Bonsai: Designing for Cultivation in AI Interactive Digital Narratives
Authors of LLM-based interactive digital narratives (IDNs) struggle to preserve creative intent as player choices and real-time generation pull storylines in unpredictable directions. Existing frameworks treat IDNs as static once published, limiting authors’ insight into and control over the storylines that emerge from unexpected player input in the wild. We propose cultivation: a design metaphor in which LLM-generated branches are stored as persistent material for authors to shape through iterative curation. Authors seed an initial scenario; the system grows new branches in response to player exploration; authors prune and revise what emerges, accumulating preference data that steers future generation. We demonstrate cultivation through Bonsai, an IDN authoring tool, and complement this design account with three simulated experiments showing that learned preferences transfer to unseen scenes, are project-specific rather than portable, and improve substantially when extraction is structured around IDN authoring categories. This metaphor reframes human-AI creative collaboration: authors become gardeners, tending ever-growing branches rather than constraining ephemeral outputs.