In this paper we describe an experiment in building Grid-aware software components as basic blocks for highperformance, adaptive Grid computations. Within the Grid.it project we are working to the enhancement of the coordination language approach of the ASSIST parallel programming environment to support high-performance software components, that can react to the changes occurring on dynamic execution platforms. We are currently evaluating expressiveness and performance issues also by integrating ASSIST compilation tools with various component frameworks. In the paper we discuss results about a graphical application made up of four CCM components, each one produced by automatic encapsulation of a parallel program. We evaluate performance behaviour by comparing the composite application with the equivalent ASSIST one, on three different testbeds: homogeneous and heterogeneous clusters, and a small Grid over a WAN. We also report first results about an Application Manager component that applies a simple adaptive policy, reacting to pipeline unbalance, to vary the amount of employed computational resources.