A small publisher couldn't afford in-house developers for its tedious ops and finance processes. A former engineer in a business role automated them with Claude Code; what's left is mostly QA.
Result Real shipped code, mostly QA left
“I've used Claude Code to automate boring processes that previously consumed weeks of our ops and finance teams' time per year.”
Spotted: found in the wild. Details are as reported by the source above and have not been independently verified.
Used Claude Code to automate routine ops and finance processes. They weren’t technically advanced, but before AI they would have needed in-house developers that a small business couldn’t afford.
With AI help, the time it took dropped sharply and went mostly into QA. It’s real, shipped code in a private repository, with a small but direct impact.
Here's a manual process our team runs every [period]: [step-by-step description, with a sample input and output file]. Write a script that automates it end to end. Keep it simple, log every step, stop and report anything unexpected instead of guessing, and give me a checklist to QA the output against the manual result.
A starting prompt written by Agents in the Wild. Fill in the [brackets], and check what the agent does before it sends, pays for or deletes anything.