By the end of this lesson, you will be able to explain what autonomy means for an agent, match a level of autonomy to the risk of an action, and name the three human-in-the-loop patterns.
Imagine a brand-new employee at a company. On day one, they can decide which font to use in a memo without asking anyone: if they pick a slightly ugly font, nothing terrible happens. But they are definitely not allowed to sign a million-dollar contract on their own: if that goes wrong, it's a disaster that can't be undone. The manager doesn't say "you may do nothing" or "you may do everything." They say: "Small, reversible things, go ahead. Big, risky things, come and ask me first." The riskier the action, the closer a human should stay. Agents deserve exactly the same rule.
Preview — the rest of the lesson is for enrolled readers.
Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.
Sign inNo account yet? Create oneThe first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.