Lesson 3.23.2 The first 10 percent: intent, scope, authority, review contract

In everyday life. Before a teenager takes the family car, you say where they may go and when to be back. You also say that they must text if plans change, and that they may never drive after midnight. You say all of it in the driveway, because once the car turns the corner, it is too late to add rules.

The first 10 percent is everything the worker must know before it starts, because you will not be there while it works. It has four parts.

1. Intent. The outcome you want and why it matters. "Reconcile Midwest Packaging's September statement so the close can be signed on Monday" tells the worker what "done" means and why it matters. "Reconcile the statement" does neither. The why also helps with small decisions you did not foresee: a worker that knows the close is on Monday treats a missing invoice as urgent. (The close is the month-end work that finishes and checks September's records.)

2. Scope. What is in, what is out, and what the worker works from: which vendor, which month, which version of the register, and which policy. Scope also stops a willing worker from doing too much. Asked to reconcile one statement, a worker with no scope may decide to tidy up three others.

3. Authority. What the worker may do on its own in this task. This is about permission, not ability: the worker may be able to edit the register, but is it allowed to? Authority comes in two layers.

   • The worker's Role Contract, the one page that describes its job and its limits, sets the most the worker may ever do.
   • The written instructions for one task, the brief, can narrow that limit, never widen it.

   Dave owns the worker's contract. The contract lets the worker update register rows, because building the register is its normal job. But a reconciliation must change nothing. So the brief has to say so: in this task, the worker may only recommend changes. The worker proposes each change, and Dave decides.

4. Review contract. How you will know the work is right, agreed before it starts.

With the teenager, where they may go is the scope, and when to be back is part of the intent. The text if plans change and the midnight rule belong to the review contract: when to stop and ask, and what must never happen.

When the worker runs day and night

A fair question: if the worker runs around the clock, when does the first 10 percent happen? Nobody is awake at 11 p.m. to brief it.

The answer is that every run still gets all four parts. They are simply written in advance, so that each run picks them up without you. The first 10 percent belongs to each piece of work, not to a time of day.

Go back to the teenager. If they drive to school every day, you do not repeat the rules each morning. You set house rules once: where they may go, when to be home, text if plans change, never after midnight. Every ordinary trip follows them. Only an unusual trip, such as a drive to another city, needs a fresh conversation, and that conversation can tighten the house rules but not loosen them.

A standing worker's setup works the same way, in three layers:

Figure 3.3. A standing worker's setup is written in advance, in three layers, so every run has all four parts even when nobody is awake.

Now look at the week from Lesson 3.1 again. On Tuesday at 11 p.m., a vendor emails. Nobody wrote anything that night, yet the run had a full first 10 percent. The standing instructions for vendor emails supplied the intent (answer the question), the scope (this vendor, its open invoices), the authority (draft, never send) and the review contract (the draft goes to the approval queue). Dave wrote those weeks earlier. That is why the worker could act at night without guessing.

So, for a standing worker, the first 10 percent does not disappear. It moves:

• Earlier. Most of it is written before the worker's first run, and it covers every run after.
• Into revisions. When a review turns up a case the instructions missed, such as Thursday's flag in Lesson 3.1, Dave adds it. The next run starts from a better setup. That is the feedback loop from the final 10 percent back to the first.
• Into the occasional brief. For a job the standing instructions do not cover yet, like this reconciliation, Dave writes a short brief. It adds the intent and narrows scope and authority for this one task.

What never changes is the order. The setup comes before the work. A worker running at night cannot ask you what you meant, so anything it needs to know must already be written down.

The review contract

The Review Contract is the set of checks you agree on before you hand the work over: what is checked, what evidence comes back, what counts as success, and what stops the worker. In practice it answers five questions: those four, and what must never happen automatically.

(A source document is the document a line was taken from, such as the invoice itself. A credit is money the vendor takes off what Brightline owes, for example when goods arrive damaged.)

These answers are not paperwork. Each one becomes a place Dave looks in the final 10 percent:

• The evidence makes spot checks possible. Dave picks a few differences, opens the source documents, and checks whether they say what the worker claims.
• The success test gives him one number to check. If the listed differences do not add up to the whole gap, the work is not done, however good the report looks.
• The stop rule produces the flags he reads first.
• The "never automatically" list fills the approval queue. Each proposed change waits there until Dave approves it. Nothing changes on its own.

Figure 3.4. The review contract, written in the first 10 percent, decides where you look in the last.

Question what the worker made of your setup

Writing the four parts is only half of the first 10 percent. The other half is testing them, and the best test is to ask questions. But questions about what? This matters, so let us be exact.

Why you cannot question your own setup

When you reread your own brief, you read what you meant, not what you wrote. You know that "the register" means approved rows only, that Midwest always sends its statement late, and that a missing invoice is usually in someone's inbox. None of that is on the page, but your mind fills it in, so the brief looks complete to you.

The worker has only the page. So the gaps do not show up in your setup. They show up in what the worker does with it. That is the thing to question: not your brief, but something concrete the worker produced from it, before the real work starts.

What you are really testing: the specification

Each question tests what the worker was given. That is more than the brief, and more than the Role Contract. Everything written down that a worker runs from is its specification. It has five parts:

The Role Contract stays one page: it is the first page of the specification and points to the rest. The other four parts grow around it as you learn what the worker needs. Chapter 21 turns the whole thing into a formal specification.

This matters for one reason. A question can expose a gap in any of the five parts, and the fix belongs in the part where the gap was found. If the worker does not know what a credit note is, that is a gap in its knowledge. If you explain it in this month's brief, next month's run has forgotten it. If you add it to the knowledge, every run has it. This is the same rule as in Lesson 3.1: correct the problem where it came from.

So the first 10 percent is a loop, not a single step. You write the specification, the worker produces something from it, you question that, and you fix the part where each gap was found. Then you go round again, until the answers stop surprising you.

Figure 3.5. The specification is everything the worker runs from. The Role Contract is its first page.

Three things you can question

Go back to the teenager one last time. Before you let them drive to school alone, you can check their understanding in three ways:

1. Ask them to describe the route. "Which roads will you take, and where will you park?" It takes a minute and shows whether they understood where they are going.
2. Ride with them around the block. Now you see how they actually drive: the speed, the mirrors, the turns. You cannot learn that from a description.
3. Ride the whole route with them on a quiet Sunday. They drive the real trip, with you in the car and nothing at stake. You see the awkward junction and the school car park that a short drive around the block never reaches.

Each check shows things the one before it cannot. A worker is the same. Before the real work starts, you can question three things it produces from your setup:

Figure 3.6. Three things you can question. Each shows what the one before it cannot.

How to choose

Pick the check that can show the risk you are worried about:

• If the risk is a wrong action, a plan is usually enough.
• If the risk is wrong quality or judgment, ask for a sample.
• If the worker will run alone or repeatedly, or a mistake would be expensive, do a dry run.

You can combine them. For a new standing worker, Dave would question a plan first, because it is cheap and catches misunderstandings early. Then he would do a dry run before the first real Monday. Each check costs more than the one before it, so start with the cheapest one that can answer your question.

How to do it, step by step

Step 1: Get something concrete to question. Ask for a plan, a sample or a dry run, and say "do not start the real work yet". For a plan:

Before you start, tell me in a few lines:
- what you will do, step by step
- what you will not touch
- when you will stop and ask me
Do not start the work yet.

This is the parent saying, "So where are you going, and when will you be back?" It costs a minute, and it already catches the biggest misunderstandings. If Dave's worker answers "I will update the register", he knows straight away that the authority part of his brief was not clear.

Step 2: Question it. Ask "what if" questions, the way a good manager questions a new employee. You are not testing the worker's intelligence. You are testing whether your setup covers the cases that matter. Five kinds of question cover most of them, whether you are looking at a plan, a sample or a dry run:

With a sample or a dry run, you can also ask the most useful question of all: "Why did you do it this way?" Pick the part that surprised you and ask. The answer shows which line of your setup the worker followed, or which line was missing.

The best questions come from your own experience. Ask about the mistake that cost the company money last year, the vendor that always does something odd, and the question the auditor always asks. That knowledge is what the worker does not have, and no setup captures all of it on the first try.

Step 3: Judge each answer. There are three kinds of answer.

• A clear, correct answer. The setup already covers that case. Move on.
• A vague answer, such as "I would handle it appropriately". The setup is silent here, and the worker would guess. That is a gap.
• A wrong answer, such as "I would record the credit". The setup is unclear or missing a rule. That is a gap too, and a dangerous one.

Step 4: Fix the specification, not just the conversation. This is the step people skip. When an answer shows a gap, do not just tell the worker the right answer in the chat. That fixes this run only. Decide which part of the specification the gap is in, and fix it there:

• A missing or unclear rule for this task goes in the brief. If the case will come up again, it goes in the standing instructions.
• A missing fact or definition goes in the knowledge.
• A wrong source, an old file or a missing permission is fixed in the inputs and tools.
• A case you want checked every time becomes an example or test.
• A limit that should apply to everything the worker ever does goes in the Role Contract.

Step 5: Stop when the answers become boring. When every question gets a clear, correct answer you could have predicted, the setup is ready, and the real work can start. For a routine task, that may take two questions on a plan. For a new and risky task, it may take a sample, a dry run and ten questions.

Figure 3.7. Question what the worker produced from your setup (a plan, a sample or a dry run) until the answers become boring. Then write every gap back into the setup.

Three worked examples

The three examples below put the steps together, one for each thing you can question. In each example, look at three things: what the person asked for, the questions they asked, and what each answer told them. Not every question finds a gap. A clear answer is good news too: it tells you that part of the setup already works.

Example 1: questioning a plan

The task. Dave is about to hand over the Midwest reconciliation.

What he asks for. A plan, before anything happens. The worker replies:

I will compare the statement with the register, list each difference with its documents, and update the register where a difference is clearly ours, such as an unrecorded credit.

The questions he asks.

The first answer also prompts the worker to ask a question of its own: "And if the credit has no credit note behind it?" Dave answers from experience: "Then stop and flag it. Midwest sometimes shows credits it has not issued yet." That is a third gap, found because the worker asked.

The fixes, and where each one goes. In the brief: Recommend only: list each proposed entry for the approval queue, and change nothing. In the standing instructions, because every reconciliation needs them: There is no tolerance: every difference, however small, is explained or flagged, and A credit with no credit note behind it: stop and flag. In the knowledge: Midwest sometimes shows credits on its statement before it issues the credit note. That last one is a fact about a vendor, not a rule, so it belongs with the other facts the worker can look up.

Why a plan was enough here: the main risk in this job is an action, changing the register. A plan is exactly where intended actions show up.

Example 2: questioning a sample

The task. Maria, the office manager, wants a worker to write a one-page monthly summary of payables (what Brightline owes its vendors) for Brightline's owner. A plan would sound fine: "I will summarize the month's invoices, payments and anything overdue."

What she asks for. A sample: just the opening paragraph, written as it would be sent. It reads:

Accrued payables rose 12 percent month on month, driven by timing differences in the Midwest Packaging account and two unapplied credits.

The questions she asks.

The fixes, and where each one goes. In the standing instructions for the monthly summary, because it recurs: The reader is the owner. Plain words, no accounting terms. Lead with what he needs to decide. In the inputs: Use the register as the only source of figures, and the dashboard export is removed from what the worker can read for this job. She also keeps her sample paragraph, corrected, as an example of the tone she wants.

Why a sample was needed here: the risk in this job is quality: the wrong reader, the wrong source. "I will summarize the month" sounds right whoever the reader is and wherever the numbers come from. Only real output shows the worker's judgment.

Example 3: questioning a dry run

The task. The AP Worker is about to start building the Monday register on its own.

What Dave asks for. A dry run on last month's invoices. He has already processed those by hand, so he knows what the register should look like. The worker runs the whole job, and nothing it does touches the real register. Then Dave compares the two. They match except for two rows.

The questions he asks.

The fixes, and where each one goes. In the standing instructions: Before adding an invoice, check whether the same vendor and invoice number already exist. If they do, do not add it. Flag it. In the knowledge: what a credit note is, how to recognize one, and how it is recorded. And last month's invoices, with Dave's register as the known answer, become a test: after any change to the specification, the worker reruns it, and the result must still match.

Figure 3.8. A dry run finds the rare cases, because it has a known answer to compare against.

Why a dry run was needed here: neither gap could have appeared in a plan ("I will add each new invoice to the register" sounds right) or in a small sample (the first five invoices were all normal). They appeared only when the worker met a month of real, messy documents, and only because Dave had a known answer to compare against. Without the dry run, both mistakes would have reached the real register on a Monday morning, with nobody watching.

The worker can question you too

You can also invite questions in the other direction. End the brief with:

Before you start, ask me about anything unclear or missing in the
intent, scope, authority or review contract. Do not start until
I have answered.

Today's AI workers are good at spotting what a brief leaves unclear, and many will ask on their own. This is useful, but it finds a different kind of gap:

• The worker's questions find what your brief left unclear: an undefined word, two instructions that conflict, or a missing input.
• Your questions find what the worker would get wrong: the risks and exceptions that only someone who knows the business would think of.

The worker cannot ask about a risk it does not know exists. So use both, but never skip yours.

Two rules

You decide the answers. The worker may suggest an answer, and it may be a good one, but the setup is your 10 percent. If you let the worker answer its own questions, it is writing its own rules.

Ask before the real work, not during it. This matters most for a worker that runs at night. At 11 p.m. it cannot reach you. Every gap you close now is a flag it will never need to raise. Every gap you leave is a guess it will make alone.

Questions at both ends

The same questions work after the work is done. In review, you question the finished output instead of a plan or a sample: "Why did it do that?" "What would it have done if…?" Every answer that exposes a gap goes back into the setup. That is the feedback loop from Lesson 3.1 in practice. The final 10 percent asks the questions, and the first 10 percent records the answers.

The difference is cost. A gap found in a plan costs a minute. The same gap found in a sample costs a few minutes. Found in the finished work, it costs you the whole job. So the rule of thumb is simple: ask your questions about the earliest, smallest thing that can answer them. Over a few weeks, the setup becomes something no one could have written at one time, because it holds the answers to every question that mattered.

Chapter 5 teaches you to write the intent, scope and authority as the Four-Part Brief: outcome, context, format and constraints. Chapter 6 teaches the Review Contract in depth, and Chapter 7 teaches the written limit on what the worker may do, the Authority Envelope. This chapter shows where they fit in the rhythm.