A hybrid analytic–holistic evaluation framework is developed and validated for assessing Information Technology (IT) undergraduate capstone projects in Thai higher education. Drawing on five academic years of multi-stakeholder assessment data, the research identifies five critical dimensions influencing evaluation outcomes: student competency performance, project proposal quality, advising effectiveness, panel variability, and assessment-criteria weighting. By integrating structured analytic rubrics with holistic panel judgments, the framework addresses persistent challenges of grading inconsistency, evaluator bias, and misalignment between academic assessment and industry expectations. Statistical analyses indicate that documentation quality, project innovation, and internship performance are the strongest predictors of final panel grades, explaining 72% of evaluation variance. The principal contribution lies in providing empirical evidence of assessment variability and a validated, replicable model that improves fairness, transparency, accreditation compliance, and alignment with professional IT competencies. The framework supports outcome-based education standards (ABET, ASIIN, ETQA) and offers practical guidance for enhancing quality assurance and graduate employability.

The rapid maturation of large language models has opened new opportunities for capable of enhancing learning outcomes, enriching instructional practice, and supporting large-scale computing education with high reliability through personalized, scalable, and data-driven instructional support. The ChatGPT Learning Companion (ChatGPT-LC) introduces a multimodal framework that integrates conversational scaffolding, code reasoning, misconception diagnostics, and learner analytics into a unified system capable of adapting instruction in real time. Deployed across 260 undergraduate learners in three programming courses, ChatGPT-LC produced substantial performance gains, including a 35.20% increase in concept mastery, 27.90% improvement in debugging accuracy, and error-type reductions ranging from 53.60% to 65.50%. Behavioral analytics revealed strong correlations between engagement intensity and performance (up to r = 0.740), with reflective and exploratory learners achieving scores above 88–90%. Instructor workload decreased by more than 32 hours per week, supported by high expert-verified accuracy (92–96%) of AI-generated feedback. System-level benchmarks demonstrated robust scalability, maintaining 97.00% success rates at 500 concurrent users and reducing latency from 450 ms to under 100 ms after optimization. Collectively, these results show that ChatGPT-LC functions not only as an automated tutor but as an adaptive cognitive partner capable of enhancing learning outcomes, enriching instructional practice, and supporting large-scale computing education with high reliability and pedagogical fidelity.