Recommendations for future CA development: educator design templates, multilingual support, and theory-informed pedagogical integration¶

Strategy · All strategies
Evidence · 3 claims (3 for) · 1 study (1 review), q2 · 0 of 1 report an effect size · 3 claims rest on one study

Description¶

The review proposes actionable strategies for future CA development in programming education. It recommends developing "modular, customizable templates that educators can easily adapt for their specific programming courses" integrating scaffolding, cognitive load management, and formative feedback; establishing multilingual support guidelines, since "Prioritizing such multilingual support should therefore be considered a strategic design choice to enhance educational outcomes"; and explicitly integrating pedagogical models such as 4C/ID, scaffolding, and chain-of-thought prompting into CA dialogue logic.

Design Implications¶

Context¶

Requirements¶

• Interdisciplinary development strategies drawing from education, psychology, and HCI

Constraints¶

• The review notes such theory-driven integrations currently remain isolated examples

Target Learners¶

• novice programmers in introductory programming courses

Target Learning Goals¶

• programming skills, algorithmic thinking, sustained engagement

Claims¶

• English dominates CA interaction languages: 17 of 23 prototypes relied exclusively on English even though only seven studies originated from English-speaking countries [+W]
• Four reviewed CAs explicitly integrate pedagogical theories, including the Vygotskian perspective, the 4C/ID model, scaffolding, and gamification [+W]
• Only 4 of 23 reviewed conversational agent studies explicitly apply learning theories, indicating a gap between CA development and pedagogical grounding [+W]

Related Strategies¶

• Design AI-enhanced learning management systems that explicitly target engagement across cognitive, emotional, behavioral, and social domains

Examples¶

-

Key Sources¶

• Barzanji and Loitsch. (2025). Exploring conversational agents for novice programmers: a scoping review. Discover Artificial Intelligence. https://doi.org/10.1007/s44163-025-00521-4