What works, what goes wrong, and how to tell the difference.
Reading somebody's documentation and turning it into a working call is exactly the boring middle that agents are good at. The failure mode is inventing an endpoint, so make it run the request.
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.