The integration of AI-powered plush robots in educational and therapeutic settings for children with Autism Spectrum Disorders (ASD) necessitates a robust interdisciplinary methodology to evaluate usability, psychological impact, and therapeutic efficacy. This study proposes and applies a four-phase research framework designed to guide the development and assessment of AI-powered plush robots for social rehabilitation and education. Phase 1 involved semi-structured interviews with 13 ASD specialists to explore robot applications. Phase 2 tested initial usability with typically developing children (N = 10–15) through structured sessions. Phase 3 involved structured interaction sessions with children diagnosed with ASD (N = 6–8) to observe the robot’s potential for rehabilitation, observed by specialists and recorded on video. Finally, Phase 4 synthesized data via multidisciplinary triangulation. Results highlighted the importance of iterative, stakeholder-informed design, with experts emphasizing visual properties (color, texture), psychosocial aspects, and adjustable functions. The study identified key technical and psychological evaluation criteria, including engagement, emotional safety, and developmental alignment with ASD intervention models. Findings underscore the value of qualitative methodologies and phased testing in developing child-centered robotic tools. The research establishes a robust methodological framework and provides preliminary evidence for the potential of AI-powered plush robots to support personalized, ethically grounded interventions for children with ASD, though their therapeutic efficacy requires further longitudinal validation. This methodology bridges engineering innovation with psychological rigor, offering a template for future assistive technology research by prioritizing a rigorous, stakeholder-centered design process.