段取り · A Dandori field guide

How to choose your first AI workflow.

A ten-question self-check for finding the workflow most worth proving in thirty days. The same survey a craftsman makes before the first cut — applied to the work you'd hand an agent.

Your readiness 0/ 20 Answer the ten questions below to score your workflow.
The name

段取り — the preparation before the work.

段取り (dan·do·ri) is the Japanese word for the preparation a craftsman does before the work begins — laying out the tools, measuring the stock, and sequencing every cut so that when the blade finally moves, it moves once and moves right. It is not the work. It is everything that decides whether the work will go well.

段取り八分、仕事二分

Preparation is eight-tenths of the work; the work itself, only two.

Why the first one decides everything

Most AI projects are not lost in the building. They are lost in the choosing — in picking the wrong first piece of work, then asking good engineering to save a workflow that was never a good candidate. Choose one that is bounded, measurable, and owned, and the first thirty days produce a plain, checkable result on real work. Choose one that is sprawling, subjective, or ownerless, and no amount of engineering produces a verdict anyone trusts. This guide is the preparation before the preparation: how to choose well.

The four cuts

Before the first cut, a craftsman checks the stock four ways.

Every workflow worth proving passes four checks. Three of the four carry a single question that can't be made up for elsewhere — we call those gates.

一 · Repetition

Does it recur enough to repay the preparation?

Frequency and named cost. Preparation pays back across repetition — work you run many times a day rewards a prepared agent many times a day. Q1–Q2. No gate — rare work can still be worth proving; it simply pays back more slowly.

二 · Boundary

Does it have edges you can trace?

Rules you can write, a clear start and finish, a shape that holds still. Q3–Q5. Gate at Q4: a clear finish.

三 · Measure

Can you judge the result?

A number for "done right," systems you can reach to check it, and a way to catch a bad result before it hurts. Q6–Q8. Gate at Q6: a numeric success line.

四 · Ownership

Is there one hand to guide it?

Someone to route exceptions to, and one person who can settle what "correct" means. Q9–Q10. Gate at Q10: one accountable owner.

On the three gates

A missing edge, an absent measure, or no clear owner doesn't slow the work down — it stops it. If any gate is a hard No, no amount of strength elsewhere makes the workflow ready. Fix the gate before you count the rest.

Where to look

The best first workflow is rarely the most valuable one.

A menu of work that tends to make good early candidates — and a few that don't, yet. Read down the last column: the high-value work at the bottom isn't off-limits, it's earned. You don't hand an apprentice the finish cut.

WorkflowRecursTime to proofIf it's wrong
Meeting & call summariesDailyFastLow
Knowledge & document searchDailyFastLow
Customer support draftingDailyFastLow
Scheduling & coordinationDailyFastLow
Request routing & triageDailyFastMedium
Proposal & quote draftingWeeklyFastLow
Data cleanup & reconciliationDailyMediumMedium
Invoice & document processingDailyMediumMedium
Contract & policy summariesWeeklyMediumMedium
Financial approvals & paymentsDailyLongerHigh
Automated production operationsVariesLongerHigh

The lesson of the last column: prove the method where a mistake costs a correction, not a crisis. The disciplined execution you show on forgiving work is exactly what earns you the right to bring an agent to the work where a mistake costs more.

The self-check · 十問

Ten questions, grouped by cut.

Pick one workflow and answer for it. Mark No (0), Partly (1), or Yes (2). Your running score sits at the top of the page.

一 · Repetition

01Does it happen often enough to matter?

A workflow you run many times a day rewards a prepared agent many times a day; one you touch twice a year barely repays the setup.

It runs daily, or many times a day.It's occasional, seasonal, or one-off.

02Is it costing you something you can name?

Backlog, overtime, rework, delayed cash, missed commitments. If you can name what it costs while it stays as it is, the improvement will be felt when it lands.

You can name what it costs to leave it alone.It's annoying, but not expensive.

二 · Boundary

03Can the rules be written down?

If a capable new hire could learn the task from a written procedure, an agent can be prepared for it. If the decision lives only in one veteran's shifting judgment, it needs to be understood first.

You could hand someone a page and they'd get it mostly right."You just have to know."

04Does it have a clear start and finish?Gate

"Process a returns request" has edges. "Improve customer experience" has none — it's a direction, not a task. You should be able to trace it from trigger to finished state in a single breath.

You can name the trigger and the done state.It's a goal, not a task.

05Will the process still exist in six months?

If it's about to be redesigned or replaced, preparing an agent for today's version spends the preparation on something that's leaving. Prove the method on stable work.

It's stable and here to stay.It's mid-change or on the way out.

三 · Measure

06Can you say what "done right" looks like — in numbers?Gate

A proof needs a verdict, and a verdict needs a line drawn before the work starts: cycle time under a target, error rate below a threshold, items cleared per day. Without a measure, "better" is an opinion.

You could write the pass/fail line today.Success is a feeling.

07Do the systems it touches have a way in?

A prepared agent works inside the systems you already run — so those systems need a door: an interface, an export, an API, a screen a governed agent can operate.

The data and actions live in systems that can be reached.It's locked where nothing can touch it.

08If it gets one wrong, can you catch it before it hurts?

A good first workflow is forgiving. A wrong answer is visible and correctable, not silent and irreversible. Prove the method where a mistake costs a correction, not a crisis.

Errors surface and can be corrected.A single silent error is catastrophic.

四 · Ownership

09Do you know who catches the exceptions?

Every real workflow has cases the rules don't cover. A prepared workflow has an answer for "when unsure, route to ___" before it meets its first hard case.

There's a clear place uncertain cases go.The edge cases have no home.

10Is there one person who can settle what "correct" means?Gate

When two people disagree about the right output, someone has to decide. Without that person, the success criteria drift and the proof has no judge. One accountable owner is worth more than a room full of stakeholders.

One name owns "right."It's owned by committee — or by no one.
Reading your score

A number out of twenty, and what to do about it.

16 – 20

This is your workflow.

It's ready to prove. Bring it to a thirty-day proof, agree the success criteria in writing, and let a plain result on real work speak for itself.

10 – 15

Promising — but sharpen it first.

The fix is almost always one of two moves: narrow the scope (Q4) until the edges are clean, or define the measure (Q6) until "done right" is a number. Make one of those moves, then score it again.

Under 10

Not this one — not yet.

Take a smaller, more bounded cut of the same work — or a different workflow entirely — and run the check again. The strongest single lever is almost always narrowing scope until the other answers turn.

Once you've chosen · The 30-Day Proof

One workflow. One governed agent. A measured result. Yours to keep.

We prepare the workflow you chose the way a craftsman prepares a job: the rules written down, the systems mapped, the success criteria agreed in writing before a single piece of work is done. Then we build one governed agent, run it on your real work, and measure it against the line you set.

保証 · Pay after proof

If the proof does not meet the written success criteria, you owe no build fee. You keep the prepared workflow documentation, rules, success criteria, and integration design. Production operation begins only if you choose to continue.

After the proof

The first workflow is a platform, not a project.

Because you keep the agent, the workflow map, the rules, the approval model, the corrections, and the reusable operating logic, the second workflow starts from a foundation the first one built — and the method compounds from there.

Bring one workflow to a workshop