Every day, hundreds of citizens call the 1813 emergency hotline, but a high rate of misdirected calls puts further pressure on an already strained system. 1813AI focuses on citizens with injuries and is developing a citizen-facing, adaptive AI chat solution that, through a new self-service app, will provide guidance and retrieve information during wait time. This creates faster access to help, reduces staff stress, and contributes to a more equitable and efficient healthcare service.
The 1813AI project aligns closely with DIREC’s commitment to supporting responsible and scalable AI in the public sector. Building on national collaboration, public data, and European values, advanced research is combined with tangible benefits for citizens and public sector employees.
The project is anchored in a unique collaboration between the University of Copenhagen, the IT University of Copenhagen, and the Emergency Medical Services of the Capital Region of Denmark.
At the core of 1813AI is a locally fine-tuned language model, enhanced with Retrieval-Augmented Generation (RAG), ensuring that responses are based on verified health information. The model is designed to continuously improve while incorporating mechanisms for handling uncertainty—for example, by explicitly acknowledging when it cannot provide a definitive response.
By integrating Natural Language Processing with Human-Computer Interaction, the system offers a concrete demonstration of how language models can be applied responsibly in the public sector.
Development leverages Denmark’s largest dataset of emergency calls, comprising more than 4 million records. Clinicians, developers, and AI researchers collaborate closely throughout the process, while citizens are actively engaged through continuous testing and feedback.
|
|
Tariq Osman Andersen – Associate Professor – University of Copenhagen
|
![]() |
Christian Hardmeier – Associate Professor – IT University Copenhagen
|
![]() |
Hubert Dariusz Zajac – Post Doc – University of Copenhagen
|
![]() |
Mette Bjerg Lindhøj – Specialist Consultant – Emergency Medical Services, Capital Region
|


The opportunities with the 1813AI project are unique and important to us. We always seek to use our data to benefit citizens, and this project especially involves utilizing our very large call dataset and enable us to explore the potential with Al in practice. However, the application af LLMs is new to us – we have very little in-house expertise in that area, and it involves resources which are hard to find.
The project will be of strategic importance, since it will kickstart the work of exploring the potential by building in-house LLM/AI solutions into our self-service hub as opposed to partnering with external partners.
Mette Bjerg Lindhøj
Specialist Consultant at Digitalization
Emergency Medical Services
Capital Region of Denmark