I had 55 pages of documentation to write, 59 screenshots to capture, and a product that was still shipping features and being rebranded weeks before release. I did it in four days with Goose , an open-source AI agent by Block, part of the Linux Foundation, and I want to walk you through exactly how. Not the polished version. The real one: how I built it, how it works, everything that broke along the way, and what I learned from it. The Problem The AI Platform by Zephyr Cloud is a desktop app where teams collaborate with AI specialists in channels. Think Slack meets AI agents. The product had been moving fast for months. Features were shipping, the UI was evolving, and the documentation was... not keeping up. What existed was a handful of developer-focused reference pages. Markdown files describing CRDT schemas and workflow adapter formats. Useful if you were building the product. Useless if you were trying to use it. We needed end-user documentation.…