🔍 Advertising Regulation in Japan (Promotional Material Review) and Artificial Intelligence JP/EN
Ethics · Regulation · Technology — Pharma Practice Notes
Educational·10 series × 10 episodes

AI Literacy── Eleven stages of working with AI, from a first spark to running it, in 10 series of 10 episodes

When AI does more of the work, what does the person directing it need to be good at? Drawing on the operator's own record of working with generative AI, this series names eleven stages, from a first spark and early conception, through locating the gap between ideal and as-is, finding words and keywords for vague unease, a rough wish, a concept, logic and blueprints, to programs and running them, and sets them out in 10 series of 10 episodes. One episode a day, over about three months.

7 of 100 published

S1Sparks and Conception7 / 10S2Ideal versus As-Is0 / 10S3Putting It into Words0 / 10S4From a Rough Wish to a Request0 / 10S5Concept0 / 10S6Making It Logical0 / 10S7Blueprints0 / 10S8Programs0 / 10S9Running It0 / 10S10AI Literacy0 / 10
How it is made The material is the operator's own record of requests, corrections and approvals with Claude since February 2026 (the operator has used generative AI since March 2023). Email addresses, server names, file locations, keys, personal and company names are removed; nothing is quoted; only recurring patterns are generalised. Every episode passes an anonymisation re-scan, a verbatim-quote check and a structure check before release.
S1 Sparks and Conception ── Turning a passing thought into work with AI
01

A Spark Can Go to AI as a Question

An idea need not become a finished request. Ask it as one sentence of goal and means, get four kinds of material and reasons against, and decide before you build.
S1-01
Read →
02

The Three-Agent Team in the First Recorded Week

Splitting work by role gives each AI output a clear verification criterion. The three-role pattern from the operator's first recorded week shows why verifiability, not volume, should guide how work is handed to AI.
S1-02
Read →
03

Start a Spark by Finding What Already Exists

Ask AI to search for existing solutions first. The list of candidates and their constraints reveals what is missing, and that gap becomes the concrete requirement for the next request.
S1-03
Read →
04

Define What You Are Collecting Before AI Collects It

Before telling AI to collect information, have it define the target first. A clear definition fixes the classification axis so that everything collected feeds straight into decisions.
S1-04
Read →
05

Let AI Inventory Your Own Expertise

Have AI read your past work and extract the structure of your expertise. The thread it finds, one you may not see from the inside, becomes the starting point for the next idea.
S1-05
Read →
06

Reviewing Only What Is Written Will Not Reduce Errors

Reviewing only the text in front of you misses the gap between source and material. The operator handed this unease to AI and had it connect cognitive bias and accident analysis into a structure.
S1-06
Read →
07

Redefine Reviewer Variance as Viewpoint Diversity

Redefine reviewer variance as viewpoint diversity, and AI can verbalize and integrate it, turning one person's review into collective intelligence. The shift in definition is the spark.
S1-07
Read →
08

Ask AI for the idea that adds a dimension

When work feels flat, ask AI for viewpoints rather than answers.
S1-08
In preparation
09

Ask 'what will it do, and what will it cost' early

Early value and cost estimates make it easier to drop weak ideas.
S1-09
In preparation
10

Keep the record that feeds the next idea

Moving every AI conversation into a searchable second brain.
S1-10
In preparation
S2 Ideal versus As-Is ── Stating the gap in a form AI can act on
01

Show 'it should work for any date' with examples

Pairing working and failing cases conveys the gap in one message.
S2-01
In preparation
02

Restate the table you wanted as a table

When AI misreads, specify the deliverable's shape instead of explaining more.
S2-02
In preparation
03

From a stale list to the hole in the system

Using a visible symptom to reach the cause: statically embedded lists.
S2-03
In preparation
04

Turn one odd section into a consistency rule

Rephrasing a local oddity as a site-wide consistency requirement.
S2-04
In preparation
05

Point to the missing day by its date

Asking by date lets AI trace the missing item to its cause.
S2-05
In preparation
06

English pages need English content

Unless stated, AI translates the frame and leaves the content untranslated.
S2-06
In preparation
07

Doubting AI's diagnosis revealed the real cause

Listing rejection reasons showed the search terms, not the supply, were wrong.
S2-07
In preparation
08

Separate 'done' from 'verified'

Have AI split its report into verified and unverified parts.
S2-08
In preparation
09

Paste the original request and ask if it was met

Checking the result against the literal request exposes design holes.
S2-09
In preparation
10

Show the ideal by naming a model example

Point to a good example, and confirm which artefact is being redone.
S2-10
In preparation
S3 Putting It into Words ── From vague unease to keywords and sentences
01

From 'make it cool' to 'tighten the letter spacing'

Turning an adjective into a measurable attribute makes it fixable.
S3-01
In preparation
02

From 'too long' to an order of argument

Converting reader discomfort into words about argument order.
S3-02
In preparation
03

It is fine to say 'I don't understand'

Ask AI to restate number-heavy reports in plain words.
S3-03
In preparation
04

Symbols a newcomer cannot read fail

Judge private shorthand by the reader's standard and rewrite it.
S3-04
In preparation
05

State the reader level as a number: 90 of 100

Give AI a numeric comprehension target instead of 'make it simple'.
S3-05
In preparation
06

Have AI translate business needs for engineers

Rewriting a business request into a specification engineers can use.
S3-06
In preparation
07

Define 'explain the essence, don't read aloud'

Turning unease about narration into a definition of tone and role.
S3-07
In preparation
08

Ask what a word means before approving

Unchecked jargon leads to wrong approvals.
S3-08
In preparation
09

Have AI state the essence of your own feedback

Turning feedback into a rule so it never has to be repeated.
S3-09
In preparation
10

What the 14 vague-word requests turned into

A table of vague words in the record and the requests they became.
S3-10
In preparation
S4 From a Rough Wish to a Request ── Turning what you roughly want into work AI can start
01

Queue ideas as reserved work

Registering new requests without interrupting the running task.
S4-01
In preparation
02

Give the goal and let AI staff the team

Delegating team composition by stating goals and permissions only.
S4-02
In preparation
03

Have AI write the hand-off note for another AI

Letting AI draft the brief another environment will execute.
S4-03
In preparation
04

List the items before building

Agreeing on the item list before any design or code.
S4-04
In preparation
05

Requests grew from 19 to 71 characters

Why terse commands became requests carrying definition-to-build order.
S4-05
In preparation
06

Set the order yourself: 1, then 3, then 2

When offered options, choosing the sequence makes the plan safer.
S4-06
In preparation
07

Japanese first, English after go-live

Stating a sequencing rule once, in a form that sticks.
S4-07
In preparation
08

How to interrupt a running task

Separating the running task from the interrupting request.
S4-08
In preparation
09

Make AI keep the request ledger and priorities

A ledger, a scoring rule and one foreground task keep requests in order.
S4-09
In preparation
10

Put a three-month request on the ledger

Registering a long-term activity with period, cadence and milestones.
S4-10
In preparation
S5 Concept ── Deciding in one sentence what to build
01

Have AI write the concept before building

Why the concept step is never skipped in classify-collect-design-review-build.
S5-01
In preparation
02

Decide from the reader's moment: today's AI in 15 minutes

Defining a section by the reader's time and behaviour.
S5-02
In preparation
03

One sentence on the screen before any algorithm

Separating the purpose sentence from the algorithm's assumptions.
S5-03
In preparation
04

Fix the topic categories first

Early categories keep collection and writing consistent.
S5-04
In preparation
05

A concept that learns from its own articles

Designing a writer that turns published work into its next prompt.
S5-05
In preparation
06

Extract success factors from 54 sources

Turning common factors into a 100-point scoring rule.
S5-06
In preparation
07

A design philosophy that evolves your old system

Redrawing an earlier algorithm at a higher level instead of replacing it.
S5-07
In preparation
08

Revert a failed concept the same day

Trying a direction and withdrawing it when quality drops.
S5-08
In preparation
09

Settling a name in three instructions

How the site name was fixed for English clarity and Japanese wording.
S5-09
In preparation
10

Put the vision on one page and get approval

Show a large vision on one page and start only after approval.
S5-10
In preparation
S6 Making It Logical ── Building with meaning, reasons and four questions
01

Write 'what it means' and 'why' separately

Separating meaning from reason turns a comparison into a decision aid.
S6-01
In preparation
02

Argue from question to conclusion without showing the frame

Using the seven-step order while keeping its labels invisible.
S6-02
In preparation
03

The screen carries facts, the voice carries meaning

The logic of never sending the same words to eye and ear.
S6-03
In preparation
04

Hunt logic errors by 14 names

Naming fallacies keeps rewrites minimal.
S6-04
In preparation
05

Define the unit before counting: one call

Cost estimates begin with what one call means.
S6-05
In preparation
06

Turn a judgement system into a parts list

Norm hierarchy, verdict vocabulary, categories, machine-human split.
S6-06
In preparation
07

'Important' only when two conditions overlap

Writing importance as the conjunction of two independent conditions.
S6-07
In preparation
08

Drop per-chapter conclusions, remove repetition

Simplifying structure so no claim is made twice.
S6-08
In preparation
09

Split roles between ML and LLM by logic

Prediction to ML, reading and critique to LLMs, confirmed by questions.
S6-09
In preparation
10

Make argument rules countable by machine

Converting argument rules into countable checks.
S6-10
In preparation
S7 Blueprints ── Components, flows and gates
01

Draw blueprints in three layers

Philosophy, then components, then execution flow.
S7-01
In preparation
02

Build what is settled; don't wait for the rest

Splitting front and back so the settled part can proceed.
S7-02
In preparation
03

Design the phone screen separately

Why device-specific design is requested separately.
S7-03
In preparation
04

Measure 100 popular videos, then design

Using measured ranges from exemplars as design targets.
S7-04
In preparation
05

Separate the slow step from the fast one

Decoupling generation from publishing and timing it to the inputs.
S7-05
In preparation
06

Put gates in the flow: one failure, no release

Pre-release gates and post-release rollback belong in the design.
S7-06
In preparation
07

Draw the off switch first

Kill switch and backups go on the blueprint before features.
S7-07
In preparation
08

Feed the hand-made good version back into the flow

Automating the layout a person made by hand once.
S7-08
In preparation
09

Design the routing between models

Routing judgement-heavy and volume-heavy work to different models.
S7-09
In preparation
10

From logic to blueprint to runbook

Carrying a rule through logic, blueprint and manual into automation.
S7-10
In preparation
S8 Programs ── Having AI build, run and verify
01

The first build: asking where each button is

Lessons from a first build done one settings screen at a time.
S8-01
In preparation
02

Paste the error message as it is

Unedited error text leads to faster diagnosis.
S8-02
In preparation
03

Free tier or your own server

Weighing free-tier sleep against server effort.
S8-03
In preparation
04

A manual that lets someone else run it

Reproducibility from the manual as the definition of done.
S8-04
In preparation
05

'Use this as the latest': rebuilding by version

Naming the version and diffing before every rebuild.
S8-05
In preparation
06

Moving from the laptop to the server

What to check when moving a local job to an always-on host.
S8-06
In preparation
07

Never paste keys into the chat

From pasting credentials to vaults and environment variables.
S8-07
In preparation
08

Inspect before you install

Scanning third-party code for malware before installing it.
S8-08
In preparation
09

Find where the lost work stopped

Recovering lost work by locating its last point in the logs.
S8-09
In preparation
10

When the server stops answering, isolate by symptom

Panel, network, console: narrowing an outage down to disk failure.
S8-10
In preparation
S9 Running It ── Automation, memory, ledgers and approvals
01

Publish at a fixed time every morning

Building daily auto-publishing from input and release times.
S9-01
In preparation
02

Find Japanese-English mismatches every day

A standing consistency check with logged results.
S9-02
In preparation
03

Turn the good run into the procedure

Recording a successful exchange and making it the standard procedure.
S9-03
In preparation
04

Save it to memory and recall it next session

Storing an unbuilt plan in a ready-to-build state.
S9-04
In preparation
05

Prevent duplication by mechanism

Turning a no-repeat rule into a check against past output.
S9-05
In preparation
06

Approve briefly, once, in a batch

Batching approval questions and answering in a word.
S9-06
In preparation
07

Never needing to say it three times

Repeated instructions become strict machine checks.
S9-07
In preparation
08

Compare options by safety

Asking which option is safest and taking the uncompromising one.
S9-08
In preparation
09

Every 'done' carries one line of evidence

Recording completion only after verification, with proof.
S9-09
In preparation
10

Report progress as a number

Tracking a long activity by published/total and a weekly note.
S9-10
In preparation
S10 AI Literacy ── Principles and practice
01

Check AI's reports against evidence

Demanding logs after a report of work that never ran.
S10-01
In preparation
02

Ask for honesty when AI changes things unasked

Asking for the account, not an excuse, after an unrequested change.
S10-02
In preparation
03

Evidence, not self-defence

Over-hedging reads as suspicious; stop at facts and grounds.
S10-03
In preparation
04

Self-review by a similar AI is not independent

Why a sibling model's critique flattered itself, and how to get independence.
S10-04
In preparation
05

Cite primary sources and always cross-check

Primary-source citations and number-by-number matching.
S10-05
In preparation
06

Delete numbers you cannot confirm

Removing unconfirmable figures and measuring source reach.
S10-06
In preparation
07

Search for sensitive data before publishing

Multiple checks for URLs, paths and keys before release.
S10-07
In preparation
08

Look at every item

Checking all items, not a sample, reduces misses.
S10-08
In preparation
09

Choose models knowing versions and billing

Understanding versions, prices and billing paths.
S10-09
In preparation
10

Eleven stages and the human role

People decide, AI builds, mechanisms verify: the whole path in review.
S10-10
In preparation