The polite version yielded better learning outcomes, and the effect was amplified in learners who expressed a preference for indirect feedback, who had less computer experience, and who lacked engineering backgrounds. These results confirm the hypothesis that learners tend to respond to pedagogical agents as social actors, and suggest that research should focus less on the media in which agents are realized, and place more emphasis on the agent's social intelligence.

The largest conclusion we can draw comfortably from the data is that development time still varies considerably for each type of learning product—and no matter what, the variables of the training development for each organization greatly differ. We do not advise that you use the results as stand-alone pieces for calculating project estimates because context is necessary to understand respondents' situations.