Scriptorium enables multi-human multi-AI teamwork for digital library search
Scriptorium: System Design and Implementation of a Multi-Human, Multi-AI Collaborative Digital Library Search Platform
Human-Computer InteractionInformation Retrieval
Summary
Searching digital libraries can be complicated when multiple people work together and use AI tools. The authors built Scriptorium, a platform where several people and AI agents collaborate openly, showing all search actions to everyone involved. Their system uses specialized AI roles managed by a central coordinator to help groups find and share information more effectively. They also explain how the system works in detail and plan to test if this teamwork method helps ideas spread better between collaborators.
What this means in practice
- •For knowledge management teams: Coordinate multiple humans and AI agents to improve collective search in organizational knowledge bases.
- •For enterprise software developers: Implement transparent multi-user and multi-AI collaboration features in digital library or information retrieval platforms.$Commercial implications: Enables development of commercial collaborative AI-driven search products suited to enterprise workflows with enhanced transparency and multi-agent support.
Authors
Abbas Pirmoradi, Milad Momeni, Anna Chu, Orland Hoeber
Abstract
This technical report documents the design and implementation of Scriptorium, a digital library search interface designed to support multi-human, multi-AI collaboration: full cross-user transparency of search activity combined with a Manager--Worker architecture of seven role-specialized generative AI agents. A companion short demonstration paper describes Scriptorium's interaction design; because a demonstration format is constrained to a few pages, it necessarily omits most implementation detail. This report documents Scriptorium's complete system architecture, data model, collaborative-interaction design rationale, and AI orchestration mechanism, including verbatim agent prompts, the deterministic guardrails that constrain them, the language model and retrieval configuration, and the steps needed to run the system, so that the design can be inspected, critiqued, reproduced, and reused by other researchers. We also discuss the system's current limitations and the user study we are planning to evaluate its central hypothesis: that combining collaborative transparency with scoped multi-agent AI assistance increases serendipitous cross-pollination between collaborators' research threads.