The University of Edinburgh and research sponsors are authorised to reproduce and distribute reprints and on-line copies for their purposes notwithstanding any copyright annotation hereon. The views and conclusions contained herein are the author’s and shouldn’t be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of other parties.

Despite rapid advances in Web Services, the user community as demanding requirements continue to outstrip available technology solutions. To help close this gap, Semantic Web Services advocates are defining and implementing many new and significant capabilities (www.swsi.org). These new capabilities should more fully harness Web Services' power through explicit representations of Web resources' underlying semantics and the development of an intelligent Web infrastructure that can fully exploit them. Semantic Web languages, such as OWL, extend RDF to let users specify ontologies comprising taxonomies of classes and inference rules. Both people and software agents can effectively use Semantic Web Services. Agents will increasingly use the combination of semantic markup languages and Semantic Web Services to understand and autonomously manipulate Web content in significant ways. Agents will discover, communicate, and cooperate with other agents and services and - as we'll describe - will rely on policy-based management and control mechanisms to ensure respect for human-imposed constraints on agent interaction. Policy-based controls of Semantic Web Services can also help govern interaction with traditional (nonagent) clients. In the mid 1990s, we began to define the initial version of KAoS, a set of platform-independent services that let people define policies ensuring adequate predictability and controllability of both agents and traditional distributed systems. With various research partners, we' re also developing and evaluating a generic model of human-agent teamwork that includes policies to assure natural and effective interaction in mixed teams of people and agents - both software and robotic. We're exploiting the power of Semantic Web representations to address some of the challenges currently limiting Semantic Web Services' widespread deployment.