The field of multi-agent systems shifts attention from one
particular agent to a society of agents; hence the interaction between
agents in the society become critical towards the achievement of their
goals. We assume the interactions are managed via an agent protocol
which enables agents to coordinate their actions in order to handle the
dependencies that exist between their activities. An agent's failure to
comply with the constraints attached within the protocol might cause a
brittle protocol to fail. To address this problem, a constraint
relaxation approach is applied using a distributed protocol language
(i.e. LCC). This talk describes the design and implementation of a
constraint relaxation module to be integrated within LCC framework.