Convergence of web service technology with intelligent and mobile agent technology, enhanced with context awareness, can produce a new software paradigm that will enable more efficient and effective mobile services. Traditionally, an agent has been a passive service requestor with the service processing happening at the provider's site. We propose that in some situations it would be beneficial if the agent could acquire the ability to execute the functionality provided by the service and run it locally instead of simply using the service. To this end, we build an analytical model which compares time consumption of traditional service access with that of component use. Such a model would allow an agent to dynamically select the more efficient approach. We describe experiments which compare the two approaches and discuss the results and lessons learnt