# What the setup did (/claude-and-chatgpt-2/case-4-nishas-month-end/what-the-setup-did)

---
type: Document
title: "What the setup did"
description: "Nisha lists what each part did, what only people did, how the setup differs from a document editor, where it can still go wrong, and who should change the method."
status: stable
order: 0.835
ksor:
  owner: team:panaversity
  audience: [ public ]
  approval:
    by: process:panaversity
    at: 2026-11-12T13:13:29Z
chapter: "F00G"
part: Front
expert_status: required
concepts: [ "What the setup did" ]
last_verified: 2026-11-12
sources:
  - id: google-history
    title: "Google, Find what's changed in a file (Google Docs Editors Help)"
    resource: https://support.google.com/docs/answer/190843
  - id: deck-history
    title: "Anthropic, What are artifacts and how do I use them? (Claude Help Center)"
    resource: https://support.claude.com/en/articles/17153992-what-are-artifacts-and-how-do-i-use-them
  - id: owner-connectors
    title: "Anthropic, Use connectors to extend Claude's capabilities (Claude Help Center)"
    resource: https://support.claude.com/en/articles/11176164-use-connectors-to-extend-claude-s-capabilities
  - id: no-source
    title: "Anthropic, Get started with Claude Sheets (Claude Help Center)"
    resource: https://support.claude.com/en/articles/18324300-get-started-with-claude-sheets
generated:
  at: 2026-11-12T13:13:29Z
  by: process:panaversity
trust_tier: unverified
build_id: sha256:ee289d75a60f3acc7dc4cab134056c3f9c1ab9c4abdba810061b7f3810eb4d15
dirty: true
ksor_version: 0.0.60
---

## Friday morning

On Friday, October 8, Nisha came in early. Lakeshore's owner would call at 6 p.m. Before that, she wanted to understand her own week. *What exactly had made it work?*

She wrote two lists.

## What the setup did

| The part | What it did this week | Without it |
|---|---|---|
| **The project** | Gave every run the same rules. Took one new rule on Tuesday, and kept it. | Someone pastes the rules each time, and forgets one |
| **The skill** | Wrote both memos in Sana's way. Knew that a returned check is an unrecorded item. | The memo depends on who wrote it |
| **The shared drive,** connected | Let every run, and the worker's morning check, read the same files | The files wait on one person's laptop |
| **The folder,** through the desktop app | Let Claude read Dana's three files where they were, before the firm copied them into the project. Held the bank's statement for Hamza's own tests. | Hamza uploads files one by one |
| **The borrowed desk** | Matched 3,400 lines in minutes, the same way each time: in three runs, two on Tuesday and one on Wednesday | Eight hours, and tired eyes |
| **The artifacts** | Held the pack as four pieces that every run updated | New files each time, with old ones left around |
| **The morning check** (the worker's routine) | Looked at the bank on a morning when nobody had asked | The firm finds out from the client |

No part was new. Each one is taught in an earlier section of this book ([Exhibit 1](exhibits.md#exhibit-1-where-the-earlier-sections-appear-in-this-case)). What was new was the joining.

## What people did

| The person | What only a person did |
|---|---|
| **Nisha** | Decided what the setup may and may not do. Approved Tuesday's pack, by name and figure. |
| **Sana** | Wrote the method. Saw what the first run forgot. Stopped a fix by hand. Approved Wednesday's pack. Wrote to Dana herself. |
| **Hamza** | Checked the arithmetic, the matching, the leftovers and the pieces, without Claude. |
| **Dana** | Recorded the returned check, and called her bank |

Nisha looked at the two lists side by side.

*"The setup did the work. We did the judgment. Before this week we spent most of our hours on the first list."*

![What the setup did, and what people did. Two columns. On the left, the setup: read the files, matched 3,400 lines, worked out the figure, built four pieces, ran again on Wednesday, watched the bank each morning. On the right, people: wrote the rules and the method, checked the result without Claude, approved by name and figure, stopped a fix by hand, told the client. A band at the foot says the setup repeats the work, and it does not carry the responsibility.](img/what-the-setup-did.png)

## Is this better than a document tool?

Hamza asked the question a student would ask. *"Dana's old accountant used Google Docs and Slides. Those have AI in them now too. What did we really gain?"*

Nisha answered in two parts.

*"For writing, nothing. Google's editors are very good. They also keep a better record of earlier versions of slides than ours do. If the job were to write a memo, I would not care which one we used."*[^google-history],[^deck-history]

*"But the job was never the memo. The job was the bank lines, the matching, the rule about returned checks, the four pieces that must agree, and the morning check. A document editor starts when someone has the figure. Our setup starts with the bank's file and ends with the pack."*

She added that the comparison has limits. The firm had not tested Google's AI features. And another firm could join other tools into a setup too.

![A document editor and a workplace. Six steps of one month-end pack in a row: read the bank's file, match 3,400 lines, work out the figure, apply the method, write the pieces, do it again next month. Under them, two rows. A document editor, with AI help: a person does steps 1 to 4 and step 6, and AI helps with step 5, writing the pieces; it helps when someone already has the figure. The firm's setup: Claude does all six steps; it starts at the bank's file and runs again next month. A line says that in both, a person checks, approves and tells the client. A band at the foot says the slow part of this job was never the writing.](img/a-document-editor-and-a-workplace.png)

She drew it as a table ([Exhibit 10](exhibits.md#exhibit-10-a-document-editor-and-a-workplace)).

| | A document editor, with AI help (Google's, or Claude's own docs) | The firm's setup |
|---|---|---|
| Where the work starts | When a person brings the figure | At the bank's file |
| Who does the matching | A person, perhaps with AI help in a spreadsheet | Claude, with a program |
| Where the rules are | In people's heads | In the project and the skill |
| Next month | Start again | Run it again |
| A late change | Fix each file by hand | Run it again |
| Who is responsible | People | People |

The last row was the same in both columns. She underlined it.

## Where it can still go wrong

Sana did not work Fridays. On Thursday evening she had left a list on Nisha's desk: what the setup does not do ([Exhibit 12](exhibits.md#exhibit-12-before-you-trust-a-setup)).

- **Instructions only ask.** The project says *"never send anything"*. A rule written in the instructions only asks Claude. A **setting** in the app really stops it. For example, an Owner decides which connected apps the firm's members may use at all.[^owner-connectors] Here a setting does the work: Nisha turned on only the shared drive, so no chat in Claude can send an email.
- **The worker is different.** The worker is set up separately, in its Slack channel. If that channel can still reach `reports@`, the worker could send. It also runs the morning check. For the worker, *"change nothing in the pack"* is only a sentence. What protects the firm there is its habit: a named approval before anything leaves.
- **The pieces are still copies.** No piece reads another.[^no-source] One run writes them all, and a person checks that they agree.
- **Hamza's tests missed one thing.** His statement already showed the returned check on Tuesday. But he took the closing balance from Claude's run note, not from the statement. From now on, his first test compares the two.
- **A program can match wrongly.** Two payments of the same amount on the same day can be paired the wrong way round. Hamza's twenty pairs are a sample, not a proof.
- **The morning check only looks where it is told to.** It saw the returned check because it downloaded the bank's lines again. It would not see a mistake in Lakeshore's ledger.
- **The first download was too early.** Tuesday's run used Friday's file, which was four days old. Sana's note asked for a rule, and on Friday morning Nisha added it to the instructions: *"If the newest bank file is more than a day old, stop and say so."* Before each run, Hamza now asks the worker in Slack for a fresh download himself.
- **One person can now do a lot, fast.** That is the point of the setup. It is also why the approval must stay with a named person.

At the bottom Sana had written: *"It did two days of work in twenty-five minutes. It can do two days of damage in twenty-five minutes too. I will keep reading everything I sign."*

## What the firm had now

By Friday the firm owned something it had not owned on Monday: a setup that could do Lakeshore's month-end again in October, and in November. Most of it would work for another client with one new project.

Nisha saw that this was worth more than the pack. She also saw the question that Lakeshore's owner was going to ask.

> **Going further: who changes the method?** The project's instructions and Sana's skill are the firm's method. This week two sentences were added to the instructions, and nothing recorded who changed them, when, or who agreed. A change to the method needs the same care as a change to the pack: one person proposes it, another reviews it, and a record keeps both.
>
> Teams that keep their instructions and skills as files can use **version control** for this. Every change is saved with its author and its date, and nothing is lost. A **pull request** is a proposed change with a page where it is described, checked, discussed and approved. It is Nisha's approval of one exact pack, applied to the method itself.
>
> You can work this way from the Claude desktop app's Code tab, which works in a folder on your computer, or with a separate app such as GitHub Desktop. Some desktop apps can open the pull request for you. Later in this book, [15.3 GitHub and the pull request](../../building-ai-workers/code-review/github-and-the-pull-request.md) teaches how.

[^google-history]: As verified on November 12, 2026, Google says "You can see changes that have been made to a document in Google Docs, Sheets, Slides, or Vids." A person with edit access can open an earlier version, name it and restore it. Find what's changed in a file, Google Docs Editors Help.
[^deck-history]: As verified on November 12, 2026, Anthropic says "Decks export to PowerPoint and PDF, or go straight to Google Slides as editable files." The help pages we checked describe no version history for decks. What are artifacts and how do I use them?, Anthropic.
[^owner-connectors]: As verified on November 12, 2026, Anthropic says that on Team and Enterprise plans "an Owner or Primary Owner needs to enable" connectors "for the organization" before members can use them, and that each person still signs in. Owners can also set each connector's actions to Always allow, Needs approval or Blocked, and members cannot override this. Connectors belong to each person's account, not to a project. Use connectors to extend Claude's capabilities, Anthropic.
[^no-source]: As verified on November 12, 2026, Anthropic says "Sheets can't pull live data from connected apps, and docs, decks, and dashboards can't use a sheet as a data source." Get started with Claude Sheets, Anthropic.