# 3.1 One rhythm in three parts (/ai-worker-paradigm/the-10-80-10-operating-rhythm/one-rhythm)

---
type: Document
title: "3.1 One rhythm in three parts"
description: "The 10-80-10 rhythm: the human defines the first 10 percent, the worker does the middle 80, and the human verifies the final 10, read as a shape and not as a timesheet."
status: stable
order: 103.1
ksor:
  owner: team:panaversity
  audience: [ public ]
  approval:
    by: process:panaversity
    at: 2026-10-26T22:26:42Z
chapter: "03"
part: I
expert_status: required
concepts: [ "3.1" ]
last_verified: 2026-10-04
sources:
  - id: v1-thesis
    title: "The Agent Factory Thesis (Panaversity, first edition, verified 2026-10-04)"
    resource: https://agentfactory.panaversity.org/docs/thesis
  - id: martell
    title: "Buy Back Your Time (Dan Martell, Portfolio, 2023; the author's book site, verified 2026-10-15)"
    resource: https://www.buybackyourtime.com/
generated:
  at: 2026-10-26T22:26:42Z
  by: process:panaversity
trust_tier: unverified
build_id: sha256:46fd53c5d7ab1c14f6347908d45c9fdaecda4d914439923ee878bdcecd57803e
dirty: true
ksor_version: 0.0.60
---

**In everyday life.** You hire a painter. You choose the colors and say
which rooms, and you agree that you will walk through the rooms before
paying. Then you go to work, and the painter paints the rooms. When you
come home, you check the edges and the trim around the doors and windows,
and only then pay.

**At work.** Dave (the controller who runs Brightline's accounting) gives
the company's AP Worker one task: reconcile a vendor's statement, and
change nothing. He should let it work, then read what comes back before
he closes September's accounts.

The book's operating rule has three parts: *Humans define intent. AI
Workers execute. Humans verify outcomes.* With the painter, you define the
intent, the painter executes, and you verify the outcome. The **10-80-10**
rhythm is that rule with numbers added. The human defines the first 10
percent, the worker executes the middle 80, and the human verifies the
final 10.

The pattern is older than AI. The entrepreneur Dan Martell describes it
as the 10-80-10 rule for delegating to people: you spend the first 10
percent of a project setting the vision (the outcome you want), a capable
team does the middle 80, and you return for the final 10 to refine and
approve.[^martell] It is also often credited to Steve Jobs, though no
reliable source confirms that. The first edition of this book applied the
pattern to AI, with AI Workers in the place of the team.[^v1-thesis] The
shape stayed the same. What AI adds is in the details: the worker
must bring back evidence you can check, flag what is unusual, and wait
for a person before any risky action — and it may keep working long
after you have gone home. The next pages are about those details.

The table below shows the three parts. The next three pages explain each
part and the words in its row.

| Part | Who leads | What happens | What it produces |
| --- | --- | --- | --- |
| First 10 percent | The human | Intent, scope, authority and the **review contract** are set | A brief the worker can act on alone. For a standing worker, it is mostly written once, in its Role Contract |
| Middle 80 percent | The worker | The worker plans, uses its tools and does the work | The output, plus the evidence the contract asked for |
| Final 10 percent | The human | Evidence is reviewed, the output corrected, then approved or sent back | A decision, and work that is ready to go out |

(The review contract is how you will know the work is right, agreed
before it starts.)

![The 10-80-10 operating rhythm, under the rule: humans define intent,
AI Workers execute, humans verify outcomes. A bar split 10, 80 and 10
percent is a guide to who leads, not a fixed split of time. In the first
10 percent, the human leads, to Define. It sets the intent, the scope,
the authority and the review contract (checks, evidence and stop
conditions). For a standing worker, you keep up the Role Contract and
standing instructions. It delivers a brief with clear limits. In the
middle 80 percent, the AI Worker leads, to Execute. It plans and does
the work, uses tools within its authority, checks results and gathers
evidence. It stops and escalates when a rule says so. It delivers the
output, the evidence and the flagged exceptions. In the final 10
percent, the human leads, to Verify. Read the flags first, clear the
approval queue, and check a sample, more where the risk is higher. Then
correct the underlying cause. For a standing worker, review at set
times. It delivers a decision to approve or revise. A dashed arrow runs
from the last card back to the first, to improve the next run. A banner
reads: "Humans set goals, limits and approvals. AI Workers execute
within them."](img/rhythm.png)

*Figure 3.1. The 10-80-10 rhythm. You own both ends. The worker owns the middle.*

> [!IMPORTANT]
> **A shape, not a timesheet**
>
> Read the numbers as a shape, not a timesheet. They describe who leads
> each part of the work, not minutes on a clock. The first time you
> delegate an unfamiliar task, both ends take longer: you write the brief
> with care and check the result line by line. A task that has run
> without errors every week for months may need five minutes of setup and
> a quick look at its evidence. And if a worker runs day and night, you
> do your two parts at fixed times. The section *When the worker never
> stops*, below, shows how. **The person responsible for each part stays
> the same. Only the time each part takes changes.**

### When the worker never stops

The table above reads like one job with a start and an end: you set it
up, the worker does it, you check it. But a Standing AI Worker never
finishes. The AP Worker builds a register every Monday and answers
vendor emails all week, day and night. So where do your two ends go,
when the worker is still working at 3 a.m. and you are asleep?

**In everyday life.** Think of a house cleaner who comes every Tuesday
while you are at work. You do not stand at the door each week explaining
the job. You wrote it down once: clean these rooms, water the plants,
never throw away papers from the desk. If something is unusual — a
broken glass, a leak under the sink — the cleaner leaves you a note. If
something needs your decision — "should I throw out these old boxes?" —
the cleaner asks and waits. And now and then, you look closely at one
room to make sure the work is still good.

That is the whole answer. The rhythm still applies to every piece of
work, but you no longer do your two parts at the same time as the work:

- **Your first 10 percent is done once, in advance.** For the cleaner,
  it is the written instructions. For the AP Worker, it is the Role
  Contract and its standing instructions. They are the setup for every
  run, until the work or the rules change.
- **Your final 10 percent happens at times you choose,** in three ways.
  An **approval queue** holds anything the worker may prepare but not
  do on its own, like the cleaner's question about the boxes. **Flags**
  mark anything unusual, like the note about the leak, and you read them
  at a set time. And **spot checks** look closely at a sample of
  ordinary work, like the one room you inspect.

Here is one week of the AP Worker, with Dave as its owner:

| When | What the worker does | Where its evidence goes | What Dave does, and when |
| --- | --- | --- | --- |
| Monday, 6 a.m. | Builds the weekly register, on a schedule | Saved with a run record; no flags | Nothing yet |
| Tuesday, 11 p.m. | A vendor emails; the worker drafts a reply | The approval queue, because sending is outside its authority | Approves the reply Wednesday at 9 a.m. |
| Thursday, 2 p.m. | A statement arrives that does not match the register | A flag, because the worker explains differences, never removes them | Reads the flag Friday at 9 a.m. and follows up |
| Friday | Keeps working as usual | — | Picks five rows from Monday's register and checks them against the invoices |

![The rhythm at two speeds, over one week. Before the week, the first 10
percent sets up the Role Contract and standing instructions, reused
across runs. Across the top, the AI Worker runs the middle 80 percent.
On Monday at 6 a.m., on a schedule, it builds the register with no flags
and saves a run record. On Tuesday at 11 p.m., a vendor's email arrives,
and it drafts a reply that waits for approval. On Thursday at 2 p.m., a
statement does not match, and it flags and explains the difference.
Across the bottom, Dave reviews the final 10 percent at a 9 a.m.
checkpoint every day. An arrow named "Approval queue" leads to Wednesday
at 9 a.m. There he approves the draft reply, which stayed blocked until
then. An arrow named "Flag" leads to Friday at 9 a.m. There he reviews
Thursday's flag and spot-checks five rows of Monday's register. A dashed
arrow runs from Friday back to the setup, where Dave adds the missed
case. A banner reads: "Set up once, run repeatedly, review
deliberately."](img/two-speeds.png)

*Figure 3.2. The rhythm at two speeds. The worker runs whenever work arrives; you review at times you choose.*

Notice three things in the week. Nothing risky happened overnight,
because the risky step — sending the reply — could not happen without
Dave. Nothing unusual got lost, because the worker flagged it and Dave
reads flags every morning. And even the work that raised no flags still
got a human look, through Friday's spot check.

**Each review also improves the next setup.** Suppose Thursday's flag
shows that the standing instructions never said what to do with
statements that arrive in a different currency. Dave adds that case.
From next week, every run starts from a better brief. This is the dashed
arrow in Figures 3.1 and 3.2, from the final 10 percent back to the
first: the end of one round of work becomes the start of the next.

So the worker runs day and night, and Dave works office hours, and the
rhythm still holds. Dave made two moves. He moved his first 10 percent
to *before* the week began, by writing the setup down once. And he moved
his final 10 percent to *fixed times in his own week*: approvals and
flags each morning, spot checks on Friday. The 4 p.m. run in the story
failed because the second move had not been made: the worker flagged the
error, but no one had a set time to read its flags.

### Why the ends belong to a person

**The two ends belong to a person, because judgment, values and
accountability cannot be handed over.** (Accountability means the work
goes out under your name.) The middle belongs to the worker, because that
is where execution scales (the work can grow without taking more of your
time).

The rhythm is also why this book teaches you to manage an AI Worker
before it teaches you to build one. The skills that matter at both ends
are defining work well and judging it well, and every route through the
book needs them.

[^martell]: Dan Martell, *Buy Back Your Time*, Portfolio, 2023.
[^v1-thesis]: The Agent Factory Thesis, Panaversity, first edition.