A new thing I'm trying out: having the LLM keep track of the experiments I ship

I realized I'm shipping a ton of updates but having a hard time remembering two weeks out to go back and check to see if they worked So I asked the LLM to make a small command to log each experiment for us to track and review later. It keeps track of: - hypothesis - feature - success criteria (and what system to check them in!) - timeline And I added a rule to prompt me to log an experiment as we are completing each item we work on. Today I went back through the last week and added review points for stuff we shipped, as well as a few new experiments that we are running starting today