When an idea seems intuitively bad but its test cost is low, approve it as a cheap experiment instead of rejecting it on intuition alone.

If you vanished for two weeks with no contact, what stops? That's your urgent delegation list.

Don't default to the biggest model. Choose by: task depth, cost, privacy, speed.

Don't subscribe to a new tool before truly using it 14 days in real workflow.

Just as you brainstorm 10 titles, generate 5 different thumbnail/cover concepts, and pick via a small sample, not instinct alone.

Know when to ask AI to generate new code versus review existing code — the two uses need different prompts and different caution.