Dual-Mode Adaptive AI Persona Recommendation for Blockchain Education: A Mixed-Methods Evaluation of the PITL System Based on Dreyfus Competency Levels

The rapid proliferation of large language models has created significant opportunities for personalized education, yet existing systems rarely account for user competency as a determinant of interaction quality. This study introduces Persona in The Loop (PITL), a dual-mode adaptive framework that recommends AI personas for blockchain and smart contract education applications. PITL employs 100 AI personas organized across two domains, ten sub-specialties, and five Dreyfus competency levels, recommending personas via either similarity-based mode grounded in Cognitive Load Theory or complementary mode grounded in the Zone of Proximal Development, with an adaptive switching mechanism driven by NASA-TLX cognitive load feedback. A mixed-methods study with 150 participants using a 2 × 5 factorial design showed that the complementary mode produced higher learning gains, while the similarity-based mode yielded lower cognitive load and higher code quality. The adaptive mechanism outperformed both fixed-mode conditions on learning gain and code quality. The Mode × Dreyfus interaction was significant for cognitive load and task duration but not for learning gains, suggesting mode effects on learning outcomes are consistent across competency levels. Qualitative interviews with 20 participants corroborated quantitative findings. PITL offers a theoretically grounded and empirically validated approach to competency-based AI persona recommendation in educational contexts.