AIToday
Large Language ModelsAI Coding AssistantsZenn AI/MLPublished: Oct 6, 2026, 10:01 JST

Claude Code powers a one-person firm's back office

Claude Code powers a one-person firm's back office

3 Key Points

  1. What happened

    A sole proprietor running AI-adoption and process-improvement work built a 'company' repository on Claude Code, where a main Claude takes requests and dispatches them to six sub-agents — research, accounting, planning, sales, legal and design. It began as one commit of 487 lines of Markdown and grew through 14 commits over roughly half a year.

  2. Why it matters

    The features he kept adding were not about what to tell the AI but about memory and information control — split state files, a single-writer rule, and no absolute paths — the same things a human organization calls information management.

  3. What to watch

    The state files are outgrowing their purpose: company.md keeps swelling even though it must stay concise, and the decision log has reached nearly 100KB, so organizing old facts and splitting files is now needed. He also suspended monthly scheduled runs and per-department persistent memory.

WHO IT HITSSolo founders and small-firm owners who want to delegate recurring back-office chores — trademark checks, bookkeeping, invoices, brand assets — to an AI setup rather than a hire. It also speaks to IT or operations staff weighing how to keep sensitive business records out of public code repositories.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Context & Analysis

The build started in April, before the June 2026 business-opening filing, because the founder found that non-core work — picking a trade name, filing, deciding on invoice registration, opening a business account, making a logo — was heavier than expected and had to be re-researched each time. The first version was one commit and 487 lines of Markdown; the finished shape came after 14 commits, and most changes were responses to problems that showed up in operation.

Those problems mostly concerned trust and continuity. To check research, he added a review mode that verifies existing reports on three axes — factual sourcing, logical leaps, and missed alternatives — and runs it in a context separate from the agent that did the research. To stop decisions vanishing between sessions, he created the state directory and a sixth flow step so the main agent records before ending a turn. When rules alone were not enough, he added a Stop hook that calls a second model to send back turns with missing records, written so that ambiguous cases pass through to avoid annoying reversals.

A drive migration in August broke absolute paths everywhere — including references to state/company.md in all six department definitions, which failed silently so agents worked without their premises. He removed absolute paths entirely, leaving symbolic links as the only place the real location is known, and unified Python execution on uv after dependencies in /tmp disappeared. The remaining friction is that the state files keep growing and there is still no check that symbolic links resolve at startup, so whether this stays a one-person company or needs reorganizing likely hinges on how he splits and prunes those files.

FAQ
What can this Claude Code setup actually do?
In about half a year it handled choosing a trade name from 10 candidates after checking trademarks and domain availability, preparing the business-opening and blue-return filings, building brand colors and logo, drafting a business plan and website copy, writing internal information-handling rules, and comparing business bank accounts and tax accountants.
How does it keep the AI from forgetting decisions between sessions?
He split state into three files with different jobs — confirmed facts, a decision log, and open tasks — and imports company.md and open-loops.md into CLAUDE.md so they load every session. Only the main Claude may write; sub-agents are read-only and return change candidates in a 【状態差分】 section for the main agent to verify.
Why does he avoid putting business files on GitHub?
Deliverables include application documents, and the state files would otherwise be barred from holding personal information. He moved both to a network drive and left symbolic links in the repository, so only CLAUDE.md, README.md and .claude/ appear on GitHub.

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleAleph Alpha releases Kolibri, a sovereign open-weight model