Design the human-in-the-loop approval gate
Rung 4 of 10 · Constraints + negative instructions
1 · Learn the move · Constraints + negative instructions
Mark every step where a human must approve before it fires. Anything client-facing, money-moving, or compliance-sensitive never sends unreviewed. In a Cowork routine that means the skill stops and waits for your yes. The gate is the difference between leverage and a license complaint.
You are a workflow designer. Take my lead-reply workflow and add a human approval gate: AI may draft, but nothing sends until I approve. List exactly which steps must never auto-send and why. [workflow]
2 · Your turn. You write the prompt
Your AI-drafted lead replies could go straight to clients unread. Write a prompt that inserts an approval checkpoint so nothing reaches a client until you've seen it.
Remember: the AI sees only your prompt, not this page. If the situation isn't in your prompt, it doesn't exist.
Optional. These shape the output when you run your prompt below, not your score.