---
title: "A Fukuoka developer had Claude Code build a bookkeeping pipeline that reconciled 200 transactions and flagged its own doubts"
person: "Ken Imoto"
handle: "@kenimo49"
profile: "https://dev.to/kenimo49"
tools:
  - "Claude Code"
  - "MCP connection to his accounting platform (platform not named)"
country: "Japan"
category: "Get tasks done"
category_slug: get-tasks-done
proof:
  - label: "Read the public source"
    url: "https://dev.to/kenimo49/i-let-claude-code-run-a-month-of-my-business-books-it-reconciled-200-transactions-and-513d"
date: 2026-11-19
date_posted: 2026-06-25
as_claimed: "The result is shown as claimed in the public source linked here. It has not been checked and is not a typical outcome."
url: "https://agentstories.org/stories/ken-imoto-claude-code-bookkeeping-200-transactions-doubt-flags.html"
markdown_url: "https://agentstories.org/stories/ken-imoto-claude-code-bookkeeping-200-transactions-doubt-flags.md"
site: "Agent Stories by Solopreneur Code"
---

# A Fukuoka developer had Claude Code build a bookkeeping pipeline that reconciled 200 transactions and flagged its own doubts

Ken Imoto @kenimo49 · Japan · Claude Code, MCP connection to his accounting platform (platform not named)

## What the agent did

Built a re-runnable pipeline that pulls the month's transactions over MCP, matches bank rows to receipts by amount and date, proposes a category with a one-line reason for each row and flags rows it isn't sure about.

## Result, as claimed

200 transactions reconciled and 11 miscategorised, a 94.5% hit rate. Review shrank to 18 flagged rows plus a sample. 7 of the 11 errors were in the flagged pile and 4 were caught on the sample.

> The result is shown as claimed in the public source linked here. It has not been checked and is not a typical outcome.

## Proof

- [Read the public source](https://dev.to/kenimo49/i-let-claude-code-run-a-month-of-my-business-books-it-reconciled-200-transactions-and-513d)

## Try it yourself

Have the AI sort a month of transactions and tell you which rows it's unsure about, so you check 20 rows instead of 200.

Prompt:

```text
Here is last month's business bank export with account numbers removed: [paste CSV]. Here is my category list: [list]. Here are my receipts and invoices with date, vendor and amount: [paste list]. For each row, match a receipt if amount and date agree, suggest one category and give a one-line reason. Add a confidence column: SURE or CHECK. Mark CHECK for anything personal-or-business, any meal or entertainment, any payment covering two things and any row with no receipt. Don't guess tax rules. End with a count of SURE and CHECK rows. Return a draft only. Never send, spend, change settings or write to a live system.
```

Steps:

1. Export one month of bank transactions and remove account numbers.
2. Paste it with your category list and receipt list.
3. Check every CHECK row yourself.
4. Spot-check 10 SURE rows. If any are wrong, add a rule and run again.
5. Give the reviewed sheet to your accountant. Don't file from it directly.

Watch out: The AI can't know if a purchase was personal or business, or your local tax rules, so a confident wrong category can slip into a tax filing.

## More

- [This story as a web page](https://agentstories.org/stories/ken-imoto-claude-code-bookkeeping-200-transactions-doubt-flags.html)
- [More stories: Get tasks done](https://agentstories.org/categories/get-tasks-done.html)
- [More stories from Japan](https://agentstories.org/countries/japan.html)
- [More stories that use Claude Code](https://agentstories.org/tools/claude-code.html)
- [Every story, indexed for AI assistants](https://agentstories.org/llms.txt)
