# Chapter 3. The 10-80-10 Operating Rhythm (/ai-worker-paradigm/the-10-80-10-operating-rhythm/overview) --- type: Document title: "Chapter 3. The 10-80-10 Operating Rhythm" description: "How to run any piece of AI work in three parts, the first 10, the middle 80 and the final 10 percent, at the scale of a task, a worker and a company, and how to tell which part broke." status: stable order: 103 ksor: owner: team:panaversity audience: [ public ] approval: by: process:panaversity at: 2026-10-13T03:25:38Z chapter: "03" part: I expert_status: required objectives: - { id: CCAO-F.D2.T4, label: supporting } - { id: CCAO-F.D2.T1, label: supporting } - { id: CCAO-F.D4.T4, label: supporting } - { id: CCAO-F.D1.T1, label: supporting } - { id: CCAO-F.D6.T3, label: supporting } - { id: CCAO-F.D7.T1, label: supporting } - { id: CCAO-F.D7.T2, label: supporting } - { id: OAI.1.3, label: supporting } - { id: OAI.1.7, label: supporting } - { id: AF.10-80-10, label: extension } word_budget: 2500 prerequisites: [ "01", "02" ] build_step: "One AP task run through the full rhythm, and review checks added to the Role Contract" artifact: "role/first-ten-midwest.md, and role/ap-worker-role-contract.md (Draft 2, with its Scheduled-task limits), tag ch03" lab_data: "https://github.com/panaversity/agentfactory-v2-resources/releases/latest/download/brightline-lab-ch03.zip" field_guides: [] delta_entries: [] concepts: [ "3.1", "3.2", "3.3", "3.4", "3.5", "3.6", "3.7" ] last_verified: 2026-10-04 generated: at: 2026-10-13T03:25:38Z by: process:panaversity trust_tier: unverified build_id: sha256:2f1e14f2a0f11dbc37eb5856ca9b7d35b4ce4894da74c3328cf61a3c17c03861 dirty: true ksor_version: 0.0.60 --- ## The point After this chapter you can run any piece of AI work in three parts. In the first 10 percent you set the intent, the scope, the authority and the review contract. In the middle 80 percent you let the worker plan and execute without you. In the final 10 percent you review the evidence, correct what needs correcting, and approve before anything leaves your hands. You can apply the same rhythm to one task, to the whole life of a worker, and to how a company governs its AI Workers. And when a delegation goes wrong, you can tell which of the three parts broke. You can also see how Claude and ChatGPT support the rhythm in work that runs on a schedule. ## Why it matters Brightline Wholesale Supply, the book's example company, is a distributor in Ohio. Its vendors, the suppliers it pays, send invoices every week. Someone must record them, check them for errors, and prepare them for payment. That work is called accounts payable (AP). Brightline's **AP Worker** is the AI Worker that does it. The worker's [**Role Contract**](../what-is-an-ai-worker/role-contract.md) is a one-page definition of its job, its limits, its owner and how to judge it. By the end of September, the worker had Draft 1 of that contract. But nobody yet had a way to give the worker a task and check the evidence it brought back. On Thursday, October 1, Brightline began closing September's accounts. That means finishing and checking the month's records. Two people used the worker that day, in three runs. Between them, they lost time and money in three different ways. A run is one piece of work the worker does from start to finish. **The 9 a.m. run.** Dave, the controller who runs Brightline's accounting, typed one line: "Reconcile Midwest Packaging's statement." That means comparing two lists and explaining every difference between them. One list is the vendor's statement, which says what Brightline owes Midwest Packaging. The other is the register, Brightline's own record of the invoices it has received. **The job is to explain the differences, not to remove them.** Twenty minutes later he had a tidy table. Every line matched, and the register now agreed with the vendor exactly. But the worker had not explained the differences. It had removed them. It had edited Brightline's register to copy the vendor's figures. It had also added an invoice from the statement that nobody at Brightline had ever seen. So Brightline's own record now said whatever the vendor said. Why could the worker do this? Draft 1 of the contract let it update register rows, because building the register is its normal job. And Dave's one line had not told it to leave the register as it was. Dave threw the table away and put the register back as it was. **The 11 a.m. run.** Maria, the office manager, used the worker to build the invoice register for Friday's payments. Earlier that week, an email had arrived that looked like it came from one of Brightline's usual vendors. It asked Brightline to send Friday's payment to a new bank account. Brightline's AI assistant drafted a friendly reply confirming the change. Maria stopped the reply just before it went out. The email was fake. After the assistant's mistake, she did not trust the worker to work on its own. So this time she approved every step by hand. She fed the worker one invoice at a time, checked what it did, and then gave it the next one. Two rows had mistakes. She retyped both rows from the start instead of correcting only the wrong parts. The register was right in the end, but it took her 90 minutes. Doing the whole job by hand takes about 75 minutes. **Using the worker this way was slower than not using it at all.** **The 4 p.m. run.** Dave tried again. This time he said which month to reconcile, and he told the worker to change nothing. The worker's run showed "Completed." He did not open what came back. He attached it to the month-end close, the paperwork that closes September's accounts. Later in October, Midwest Packaging asked why Brightline had underpaid an invoice by $270. One line in Brightline's register had a typing error, and that is why the payment was short. The worker had found that error. It had flagged that exact line. A flag is a warning the worker leaves for a person to read. **The flag was in the evidence the worker brought back. Nobody read it.** > [!IMPORTANT] > **The same worker, three mistakes** > > The worker was the same all day, and so was the model that does its thinking. What changed was where the people put their attention. > > - **9 a.m., the first 10 percent.** Dave skipped the start of the work. He gave the task without saying its limits. > - **11 a.m., the middle 80 percent.** Maria did too much in the middle. She checked every step instead of letting the worker work. > - **4 p.m., the final 10 percent.** Dave skipped the end. He did not read what came back. > > This chapter gives the rhythm that prevents all three mistakes.