Output: This project provided us with numerous unexpected learning opportunities and allowed us to demonstrate significant agility in a highly dynamic, fast-paced environment.
Watched the video. Yeah, it’s cheesy, it’s not perfect, but it’s pretty f-ing good nonetheless. IMO, this article reads like a stodgy old English professor berating a freshman essay because it wasn’t world class literature.
I have found enabling the codebase itself to be the “Claude.md” to be most effective. In other words, set up effective automated checks for linting, type checking, unit tests etc and tell Claude to always run these before completing a task. If the agent keeps doing something you don’t like, then a linting update or an additional test often is more effective than trying to tinker with the Claude.md file. Also, ensure docs on the codebase are up to date and tell Claude to read relevant parts when working on a task and of course update the docs for each new task. YMMV but this has worked for me.
For this to truly be funny, it needs to be installed on on an unsuspecting user’s laptop, preferably some C-level type about to join an in-person board meeting.