Reactive software agents - 1
Do not possess internal, symbolic models of their environments; instead they act/respond in a stimulus-response manner to the present state of the environment in which they are embedded
relatively simple -- interact with other agents in a basic way. Viewed globally, complex pattern of behaviour might emerge.
Key ideas: emergent complexity, task decomposition (agent = collection of autonomous modules responsible for specific task, inter-module communication is minimised), tend to operate on (representations of) raw data