Skip to content
The AI Agent Factory

One job, start to finish

Approved by
Panaversity ·
8 min read

You will follow one small company through this book: Brightline Wholesale Supply, a company in Columbus, Ohio, that buys goods in large amounts and sells them to stores. Its accounting team pays the bills, called invoices, that its suppliers send. Every Friday the team decides which invoices to pay that week. This weekly set of payments is called the payment run. The invoices are kept in a folder named Invoices. The team follows a written payment policy: its rules for which bills to pay. The team also has a checking program that adds up this week's invoices to the cent. This week, the folder holds 15 unpaid invoices.

Here is that job, handed to an AI Worker in one message. A message like this is called a brief. In it, "pay" means pay this week, "hold" means wait, and "ask" means a person must decide.

Prepare this Friday's payment run from the Invoices folder. Follow version 3 of our payment policy, not the old version 2. You are done when every invoice due in the next seven days is marked pay, hold or ask. Return a spreadsheet with one row per invoice, showing the decision and the policy rule you used. Your invoice total must match the checking program's total. Mark these invoices "ask": invoices from a new supplier, invoices large enough to need a manager's approval, and invoices with changed bank details, because thieves often send fake new bank details to steal payments. Only suggest. Never approve or send a payment. Show what you checked and what the checks found.

This short brief has four parts. Every good brief in this book has them, and Chapter 5 teaches each one.

PartWhat it saysIn this brief
OutcomeWhat you want back, and how to know it is doneThis Friday's payment run. It is done when every invoice due in the next seven days is marked pay, hold or ask, and the total matches the checking program's total
FormatWhat shape the result takesA spreadsheet with one row per invoice: the decision and the policy rule used, plus a note on what was checked
InputsWhich sources to useThe Invoices folder, version 3 of the payment policy, and the checking program's total
AutonomyHow far the worker may go without youOnly suggest, never pay, and leave risky invoices to a person

We call the test inside the outcome the done-when, short for "the job is done when". It is a test the worker can apply to its own work, so it knows when to stop. But you still check the total yourself, with a program you trust, like the checking program.

What comes back is not just an answer. It is finished work: a spreadsheet of decisions, a short note on the checks the worker ran and what they found, and a list of invoices marked "ask" for a person to decide.

This book teaches what you do next. You look at the checking program's result yourself. You do not just trust what the worker says about it. You decide the "ask" invoices yourself. Then a different person, the one in charge of payments, makes the payments. This person uses a payment system that blocks the AI Worker. Even if the worker tried to pay, the system would say no.

One more idea before the figure. The brief tells the worker what it should do. Permissions decide what it is able to do. They are the settings and systems that allow some actions and block others, such as sending a payment.

One job, start to finish: you start it, the AI works, you check the result. Five steps. 1, You brief: outcome with its done-when, format, inputs, autonomy. 2, The AI works: reads files, uses apps and a browser, calculates with code, and asks when it needs help. 3, The AI returns a decision spreadsheet, the results of its checks, and "ask" items for review. 4, You check: compare totals with the checking program, review the decisions, and resolve the "ask" items. 5, A person pays: the authorized person sends payments, and the payment system blocks the AI Worker. Steps 1 and 4 are your part, steps 2 and 3 are the AI Worker's part, and step 5 belongs to the payment officer. A band says: the brief defines what the worker should do, and enforced permissions limit what it can do. At the foot: you can guide the worker while it runs, and you check the evidence before approving the result.

Read the figure from left to right. You start the job with the brief, and you check what comes back. The worker's part is in the middle, and another person, the payment officer, makes the payment. You can also watch and add instructions while the worker is busy, and it may stop to ask you a question or to wait for your OK.

Check yourself

Question 1 / 10

0 answered

Which of these is NOT one of the four parts of a good brief?

Owner
Panaversity