TombWriter: Scaffolding Story Archeology through Beat-Level Interaction in Human-AI Co-Writing
For researchers and designers of AI co-writing tools, this work introduces a new interaction paradigm (story archeology) that prioritizes writer agency and structural control, though the qualitative findings are preliminary and based on a small sample.
The authors propose story archeology, an LLM-based co-writing approach where prompts are refined over time at the beat level to extract the writer's intended story. In a qualitative study with five experienced writers, they found that writers valued the system for structural discovery but reported voice loss and framed AI as a generation engine rather than a collaborator.
The dominant paradigm for LLM interaction in AI co-writing uses disposable prompts that vanish after use. This may lead to imprecise results, cumbersome workflows, and diminished author agency and ownership. We propose LLM-based story archeology, where prompts serve as a hierarchical story instrument refined over time to extract the writer's intended story. Drawing on the fossil theory of story- telling, where stories exist as latent structures that writers excavate through their craft, this approach supports agency and ownership through high involvement and control. Writers work at the level of story beats rather than prose. They generate character actions in scenes to discover emergent possibilities, simulated by the LLM or directly nudged, then edit resulting beats to refine scenes iteratively. Prose is generated from beats based on style and genre, separating structure from style. We developed TombWriter, a web-based tool that visualizes stories as navigable cards -- characters, scenes, and beats -- through a five-stage narrative pipeline. We conducted a qual- itative study with five experienced writers who used the system over three days. Through semi-structured interviews, we found that writers framed AI as a generation engine rather than collabo- rator, claimed ownership while reporting voice loss, and valued the system for structural discovery rather than prose production. We contribute the story archeology approach, the TombWriter system, and qualitative findings on beat-level human-AI co-writing.