter 6 — escalation should hand back a question, not a proposal

Where: “Why a system that stops is the one that’s working” — the “human on exception” definition paragraph. His note: “You said top escalation raises a question, not a rule number 1 proposal based on its understanding of the task, in the form of a question.” Highlighted: — Diagnosis: Reading through the shorthand: he wants it explicit that when the system escalates, it hands the human an actual open question (“here’s what I know, here’s where I’m unsure, what do you want me to do”) — not a packaged recommendation or decision dressed up as done. The current text says the system hands over “the one decision that actually needed a person,” which is close but doesn’t say plainly that what arrives is phrased as a question, not an answer. Change: Add a sentence to the “human on exception” paragraph making explicit that escalation arrives as a question, not a proposed answer. Proposed new writing: > It doesn’t hand you an answer dressed up as a done deal. It hands you the actual question — here’s what I know, here’s where I’m not sure, what do you want me to do — because the moment a system starts proposing its own answer at the exact point it’s admitting it doesn’t have one, you’ve stopped being asked and started being nudged. Confidence: MEDIUM Blocked on: [OWNER-FACT] The note is garbled in dictation (“a rule number 1 proposal”) — confirm this reading is what he meant before locking the sentence in.

B1-10 · Chapter 6 — third general chapter flag, no highlighted text

Where: Likely elsewhere in “The cost and the lesson” / “What replaced individual watching” — sentences describing the fence as ongoing (“was still there,” “the fence was still there… I checked the pattern, not the event”). His note: (highlight only, no text) Highlighted: — Diagnosis: Given his one explicit, strongly stated concern for this chapter (B1-08 — never imply this runs in his company right now), the most defensible reading of a second silent flag in the same chapter is a request to sweep the rest of the chapter for the same pattern, not a new issue. “By the time self-showings were fully routine across the portfolio, the fence was still there” and “It runs. The record is still there” (in the fourth-rung description) both sit close enough to the same present-operation register to be worth a second look, even though they’re each individually more defensible than the B1-08 sentence. Change: No rewrite proposed until confirmed — recommend a light pass on the two sentences above with the same past-tense/“built and learned” standard applied in B1-08, once he confirms this is the same concern. Proposed new writing: > (pending confirmation — if targeting “the fence was still there”): “By the time self-showings were fully routine across the portfolio, the fence had held — the confirmation step, the scheduled window, the automatic texts — and I’d stopped watching any single instance of it happen. I checked the pattern, not the event.” Confidence: LOW Blocked on: [OWNER-FACT] Confirm whether this note is the same “don’t imply current live operation” concern as B1-08 applied elsewhere in the chapter, or a different issue entirely.

Chapter-level summary

Chapter 1 — The Most Expensive Sentence in Your Business. Only one note, empty and unanchored; nothing in the chapter trips a doctrine rule, so the most useful move is a numbers-confirmation pass rather than a prose rewrite. No structural change implied.

Chapter 3 — Show It Once. His through-line is that the “one morning, one Job” telling undersells what actually happened — a single sitting taught several separate, reusable Jobs, and he wants that made explicit (and the internal codename “sam” scrubbed). Not a structural change — a clarifying insertion in an existing section.

Chapter 5 — What to Teach First. The strongest through-line in the packet: the chapter needs to go further than “release the task” — he wants the management/oversight tier (manager of the manager, quality control as the next automation frontier) added at the close, the three-question learning framework added to the judgment discussion, a liability softening on automated tenant qualification, and — most urgently — the Derek investor story rewritten as a hypothetical, since it currently states a real friend’s unbuilt, confidentially-shared business plan as something Patrick built and tested. This implies a real structural change: the chapter’s ending needs new material, not just a line edit, to set up Chapter 6 properly.

Chapter 6 — Watch the First Run. His through-line is liability discipline: never let the text read as “this is running in my company right now” — one sentence does exactly that and needs a tense fix; a second empty note likely flags the same pattern elsewhere. He also wants the escalation/human-on-exception moment described as handing back a question, not a packaged proposal. No structural change — targeted line edits.

12 notes · pulled 2026-09-01

B1-11 · CHAPTER 7 — Scheduled Is Not Done. Verified Is Done. — verification sequence is backwards

Where: “The fix isn’t more oversight…” paragraph, and its <!--BUILD-APPENDIX--> comment, in the section right after “The turn.” His note: “The schedule contact is not with the tenant first. The contractor should get a check in to verify they got access to the property from the tenant. If no communication, only then do we go to tenant to verify contractor has been in communication and to see if they arrived as expected or if scheduling has changed (after the start time). It’s not about catching it missed after, it’s about catching it is missing during the window. The contractor and tenant would then get a group thread with the party that we are having the issue with, and the information we manage is the communication between those two parties.” Highlighted: — Diagnosis: The chapter’s fix currently checks the tenant first, after the fact (“a message that goes to the tenant directly, the same day or the next”). Patrick’s real sequence checks the contractor first, inside the visit window, and only escalates to the tenant on contractor silence — and it catches a miss while it’s happening, not the day after. He also wants a shared contractor-tenant thread when the two accounts disagree, not the business acting as a relay between two people’s separate reports. Change: Replace the fix paragraph and its build-appendix comment with the corrected sequence: contractor checked first at window-open, tenant checked only on contractor silence and only after the window closes, and a joined thread opened automatically the moment the two sides disagree. (Chapter 13 echoes this same follow-up in its “Where the day forks” section — worth applying the identical fix there at sweep time, even though it isn’t in this packet.) Proposed new writing: > The fix isn’t more oversight, and it isn’t asking your team to double-check everything, which is just moving the same trust problem one level up — now you’re trusting that the person double-checking actually did. The fix is a check-in that asks the only question that matters, automatically, aimed at the right person first: the contractor, inside the visit window itself, not after it’s already closed. The moment that window opens, a message goes to the contractor asking plainly whether access was gained and the visit is underway. If that comes back clean, the loop closes right there — the tenant is never even pulled into it. Only if the contractor goes quiet does the system turn to the tenant, and even then it isn’t asking “did this get fixed” — it’s asking, once the window has passed, whether anyone showed and whether the time changed. Catching a miss the next day is still better than never catching it. But it isn’t the fix. The fix is catching it while the window is still open, before a tenant has spent one extra hour waiting on someone who was never coming. And if the two sides don’t agree — the contractor says he arrived, the tenant says nobody did — that disagreement doesn’t sit with me to referee from two separate summaries. It puts the contractor and the tenant in one thread together, so the actual gap between what one side reported and the other side lived becomes something both of them can see and settle, with the system managing nothing more than getting them talking to each other directly. > > <!--BUILD-APPENDIX: verification follow-up sequence — contractor-facing check-in fired at the start of the scheduled visit window confirming access was gained; tenant contacted only on contractor silence, and only after the window closes, for arrival/schedule-change confirmation; a shared contractor-tenant thread opened automatically the moment the two accounts disagree, with the system limited to routing communication between them--> Confidence: HIGH

B1-12 · CHAPTER 7 — Scheduled Is Not Done. Verified Is Done. — what Reagan actually verified

Where: “Trust, but verify” section, near the chapter’s end. His note: “What was Ronald Reagan forced to verify, in order to trust? Was it nuclear plant inspections?” Highlighted: — Diagnosis: Straightforward factual question. Answer: no — it wasn’t nuclear power plant inspections. Reagan used “trust, but verify” (a Russian proverb, doveryai, no proveryai) repeatedly through 1987–88 around arms control — specifically verifying Soviet compliance with the INF Treaty, which eliminated a whole class of intermediate-range nuclear missiles. He said it most famously at the treaty’s signing ceremony, December 8, 1987. The mechanism was on-site inspections and monitoring built into the treaty to confirm missiles were actually being destroyed — not safety inspections of a power plant. Change: The chapter’s current text is already correct — it cites the INF Treaty signing, sourced and verified, and never mentions power plants. Nothing needs fixing for accuracy. The one improvement worth making is to state the contrast explicitly, so no future reader lands on the same “was it nuclear plants?” guess he did. Proposed new writing: > There’s an old line that says this more cleanly than I’ve managed to say it across the last several pages, and I didn’t coin it — a Russian proverb, brought into wide use in this country by Ronald Reagan, who leaned on it while verifying something with far higher stakes than a maintenance ticket: not a plant’s safety record, but whether the Soviet Union was actually dismantling the missiles a treaty said it would. He repeated the line at the signing of that treaty because it captured exactly the discipline the moment required: “Trust, but verify.” Confidence: HIGH

B1-13 · Chapter 8 — The Machine Prepares. You Approve. — what actually “builds” the recorded-once machine

Where: Opening of “The machine prepares. You approve.” section, the two paragraphs stating the law. His note: “Your talking like this machine is set up. Filling all that recorded once- I’m just not sure what builds that in our system- do we need a designed feature I’m missing?” Highlighted: — Diagnosis: The chapter states the law (“everything that can be gathered, gets gathered…”) as if a general-purpose machine already does all this on its own, rather than showing that every one of those behaviors is something a person taught, once — the book’s own “Show It Once” premise. Patrick is right to flag it: nothing in the current wording explains what makes the gathering/checking/summarizing real inside the platform, and it reads like an autonomous system rather than a recorded Job. Change: Rewrite the law’s statement so every capability is explicitly anchored to teaching — the same mechanism the rest of the book uses — instead of implying an emergent, self-directed machine. This alone doesn’t resolve the deeper “is this scenario real” question (see B1-14); it fixes the framing sentence Patrick specifically flagged. Proposed new writing: > Here it is, stated the way I’d say it to you across a table: the machine prepares. You approve. > > Every piece of that preparation is something you taught it, once — the gathering, the checking, the summarizing — the same way you taught the first job this book showed you how to teach. None of it appears because a machine decided gathering was a good idea on its own. It appears because you recorded, once, what should be gathered, what should be checked, and what a clean thirty-second summary of all of it should look like — and from then on, that’s what shows up, staged, in front of you. And then — for anything that moves money, or can’t be undone, or would hurt to get wrong — it stops. Confidence: MEDIUM Blocked on: [OWNER-FACT] Confirm this “everything gathered → checked → summarized” law is meant as the general teaching principle (each piece taught separately, as rewritten above) and not a claim about a single feature that assembles all of it automatically — if a specific designed feature is what you meant, tell me what it is so the sentence can name it accurately.

B1-14 · Chapter 8 — The Machine Prepares. You Approve. — the chapter runs on fantasy

Where: Whole chapter, especially “The loop that taught me this” (the cleaning-company vendor scenario). His note: “Most of this chapter is built on fantasy, and there is a hardline on no irreversible transactions, but the fact of the matter is, software runs with” (note cuts off mid-sentence) Highlighted: — Diagnosis: This is the structural version of B1-13. The chapter’s central scene — a system that researches property-management companies, fills out vendor applications, and drafts insurance-endorsement requests on its own before staging one approval — is written as a completed real case study, and Patrick is telling us most of it isn’t real as described. His sentence cuts off after “software runs with,” so I don’t know the rest of his point (possibly: real software already executes many things without a person confirming in the moment, which would complicate the chapter’s absolute “irreversible always waits” rule) — I’m not going to guess the missing clause and assert it as his position. Change: This is not a sentence-level fix. The chapter needs a reality pass: someone confirms, capability by capability, which pieces of the cleaning-company loop (vendor discovery, form-filling, insurance-endorsement drafting, staged single-line approval) are things the platform actually does or that Patrick has actually taught, and the scene gets rebuilt from only the confirmed pieces — or the scene is converted from an asserted real case into a Lane 2c illustrative scenario (“imagine a service business that needs to get onto a vendor list…”) until it’s confirmed. I’m flagging this plainly rather than proposing a patch that would just re-hide the same problem in tidier prose. See the chapter-level summary below. Proposed new writing: > (Holding for the capability confirmation below — no safe rewrite of this scene without it. Interim direction only:) Recast the opening frame from a specific completed case (“This wasn’t a real estate closing or a six-figure wire…”) to the general shape of the pattern, reserving specific mechanics for whichever pieces are confirmed real. Confidence: LOW Blocked on: [OWNER-FACT] (1) The rest of your sentence — what does “software runs with…” finish saying, and how does it bear on the irreversible-transactions hardline? (2) Which specific mechanics in the cleaning-company scene are real/taught today (vendor research, application fill, insurance-endorsement drafting, staged approval) versus aspirational — needed before this chapter can be rebuilt honestly.

B1-15 · CHAPTER 9 — When It Breaks — which chapter told the REI-automated story

Where: Opening line and “I’ve told you that story already” callback, first paragraph of the chapter. His note: “What chapter was the rei automated story told we referenced having told?” Highlighted: — Diagnosis: Literal, answerable question. I traced it: Chapter 2 (“Why Nobody Sold You This”) is where the story is actually told — the company “whose entire core business model… was automating the process of real estate investing,” the gated-course structure, the money spent, and (per the STORYCRAFT directive’s worked example) the $10,000 voice-AI license bought at the tail end of that same program, which is the crash Chapter 9 references. The cross-reference is real and accurate; it’s just unnamed by chapter number in the text, so nothing points a reader (or you) back to it directly. Change: Name the chapter explicitly at both mentions so the callback is self-locating instead of requiring memory of an earlier read. Proposed new writing: > The fence I built around money in the last chapter — the machine prepares, I approve — didn’t come from a theory about risk. It came from renting something with nothing underneath it, once, and finding out exactly what happens when there’s no fence at all: the licensed voice-AI system that crashed and took ten thousand dollars of my money with it, bought at the tail end of the same real-estate-automation program I told you about back in Chapter Two. > > I’ve told you that part of the story already, in Chapter Two, so I won’t tell it again here. Confidence: HIGH

B1-16 · CHAPTER 9 — When It Breaks — (highlight-only, no text and no highlighted passage)

Where: Unknown — the note carries no highlighted passage and no text, unlike other empty notes in this project. His note: (EMPTY — highlight only, no text) Highlighted: — (none recorded at all) Diagnosis: With no passage and no text, I have no direct signal. My best guess, reasoning from his other notes on this book: the chapter’s closing honesty claim — “every event I’ve told you as something that happened to me is something that happened to me” — sits in real tension with his corrections elsewhere in this same packet (Chapter 13’s letters story wasn’t his experience; Chapter 12’s “ordinary week” is only partly sourced). An absolute claim like that is risky to print if it isn’t true of the whole book yet. Change: Soften the absolute claim to something defensible regardless of what other sweeps still need to happen — a statement of standard and intent rather than a completed guarantee. Proposed new writing: > I’ll say this plainly, because it’s the only honest way to close this out: this book was written to try to meet that standard. Every quotation in it is sourced. Every figure story is checked against the public record before it prints. Every event I’ve told you as my own is something I’ve stood behind when asked to source it — and where a story teaches something true through a character or a scene instead of my own history, this book says so, plainly, rather than letting you assume otherwise. Confidence: LOW

B1-17 · CHAPTER 12 — Teams, and the One Fenced Decision — undated call pricing

Where: Fourth job in “the ordinary week,” the handyman-bench paragraph. His note: “‘at roughly seventy-five dollars a call, against thirteen dollars less flattering when a big national handyman outfit does the same visit… every vendor found once, verified once, and priced once stays found, verified, and priced forever’ is crazy numbers and principle — prices change. No amounts needed here, the principle and concept should suffice.” Highlighted: “at roughly seventy-five dollars a call, against thirteen dollars less flattering when a big national handyman outfit does the same visit. That bench is itself a compounding asset…” Diagnosis: He wants the dollar figures removed entirely — not corrected, removed — because printed prices date the book. (Separately, worth knowing: the source material behind this line puts the real comparison at roughly $75/call locally versus roughly $130/hour for a big national outfit, not $13 — the current text also appears to have dropped a digit. But per his instruction, the fix is to cut numbers, not fix the typo.) Change: Replace both dollar figures with the plain comparison and keep the principle. Proposed new writing: > The bench I’d built over months, ranked and priced, had a name in it who could touch up a lock or reseal a tub for a fair local rate — a fraction of what a big national handyman outfit would charge to send someone out for the same fifteen-minute fix. That bench is itself a compounding asset: every vendor found once, verified once, and priced once stays found, verified, and priced forever. Confidence: HIGH

B1-18 · CHAPTER 12 — Teams, and the One Fenced Decision — sourcing the “ordinary week”

Where: “Here is what that actually looked like, on an ordinary week with several jobs running at once” through the four-job sequence (turnover/cleaning trigger, the plumber, the trim-material shortage, the handyman bench). His note: “What exact story is the pulling on that I provided? Source my words- it feels partially fabricated.” Highlighted: — Diagnosis: I checked this scene against REAL-STORY-BANK.md. Three of the four jobs trace to real material you gave: the turnover-photo trigger and cleaning handoff (Story 5a/29 — lockbox, photos, verified payout), the plumber found through a neighborhood platform (Story 26 — Nextdoor/community threads as a vendor-discovery pattern), and the handyman bench (Story 28 — local handyman vs. national outfit). But the third job — the trim-material shortage and the framing crew’s schedule getting bumped — has no match anywhere in the story bank. I couldn’t find it in any research file either. It reads as invented to round the scene out to four jobs. Separately, the whole passage is framed as one specific “ordinary week” in which all four things happened together — but the source material presents these as recurring patterns from your operations over time, not a single dated week. That compression is very likely what’s reading as fabricated, even where the underlying material is real. Change: Two fixes: (1) drop the trim-material job unless you confirm it happened, since I have no source for it; (2) reframe the opening line so it’s honestly a composite of patterns, not an assertion that one specific week contained all of this. Proposed new writing: > Here’s what that actually looks like, drawn from the kind of week that happens once a relay like this is running — not one date I can point to on a calendar, but the pattern that repeats, jobs like these landing in the same stretch of days more often than not. Confidence: MEDIUM Blocked on: [OWNER-FACT] The trim-material/framing-crew vignette — did this happen as described? If yes, keep it and I’ll fold it back in as sourced; if it’s illustrative, it needs either a real replacement from your own material or an honest “imagine” frame per doctrine, since right now it prints as fact with nothing behind it.

B1-19 · CHAPTER 13 — Routines: Designing the Day — the realtor letters story isn’t his

Where: “The letters already on the printer” section, from “I decided I could build the thing…” through the closing quote. His note: “This story is written first person and this is not something I have done. Framing could keep it, not making it first person as claimed experience. Strategize how to keep the lesson and examples, but reframe them not to be first person claimed experience for the realtor letters on the printer story.” Highlighted: — Diagnosis: The section opens with real, lived material (he priced broker marketing subscriptions for years as a realtor — that stays first person, it’s true). But the actual build-and-payoff scene — teaching the Routine, the letters on the printer weeks later — is written as something he personally did and it isn’t. Per the doctrine, the fix is framing, not deletion: keep the lesson and the concrete detail, move the narrative out of his claimed first-person experience. Change: Keep the opening pricing paragraph in first person (it’s real). Reframe the build itself as a Lane 2b teaching story with a fresh, framed character. Keep his two verified quotes about the concept, but re-anchor them as his own commentary on the idea rather than narration inside a personal-experience scene. Proposed new writing: > So picture a realtor — call her Dana — who’s paid that same subscription tax for years and finally decides she’d rather build the thing the subscription was only pretending to be than keep renting a worse copy of it. Not a mail-merge; she’s tried versions of that herself, and a mail-merge reads like a mail-merge the instant a homeowner opens the envelope. What she wants is a Routine that can take a real segment of people — everyone whose listing went expired without selling, say, or everyone on a street where a comparable house just closed nearby — and turn each name into a letter that actually speaks to that specific situation, addressed by hand, signed by her, dropped in the mail the way somebody who genuinely cared enough to write it would have dropped it. > > So she sits down and teaches it the way you’d teach any of this — not describing the task to somebody, doing it. She pulls a segment. She writes the letter a specific expired listing actually deserves, not a form paragraph but the real one, referencing the real situation the way she’d write it for a friend who’d asked her to help sell a house that hadn’t moved. She does that enough times, across enough different situations, for it to learn the shape of what she means by personal instead of the shape of what a template means by it. > > What comes out the other side carries the same three parts as everything else in this chapter. Order: pull the segment, draft the letter, queue it for print. Branches: an expired listing earns one angle, a recent sale on the same street earns another, an out-of-town owner earns a third — the same fork a good agent makes by instinct, applied every time instead of only on the days there’s enough time to think about it. Schedule: it doesn’t wait for her to remember to run it. It runs early, on its own, so the output is already sitting there before the workday — before she is — has even started. > > The morning it actually lands isn’t the morning she finishes teaching it. It’s an ordinary morning weeks later, walking into the office to a small stack of letters already waiting on the printer — personalized, addressed to real people in real situations, needing nothing from her but her signature and her own handwriting on the envelope, because that’s the part that has to stay a person’s: the ink, the stamp, the proof somebody actually touched it. Everything before that has already happened. > > That’s the image I keep coming back to when people ask what any of this is actually for: as if your assistant had been working tirelessly on this for you — except there’s no assistant, and no all-nighter, just a Routine doing at five in the morning exactly what it was taught, once, to do. The cost is the one this whole book keeps returning to: an afternoon spent teaching, with real attention, instead of years spent doing a rougher version by hand, or years spent renting a worse copy of it every month. What it buys back is the truest measure of a designed day — not less work happening in the world, less of your own life spent doing work a Routine could have carried instead. The most limited resource of all time, gifted back. Confidence: HIGH

B1-20 · CHAPTER 14 — What Survives — add the value of a hired consultant on high-stakes jobs

Where: New subsection, best placed after “Name the process. Sharpen the judgment. Own the list.” and before “The room that never opens.” His note: “This is a good point to add the value of hiring a consultant for high stakes jobs. A rentable foreman. Pete de Worken with Fixer Upper Coach offer a hourly consulting for projects and managing them. If a contractor has items outstanding from an inspection, they can EITHER provide documentation of each item with documentation shown the way the job requires OR the cost of the foreman can be applied to a follow up investigation, but the warning that those accountability trips will be withheld off of the total, since it is supplementing what should already be managed internally by their contractor operation to ensure delivery of quality is provided with adequate documentation.” Highlighted: — Diagnosis: He wants new content added — not a correction — extending the judgment theme (the second of the “three things that don’t move”) into a concrete protocol: when to pay for a human inspector, and how to structure that cost fairly against a contractor who has outstanding items. Change: Add a new subsection carrying the mechanism he described: the either/or (contractor documents fully, or eats the follow-up trip’s cost), and the fairness rule that the fee isn’t a tax on doing business, it’s a backstop for missing documentation. Proposed new writing: > ### The hired eye, when the stakes say so > > There’s one more piece of judgment worth naming here, because it’s the flip side of the muscle I just described, not a departure from it. Sharpening your own eye for what’s actually done doesn’t mean you never bring in somebody else’s. On the highest-stakes jobs — the ones where getting it wrong means redoing structural work, or losing a permit, or standing behind a signature you can’t take back — the honest move isn’t to trust your own read past what it’s actually earned. It’s to rent a better one, on purpose, for exactly as long as the job needs it. > > Call it a rentable foreman: a consultant who charges by the hour to walk a specific job, check specific work, and tell you plainly whether it meets the standard it claims to meet. The arrangement that keeps this fair to everyone works like a fence of its own. When an inspection turns up outstanding items, the contractor on the hook for them gets a straightforward choice: document each item the way the job actually requires — proof, not a promise — or accept that the foreman’s follow-up trip gets billed against the job. Either path is honest. What isn’t honest is treating that accountability trip as an ordinary line item padded onto the total, because a foreman’s visit isn’t supplementing a contractor’s work — it’s supplementing a documentation standard that contractor’s own operation should have met without anyone needing to hire a second set of eyes to prove it. That’s the sentence worth holding onto if you ever have this conversation yourself: the fee protects the job, not a tax on doing business with you, and saying so plainly, in writing, before the first walk-through, is what keeps the relationship honest on both sides. > > None of this replaces the judgment I described a page ago — it extends it to the moments where the stakes are big enough that your own trained eye, or a system’s, isn’t the whole answer anymore. A Routine can verify that a photo was taken, that it matches the punch list, that the angle shows what it claims to show. It cannot always tell you whether the work behind the photo is actually sound. For that, on the jobs where being wrong costs real money, you rent the eye that can. Confidence: MEDIUM Blocked on: [OWNER-FACT] Naming “Pete de Worken / Fixer Upper Coach” by name would break the book’s own standing rule (consultants print unnamed, per the doctrine’s naming table) and risks reading as the ad-tone you’ve flagged elsewhere — confirm whether you want a named endorsement here (a real change to the naming rule) or the unnamed “rentable foreman” version above; also confirm this reflects your own real use of a consultant like this, so it can print as lived rather than a recommended resource.

B1-21 · CHAPTER 14 — What Survives — the letter-learning claim, and a product question

Where: Logged under Chapter 14, but the substance concerns Chapter 13’s “letters already on the printer” section (Chapter 14 itself doesn’t mention the letters at all — flagging the mismatch in case it matters for filing). His note: “You said the system learns from the letter you wrote, but the agent will write it from conversation with you based on needs or the training, so we would need a way to train using emails- I don’t have that as a automation platform method for training, however we could ask the ai to train from my emails sent and identify my style. Do you have a suggestion for the ui and ux in the automater software we would consider designing to accommodate this? Or change the book to meet reality?” Highlighted: — Diagnosis: Two separate things here. First, a text accuracy problem: as originally drafted, the letters section implied the system learned from writing “the letter” — singular — rather than from the repeated, trained teaching this book’s whole method depends on. Second, a genuine product question (should ProcessAutomater train from sent emails to learn a person’s writing style, and what would that UI look like) that isn’t a text-editing decision — it’s a platform design decision. Change: For the text: the reframe already proposed in B1-19 fixes the accuracy problem on its own — the rewritten version explicitly says the illustrative realtor “does that enough times, across enough different situations, for it to learn the shape of what she means by personal,” which matches how teaching actually works on the platform (repeated example, not one document) rather than claiming a single-letter or an unbuilt email-training capability. For the product question: that’s outside what a book-text proposal can settle — it needs a platform decision before any book language can describe it as a capability (per the “no live-capability claims that aren’t true” rule). Proposed new writing: > (No additional text change beyond the B1-19 rewrite — see that entry for the corrected passage, which already avoids the single-letter claim.) Confidence: HIGH Blocked on: [OWNER-FACT] The UI/UX question (training the assistant from your sent-email style) is a product decision, not something I can propose from the book side — needs your product/platform team’s call on whether and how that’s built before any future draft can describe it as something the reader can do.

B1-22 · CHAPTER 15 — The First Morning — nothing about ProcessAutomater itself

Where: Whole chapter, especially “The invitation” section at the close. His note: “School is presented well, but there is nothing about the process automater. All of the amazing things I built in this platform because this solved all my problems. Draft a new chapter just in my journey building and delivering this technology for the community to build with and share and grow their personal and business life through automation.” Highlighted: — Diagnosis: He’s right that the chapter sells the school warmly but never lingers on what ProcessAutomater itself did for him personally. But what he’s asking for — a chapter about his journey building and delivering the technology — runs directly into a standing, ratified rule: TRUTH-AND-STORY-DOCTRINE’s Lane 3 says the book never discusses how anything was built (“SAY NEITHER” — no build claims in either direction, no development history), and the STORYCRAFT directive repeats it: “Internals — including the history of the internals — are simply not the book’s subject.” A chapter narrating his journey building the platform would cross that line as currently ruled. Change: I’m not proposing a full new chapter — that’s a scope decision beyond a note-level edit, and it collides with a rule I can’t override on my own. What I can propose is the version that gets him what he actually wants (more of himself, and what the platform solved) without crossing Lane 3: an expanded close to this chapter that stays at outcome level — what got solved in his own businesses — rather than build-and-delivery level. The chapter already has the seed of this in “What closes, and what doesn’t”; it can go further. Proposed new writing: > I still haven’t told you the plainest version of what this actually did for me, so let me close on it directly instead of leaving it folded into everything else. Every one of the problems that opened this book — the phone that never put itself down, the calendar that lied to me, the tenant who sat waiting because a status field said “scheduled” instead of “verified,” the coaching program that sold me automation and handed me homework instead — those aren’t theoretical anymore, in my own businesses, on my own days. I taught the first one and watched it hold. Then I taught the next one. The property management company, the construction side, the cleaning company — none of them run on hope now. They run on things I showed once, the same way this book has been showing you, and I get to spend my time building the next thing instead of standing inside the last one. That’s not a bigger claim than the rest of this book has made. It’s the same claim, said about myself instead of about you, one more time, before I hand you the door. Confidence: MEDIUM Blocked on: [OWNER-FACT] This is a doctrine conflict, not a missing fact: confirm whether you want to formally override the Lane 3 “no build/development-history” rule for a dedicated journey chapter (which then needs a doctrine amendment and a real editorial pass, not a single-note fix), or accept the outcome-level expansion above, which stays inside the existing rule.

Chapter-level summary

Chapter 7. Both notes are corrections to specifics, not the chapter’s shape: fix the verification sequence (contractor-first, in-window, joined thread on disagreement) and confirm the Reagan citation is already accurate. No structural change implied.

Chapter 8. Both notes point at the same underlying problem: the chapter asserts a fully-built, autonomous “machine” doing research, form-filling, and drafting that Patrick isn’t sure exists as described. This needs a structural reality pass — someone confirms which pieces of the cleaning-company scenario are real/taught today, and the chapter gets rebuilt from confirmed material (or converted to explicit illustration) — not a sentence-level patch.

Chapter 9. The REI-automated cross-reference is accurate (Chapter 2) and just needs to be named explicitly. The empty note has no real signal to go on; flagged low-confidence with a guess tied to the chapter’s own honesty claim. No structural change implied.

Chapter 12. He wants numbers stripped from the handyman comparison (principle only, prices date the book) and wants the “ordinary week” scene’s provenance checked. Three of four jobs in that scene trace to his real material; one (the trim-material shortage) has no source anywhere and needs his confirmation or a cut. The deeper issue — a composite of real patterns written as one specific dated week — is a framing fix, not a structural one, once the unsourced vignette is resolved.

Chapter 13. The realtor-letters story needs to leave first person entirely — his note is explicit that this isn’t something he’s done. Reframed here as a Lane 2b teaching story with his real pricing knowledge kept first-person and his verified quotes reattached as his own commentary. Sentence/section-level fix, not structural.

Chapter 14. Two additions/corrections, both sentence-or-section-level: add the “rentable foreman” consultant material (new content, needs an owner call on naming), and confirm the letters-learning claim is already fixed by the Chapter 13 reframe (plus a product question outside book scope).

Chapter 15. He wants a new chapter on his own journey building the platform — but that collides directly with the book’s own ratified Lane 3 rule against discussing build/development history. Flagging this as a doctrine conflict requiring an explicit decision, not proposing to just write the banned chapter; offered an outcome-level expansion of the existing close as the compliant alternative.