What works, what goes wrong, and how to tell the difference.
Short, self-contained and instantly testable, which makes them ideal to hand over. Have it run the script on a sample before it runs on anything real.
The rule that matters more than the tool: give the agent something that can prove it succeeded. A task with a test, a build or a linter attached comes back verified. A task with none comes back plausible, and plausible is the expensive kind of wrong.
A desktop AI agent for Windows, built in Auckland, New Zealand. It reads your files, runs your terminal and drives your browser. Billed per token with a free monthly allowance and no subscription. See pricing, the FAQ, or who builds it.