Agent software is a topic of growing interest to users and developers
In the computer industry Already, agents and wizards help users automa
te tasks such as editing and searching for information. But just as we
expect human assistants to learn as we work with them, we will also c
ome to expect our computer agents to learn from us. This paper explore
s the idea of an instructible agent that can learn both from examples
and from advice. To understand design issues and languages for human-a
gent communication, we first describe an experiment that simulates the
behavior of such an agent, Then we describe some implemented and ongo
ing instructible agent projects in text and graphic editing World Wide
Web browsing, and virtual reality Finally, we analyze the trade-offs
involved in agent software and argue that instructible agents represen
t a ''sweet spot'' in the trade-off between convenience and control.