Video presentation
ICMIF AI Summit 2026
Länsförsäkringar is exploring how generative AI can support customer service in a large, regulated mutual insurance environment. This case study highlights a practical approach to deploying AI responsibly, with attention to governance, service quality and long-term organisational readiness.
Länsförsäkringar’s customer-facing AI chatbot illustrates both the potential and the complexity of deploying generative AI in a regulated insurance environment.
The chatbot solution was designed using a multi-agent architecture, incorporating guardrails, domain-specific “area agents”, validation layers, and a tone-control agent to ensure brand consistency and accuracy. This layered approach was critical to managing risks such as hallucinations, inappropriate outputs, and security threats, especially given that customer-facing AI cannot rely on users to verify responses.
After 18 months in production, the chatbot handled approximately four out of five customer interactions, demonstrating strong efficiency gains and enabling 24/7 service. An unintended but valuable outcome was that employees also began using the chatbot to support their own queries, effectively turning it into an internal knowledge tool.
Speaker:
- Martin Björkman, Head of Data Science, Länsförsäkringar (Sweden)
Member only content
This content is only available to ICMIF members. Please complete the form and we will get back to you as soon as possible.
Access the full member-only content
This is an abridged version. To access the full article/recording, please complete the form above to request the link to the full version being sent directly to you, or visit the member-only link for the ICMIF Knowledge Hub (for more details of how ICMIF members can access this please click here or contact ICMIF).
