This article examines the issue of developing semantics for agent communica
tion languages. In particular, it considers the problem of giving a verifia
ble semantics for such languages-a semantics where conformance (or otherwis
e) to the semantics could be determined by an independent observer. These p
roblems are precisely defined in an abstract formal framework. Using this f
ramework, a number of example agent communication frameworks are defined. A
discussion is then presented, of the various options open to designers of
agent communication languages, with respect the problem of verifying confor
mance.