When an agent A communicates with another agent B, a certain amount of information I is transferred from A to B by means of an ACL message. Inside the ACL message, I is represented as a content expression consistent with a proper content language (e.g. SL) and encoded in a proper format (e.g. string). Both A and B have their own (possibly different) way of internally representing I. Taking into account that the way an agent internally represents a piece information must allow an easy handling of that piece of information, it is quite clear that the representation used in an ACL content expression is not suitable for the inside of an agent.
Read the rest of this entry »