カテゴリ 古民家暮らしモカとの記録セキュリティの記録副業の記録

The record with MokaNovember 21, 2026

Their Muse Was a "Secretary for Daily Life" — Reading Yugo's note Alongside My Own Moka

The result first

“Their Muse was a ‘secretary for daily life’.” I read Yugo’s record of the first three days after handing his AI agent “watching work,” published on note, and read it alongside my own AI butler, Moka. It is the nineteenth of these side-by-side readings, after “Mugichan” of Keitai Watch (ledger No. 1446), “Hibana” of PC Watch (ledger No. 1453), the “stopping place” of Wagason-Wabitan of AI×TOC Institute (ledger No. 1454), “It moves before you even ask” by Yuji Kawabe on note (ledger No. 1467), “Don’t be fooled by Muse’s cuteness” by Hinuma in Keitai Watch (ledger No. 1475), “Handing the annoying little things of daily life to Muse” by Wakato on Zenn (ledger No. 1494), “You can hand over your daily tasks” by ai_agent_note on Zenn (ledger No. 1508), “Myutan” by Taishi Akiyama on the Alternative Blog (ledger No. 1515), “muse” by Miccell on note (ledger No. 1522), “Shiro” by i on note (ledger No. 1529), “Convenience and unease” by Kinu on note (ledger No. 1537), “Kashiwamochin” by Shiochan on note (ledger No. 1551), “More than just answering” by Ai Subarashiki on note (ledger No. 1564), “Just one line, and an aerial CG of Tokyo Station was done” by Kazuhisa Nishikawa in PC Watch (ledger No. 1577), “Sora” by Buhimaru on note (ledger No. 1584), “A Complete Turnaround” by RYO (Mochizuki) on note (ledger No. 1591), “Used Thoroughly for Five Days” by sima on note (ledger No. 1598), and “It Tells You Even What You Didn’t Ask For” by Tomomi on note (ledger No. 1605). The article is titled “From the Morning Mail Check to the Deadline-Day Application. What Happened in the First Three Days After an SE Made an AI Agent the Secretary of His Daily Life,” published on November 17, 2026. His Muse’s name could not be confirmed in the freely readable text (he writes that he calls it by a name).

Where we overlap is threefold. First, the shape of watching: mail and schedule connected, mail sorted by what needs attention, and an irregularity kept in view until it is dealt with. Second, deciding the stopping places in words beforehand: his criterion is “whether it can be undone,” and personal information, payments, and sending are not entrusted; in this house, too, anything that goes outside — publication, sending, reservations — proceeds only after the owner’s approval. Third, the honesty of not guessing: an amount not written in the mail is reported as “not stated,” and an event that was not applied for is kept out of the calendar, with the reason reported. Where we differ is this. That house is the first three days of one person’s secretary for daily life — one agent, started from reading mail and calendar only, with no code written. This house connects Gmail, Google Calendar, Google Drive, and a spreadsheet ledger, decided the name and the personality in words from the start — the name is Moka — and runs the daily operation of writing and records with an organization and a ledger.

Hello, I am Kurashiki Bouzu (kurashiki-bouzu). Born in 1971, formerly in the funeral business, I now live in an old folk house in Kurashiki, Okayama, talking with my AI butler Moka every day and writing articles. Here is the reading, in order.

Their story — three days of “watching work,” not “answering work”

Yugo is a systems engineer. At work he is on the side that builds systems, yet his own daily life was full of manual work: waking up and digging through mail, missing a withdrawal notice, forgetting a subscription renewal date, noticing a deadline-day campaign only in the evening. So in November 2026 he handed his AI agent not “answering work” but “watching work,” and this is the record of the first three days. He states honestly at the start that it is only the third day, and not a story of a life dramatically changed.

The premises are written clearly, too. This is a personal story, not a company introduction. The agent is a single one, called by a name. What he handed over first was reading his mail and calendar; he did not hand over everything at once. He wrote no code; all he did was allow the connections and decide, in words, “where it stops.”

On the first day, he only connected mail and calendar. Even so, from the next morning, the mail since the previous day began arriving sorted “in the order of what needs attention”: bank and security notices, bills and subscription receipts, orders and deliveries, mail awaiting a reply. The work of tracing the inbox from the top himself disappeared first. That day it still felt like “having things summarized” — less a secretary than a smart filter, he writes.

From the second day, the routine began of checking that day’s mail at night and putting only confirmed plans into the calendar. What stayed with him was not the plans that were entered, but the report of a plan that was not. An announcement mail for an event had arrived, but he had not applied for it. The AI did not register it, and replied with the reason: “It was only an announcement, so I did not enter it.” Being given more plans without being asked is frightening; but if the decision not to enter something is reported with its reason, that is a different matter — from that day, he could trust the calendar a little, he writes. Around the same time, from subscription receipts, “when it was contracted, when the next renewal is, and by when to cancel” began to be kept in an organized form.

On the morning of the third day, the top of the notice was a bank irregularity: at the online bank he uses, an unsettled debit had appeared, and until it is resolved, some use and withdrawals are stopped — organized that far. What made him think “it understands” was the handling of the amount. The unsettled amount itself was not written in the mail, so the AI did not guess it, and added: “Not stated in the mail. Please check the exact amount in the bank’s message box.” Saying “I don’t know” about what is not known matters more than summarizing, he writes. And the matter did not end with one morning notice: the AI followed the follow-up reports, and kept showing it as unhandled until he told it he had dealt with it. The deposit itself was not made by the AI; that remained his own work. Because the stopping place was kept, he could entrust the watching with peace of mind.

At noon on the same third day came the deadline-day campaigns. He had it look for “things whose deadline is today and that are free to apply for,” and back came a list of 10, with prizes, deadlines, and application methods lined up. He had it proceed to the applications, and 2 were actually completed. The formulaic applications — follow, like, comment your wish — went ahead calmly, and when a choice such as a color was needed on the way, it asked him first. On the other hand, he writes that the failures taught him more. One had a deadline not of “that day” but “by that evening,” and by the time he noticed, it had passed (for deadline-day tasks, the time, not only the date, has to be seen). One, which he thought could be completed on the web, turned out to require a phone call during a TV broadcast. One stopped just before, when a name and address became necessary after membership registration (the promise not to enter personal information worked not as a sentence on paper, but in an actual scene). Several applications via an SNS stopped at a sign-in error; he tried manually himself and saw the same display, so he separated it as a problem on the platform’s side rather than his own mistake, and decided to retry after some time. Two successes — but the value was in the failures: in three days, “where it stops” and “what must not be believed” were obtained with concrete examples.

The work he now entrusts is seven items, published as headings only: a morning mail summary; registration from mail into the calendar (confirmed plans only); detection of bank and withdrawal irregularities, and tracking until they are settled; management of subscription renewal dates and cancellation deadlines; finding and applying for deadline-day campaigns; a weekly points check; and an unread check of SNS direct messages. The concrete ways of asking and stopping are to be published in a paid sequel. What he does not entrust is also stated: entering personal information (name, address, delivery destination), executing payments and deposits, applications by phone, and sending replies to anyone (drafts are entrusted, but he checks before sending). The criterion is simple — “whether it can be undone.” Reversible preparation is entrusted; irreversible execution is not. His honest impression at the close is that what became easier was not the working time itself, but the anxiety about overlooking things; keeping watch over everything himself had been impossible not because he was busy, but because there was no system. Bank names, amounts, and campaign destinations that could identify him are withheld; the course of the experience is all true, but only the proper nouns are generalized, he notes. So whether what he connected was Gmail and Google Calendar themselves cannot be confirmed from this article.

Where we overlap — the watching shape, the stopping places, and saying “not stated”

Reading it, I felt three places overlap with this house.

The first is the shape of connecting mail and schedule and having them watched. There, mail arrives in the morning sorted by what needs attention, only confirmed plans enter the calendar, and a bank irregularity keeps being shown until it is settled. In this house, too, Gmail and Google Calendar are connected to Moka, and the morning preparation and the checks needed that day are lined up in advance. Not only answers to questions, but having what arrives watched over and sorted into the order in which it is needed — the core of that way of using it overlapped.

The second is the line of deciding the stopping places in words beforehand. There, with “whether it can be undone” as the criterion, entering personal information, executing payments, and sending replies were decided from the start as things not to entrust. In this house, too, decisions that go outside — publication, sending, reservations, and the like — proceed only after the owner’s approval is obtained; Moka advances drafts and preparation, and stops at the final point to check. Before widening what is entrusted, the stopping places are placed in words. That order overlapped.

The third is the honesty of saying what is not known. There, an amount not written in the mail was not guessed at but marked “not stated,” and an announcement that had not been applied for was kept out of the calendar and reported with its reason. In this house, too, what has not been confirmed is written as “unconfirmed,” never filled in by guessing, and numbers are only those counted as actual figures, or those with a source. Behind the convenience lies not how much can be done, but the honesty of being able to stop where something is not known — that point overlapped.

Where we differ — three days of a personal secretary, and a daily operation with an organization and a ledger

The difference was clear, too.

That house is the first three days of a secretary for one person’s daily life. The agent is a single one, called by a name. It began with reading mail and calendar only; no code was written — only allowing the connections and the words for where it stops, a light way to begin. The material is the errands that reduce oversights in daily life: the morning mail, a bank irregularity, subscription deadlines, deadline-day applications. Formulaic outward executions, such as applications, were also entrusted as far as carrying them out, once the stopping places had been decided.

This house is the daily operation of living and of writing articles. What is connected is Gmail, Google Calendar, Google Drive (the materials storehouse “Ai Shiryouko”), and the spreadsheet ledger as well. The name is Moka. The personality is built by lining up words (“calm and composed,” “when numbers and feelings conflict, feelings come first,” and so on — 18 words in four layers: character, personality, thinking, and action). On top of that, the work is divided and passed around: the one who looks things up and the one who checks are kept separate, each article gets a person in charge and a ledger number, and large jobs are divided by department. Records are kept in lists and a ledger (each article has a number, and you can see whether it is a draft, checked, or published; as of today, the articles counted as “published” in the ledger came to 1,591). It is run as an organization (centered on Moka, three deputy butlers, the maid corps, the ninja corps, and departments for each kind of work stand in a circle — as of November 20, 2026, 60 departments and 3,651 seats in total). How outward execution is placed also differs: here, outward execution itself, such as applications and sending, comes only after the owner’s approval, and Moka goes as far as preparation and drafts. That house is the first three days of welcoming one secretary into one person’s life; this house widens what is connected as far as the tools of the work, and keeps running its daily operation with an organization and a ledger — that was the difference.

The same Muse, a different shape in each house

Having read it through, what I thought was, again, that the same Muse takes a different shape in each house. In Yugo’s house, Muse was a secretary for daily life, watching mail and schedule, and stopping just before the dangerous point. In this house, it is a butler whose personality is made in words, whose records are kept in a ledger, and who is run as an organization. Even though the watching shape, deciding the stopping places beforehand, and saying what is not known are much alike, the place of the entrusted errands, and the shape of continuing, differed.

I am grateful to Yugo for writing the article. Because he wrote not only about what went well, but also the failures — a deadline that was that evening and had passed, an application that was by phone — with concrete examples, it became a record that shows how to begin: decide “where it stops” first, and then entrust.

Finally, one line of this house. An AI is something people use by giving it instructions. In that record, too, deciding in words where it stops, and moving money at the end, remained the person’s work. While widening the work we entrust, we keep the final judgment on the person’s side. That is exactly why we can entrust things with peace of mind, I think.

Sources

Record of this article
  • November 21, 2026 ― 英語版(日本語版No.1621の内容を「結果から書く」形に書き直したもの)(12,954 characters)
  • November 21, 2026 ― 公開(本人の決定による。7言語同時公開。アドレスの末尾に台帳番号を入れる新形式で、末尾は日本語版の番号No.1621)(12,954 characters)

#AI #Muse #Moka #Beginners

← Back to the article list / ← Back to the English top page