By the end of this lesson, you will be able to name the four main risks of agents that act (mistakes at scale, unclear responsibility, manipulation, impact on people), explain prompt injection with an analogy, and say why safety must be designed in from the start.
Giving someone directions to your house is no big deal. If they get a direction wrong, they end up lost for a few minutes, that's all. Handing someone the keys to your car is a completely different matter. If they make a mistake behind the wheel, someone could get hurt, and there's no undo button. Chatbots give directions: they talk, and a wrong answer is annoying but usually harmless. Agents hold the keys: they act, and a wrong action can have real consequences. That's why agents deserve the same extra caution you'd use before handing over your keys.
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.