I'm the GC building an AI-powered legal function at Worksome and I’m documenting everything.
When product wanted to build a bot at our hackathon, I asked one question: How often does this come up? The answer changed their plans. Here's my five-question framework for deciding what's actually worth building and what decisions you need to make along the way.
AI acts more like a human than we admit. Give it imprecise instructions over a long conversation and it gets confused, same as a person would. Except a person who fixes an error, fixes that error. AI tends to rewrite the whole thing. So I built a skill that makes it prove the work is actually done, category by category, before I take “looks good” on faith.
I had eight worker agreements, eight different outside counsel drafting styles, and a plan to fix all of it at once with AI: pull in the substantive revisions, reformat everything to match, and reorder every clause so IP rights lands in the same spot no matter which country you're looking at. Three jobs, one prompt, zero upfront plan. Here's exactly where it fell apart, including the moment I told AI to "just start over" and it decided to be even more helpful.