Designing AI-Assisted Interaction Concepts for Collaborative Scientific Work
Multimodal Interaction for Electronic Laboratory Notebooks
My Role
Student
Supervision / Team
Prof. Robin Neuhaus (Supervisor)
Tools & Tech
The Challenge
Scientific research today is increasingly collaborative, data-intensive, and distributed across people, time, and tools. While Electronic Laboratory Notebooks (ELNs) have replaced paper notebooks in many labs, their role often remains limited to after-the-fact documentation rather than actively supporting researchers during ongoing work. Through preliminary research, it became clear that many ELNs feel rigid and disconnected from real laboratory practices. Researchers frequently juggle experiments, data interpretation, and collaboration under time pressure, yet documentation and knowledge reuse are treated as secondary tasks. This creates friction, fragmented records, and a loss of contextual knowledge—especially when experiments span multiple days or team members. At the same time, emerging AI technologies offer new possibilities to support scientific work. However, there is a clear gap between technical AI capabilities and meaningful, trustworthy interactions that fit naturally into laboratory workflows. The central challenge of this thesis was therefore not how to build AI, but how to design AI-assisted interactions that genuinely support collaboration, sense-making, and continuity of work—without increasing cognitive load or disrupting established practices.
Approach & Solution
This thesis followed a user-centered design approach, grounded in Human–Computer Interaction (HCI) and Computer-Supported Collaborative Learning (CSCL) principles. Rather than proposing a fully automated system, the focus was on designing interaction concepts that carefully integrate AI as a supportive collaborator. User needs and design requirements were derived from a combination of empirical data and literature, including surveys conducted within a large research institute, prior workshop findings, and existing research on collaborative work, distributed cognition, and cognitive load. These insights informed the design of an AI-assisted ELN interaction concept that combines two complementary modalities: Hands-free voice interaction, allowing researchers to document experiments during lab work without breaking focus or workflow A conversational chatbot interface, enabling researchers to retrieve past experiments, explore shared knowledge, and maintain continuity across team members and time Rather than treating the ELN as a passive repository, the proposed concept reframes it as an active partner in scientific sense-making. The design emphasizes transparency, progressive disclosure, and user control, ensuring that AI suggestions remain understandable and trustworthy. To evaluate the concept despite limited access to domain experts, a Wizard-of-Oz user study was conducted. This allowed realistic interaction scenarios to be tested while keeping the AI behavior controlled and interpretable. The evaluation combined standardized measures—such as perceived workload, usability, and trust—with qualitative feedback to capture both experiential and reflective aspects of use.
Key Outcomes & Impact
A structured set of user needs and design requirements for AI-assisted ELNs
A conceptual prototype illustrating voice interaction and conversational AI
Design insights reducing cognitive load and improving collaboration
Empirical findings on trust, usability, and workload
Practical guidelines for integrating AI in research systems
A design-oriented perspective on AI in scientific workflows