Beginner article
Human agency is not a button, for beginners
Why responsible agent systems need real human authority, not just a decorative approval prompt.
Plain meaning
What this means
Human agency means the person keeps meaningful control over direction, boundaries, and consequences. A button only helps if the person has real information and real choice.
Why it matters
Why a beginner should care
A system can look safe while quietly pushing humans to approve things they do not understand.
Small safe example
Try it safely
Before an agent sends an external message, show the draft, source context, risk, and exact action for human approval.
First moves
The smallest useful path
Common mistake
What to avoid
Adding an approval step after the system already made the important decision.
Guardrails
Keep these checks steady
- Use approvals before external effects.
- Avoid vague yes or no prompts.
- Keep authority boundaries visible.
- Respect human override.
Go deeper
When you want the full version
This beginner article gives you the practical starting point. The full AI Lab topic has the technical details, implementation notes, and deeper structure.