This paper illustrates the conceptual and operational architecture of an Artificial Intelligence (AI)-based instructional co-design device. Placing itself at the intersection between Special Pedagogy, educational technologies and Universal Design for Learning (UDL), the contribution presents the design of a device capable of making the dialogue between curricular teachers and specialized teachers for support activities more functional in order to design inclusive teaching formats. The design of the device is divided into three interconnected phases: the "low-impact" micro-design (the Lesson Project File), the observation and description of the class context (Observation Matrix) and the generation of personalized teaching mediators through specific engineered prompts. The research protocol includes a within-subjects methodology divided into three phases: a control phase (traditional lesson), an experimental phase (lesson with the support of the AI device) and a qualitative phase (semi-structured interviews with teachers and students). The expected results foreshadow significant repercussions on the sustainability of inclusive teaching and on the culture of shared planning.
Inclusive co-design and artificial intelligence (AI) device: an experimental research protocol for schools
Borsini L.
2026
Abstract
This paper illustrates the conceptual and operational architecture of an Artificial Intelligence (AI)-based instructional co-design device. Placing itself at the intersection between Special Pedagogy, educational technologies and Universal Design for Learning (UDL), the contribution presents the design of a device capable of making the dialogue between curricular teachers and specialized teachers for support activities more functional in order to design inclusive teaching formats. The design of the device is divided into three interconnected phases: the "low-impact" micro-design (the Lesson Project File), the observation and description of the class context (Observation Matrix) and the generation of personalized teaching mediators through specific engineered prompts. The research protocol includes a within-subjects methodology divided into three phases: a control phase (traditional lesson), an experimental phase (lesson with the support of the AI device) and a qualitative phase (semi-structured interviews with teachers and students). The expected results foreshadow significant repercussions on the sustainability of inclusive teaching and on the culture of shared planning.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


