Abstract
Many educators utilize generative artificial intelligence (GenAI) to streamline demanding workloads and accelerate the individualization of instruction for students with disabilities (SWD). However, challenges may arise if such tools perpetuate ineffective instruction for SWDs. To address this issue, CoIEP was developed. CoIEP is a large-language-model-based multi-agent system specially designed to assist educators in developing individualized programming and evidence-based instruction for SWDs. This article describes how CoIEP, combined with an explicit instructional decision-making process, can support special and mathematics education co-teachers in efficiently designing evidence-based instruction for SWDs. To bridge ongoing debates on effective mathematics instruction for SWDs within both special and mathematics education, this collaborative approach intentionally integrates opportunities for SWDs to foster metacognition (i.e., “thinking about thinking”) as a bridge, a shared understanding, between the two communities. This article presents a step-by-step overview outlining how co-teachers can effectively prompt CoIEP to design evidence-based, metacognition-aligned mathematics instruction for SWDs.
Get full access to this article
View all access options for this article.
References
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
