AI and automation

AI and finance automation

I build the tooling around the accounting work I am responsible for. That means the automation has to survive an audit, which changes what you are willing to automate.

The accountant who builds

Most automation builders do not understand accounting controls, and most accountants do not build automation. I do both, which means the systems I build respect the controls they run inside.

In practice the difference shows up in where the automation stops. Someone approaching a bank reconciliation purely as an engineering problem will try to automate the whole thing, because from the outside it looks like a matching exercise. Someone who has had to explain that reconciliation to an auditor knows which decisions have to stay with a person, and builds the automation to hand those decisions over cleanly rather than absorb them.

How I decide what to automate

Every process I have automated in finance has been split the same way, into three kinds of work.

Clerical work

Gathering, formatting, routing, matching, chasing status. No judgment is involved and nothing is being decided. This is where automation pays for itself, and it is usually most of the volume.

Assisted judgment

Work where a proposal can be generated with reasoning attached and a person accepts or rejects it. The automation drafts, the person decides. Useful as long as the reasoning is visible and rejecting is as easy as accepting.

Control points

Approvals, exception resolution, anything that creates an obligation or moves money. These stay with an authorized person. Automating a control point does not make a process faster, it makes it undefendable.

Getting that boundary right matters more than the tooling. An automation that quietly closes out exceptions is worse than no automation, because it removes the signal that something is wrong while appearing to improve throughput.

What I have built

The work below came out of problems in my own close, not from looking for a reason to use a new tool.

All projects

Tools

I use Claude, ChatGPT, and Codex daily to build finance tools, n8n for workflow automation on a self-hosted VPS, and Supabase and Next.js when something needs to be a real application rather than a workflow. For anything touching private data I run local models instead.

  • Claude (Chat, Cowork, Code)
  • ChatGPT
  • Codex
  • n8n (workflow automation)
  • Supabase (database and API for large datasets)

Beyond finance

The same approach applies outside accounting, which is why I started Hawk Eye AI. Small businesses lose work to problems that are nobody’s fault: a call that came in while everyone was busy, a follow-up that did not happen because the next morning got away from them. Those are process problems, and they respond to the same treatment.

Read about Hawk Eye AI

Articles on automation

Thinking about automating something in finance?

If you are working out where the line should sit between automated and reviewed, that is a conversation I enjoy having.