Learning how to program in Primary Education has attracted significant research in recent years. It is unclear though how programming environments and languages should be adapted to children to achieve better learning and use, but one trend seems to be the use of Scratch. The question in this paper is what programming environment can be used to continue teaching programming to children who have already been taught Scratch for years. This paper's proposal is that students aged between 10 and 12 can benefit from interacting with a friendly learning companion using p-code such as Alcody. The hypothesis is that students (aged between 10 and 12) with a knowledge of Scratch will be able to significantly improve their scores by using a learning companion to teach them how to program even during the COVID-19 pandemic. To check the hypothesis, an experiment was carried out during the 2019/2020 academic year with 137 students in Ecuador. A significant improvement in the scores of the students was recorded together with high satisfaction.

No abstract

No abstract

No abstract

Pedagogic conversational agents are computer applications that can interact with students in natural language. They have been used with satisfactory results on the instruction of several domains. The authors believe that they could also be useful for the instruction of computer science programming. Therefore, in this chapter, the MEDIE methodology is described to explain how to create an agent to teach programming to primary education children and develop their computational thinking. The main steps are to communicate with the teacher team, to validate the interface, and to validate the functionality, practical sessions, and evaluation. The first two steps are covered in this chapter.