I used to check slides the hard way - clicking every object, eyeballing every font, hoping I'd catch what my eyes kept missing. Then I wrote a script to do it for me. My first reaction was: oh shit, that actually worked. What happened after I ran it four more times is the part nobody talks about.

I pasted my messy notes in. Not the polished draft — the real one. I wasn't looking for publishable output. I wanted a second pass on my thinking. Three weeks in, something shifted. AI wasn't editing my status updates anymore. It was pressure-testing my judgment. That's a different thing entirely.

I wasn't avoiding AI because I doubted it. I was avoiding it because I thought it required a project. So I gave myself a constraint: if something would take less than 10 minutes to try, I'd try it. No optimization. No perfect prompt. Just a quick experiment layered into real work. What happened after wasn't what I expected.

I was re-thinking the same framing decisions every week. How direct should the summary be? What counts as a real risk versus noise? None of that was strategic. It was just repeated cognitive setup. I wasn't looking for automation. I was looking for less friction.