Tinker Tales: A Tangible Dialogue System for Child-AI Co-Creative Storytelling

Tinker Tales is a tangible dialogue system combining physical storytelling boards, NFC-embedded toys, and mobile apps to enable child-AI collaborative storytelling. A user study with 8-year-olds demonstrates that conversation design and prompt framing significantly influence how children engage in co-creative dialogue with AI agents, with educational scaffolding affecting narrative consistency and contribution patterns.

Tinker Tales represents an emerging frontier in human-AI interaction design, specifically addressing how conversational architecture shapes creative collaboration between children and AI systems. The research moves beyond treating dialogue systems as simple question-answering tools, instead positioning them as intentional pedagogical instruments that guide creative thinking through carefully structured prompts. This distinction matters because it reveals that AI-mediated experiences aren't neutral interfaces—they actively shape cognitive and creative outcomes through design choices.

The tangible interface approach combining physical artifacts with voice-based dialogue addresses a critical gap in child-AI interaction. Young learners benefit from embodied cognition, where physical manipulation reinforces conceptual understanding. By embedding NFC technology in toys and integrating them with mobile apps, the system bridges digital and physical play spaces in ways that align with established educational theory around narrative development and social-emotional learning. This multimodal approach contrasts with text-only conversational AI implementations.

The user study findings reveal that prompt framing—specifically whether the AI provides educational scaffolding for narrative elaboration—directly influences children's responses. When prompts structure thinking more explicitly, children produce more consistent narrative contributions. For developers and educators, this suggests conversational AI requires intentional design to achieve learning objectives; generic dialogue systems may fail to support desired educational outcomes.

This work signals growing recognition that AI systems in educational contexts need explicit pedagogical architecture. As AI tutoring systems proliferate, understanding how conversation design affects learning becomes commercially and educationally critical. Future development likely involves scaling these insights across age groups, measuring long-term learning retention, and exploring how different narrative scaffolding approaches optimize various educational competencies.

• →Conversational prompt design directly shapes how children engage in co-creative storytelling with AI agents
• →Tangible interfaces combining physical toys with voice dialogue improve engagement for young learners aged 6-8
• →Educational scaffolding in prompt framing increases consistency and quality of children's narrative contributions
• →AI systems in educational settings require intentional pedagogical architecture rather than generic dialogue design
• →This research bridges embodied cognition theory with modern conversational AI for child-centered learning experiences