PostNord Overhauls Swedish Customer Support with ElevenLabs ElevenAgents Multi-Agent AI System
PostNord, the postal service for Sweden and Denmark, replaced its Swedish customer support line's AI phone system with a multi-agent system built on the ElevenLabs ElevenAgents platform, as detailed in an ElevenLabs case study published on November 17, 2026.
A New Era for PostNord's Customer Service
The core of PostNord's updated system is an orchestrator that intelligently classifies incoming caller needs. Once a caller's intent is understood, the orchestrator routes them to one of four specialized subagents. This includes a dedicated parcel-tracking agent, streamlining inquiries related to package delivery.
A key capability of the new system is its advanced language processing. It understands and speaks natural Swedish, including various regional dialects, ensuring broad accessibility and a more intuitive interaction for callers. The system operates 24/7, providing round-the-clock support without human intervention.
Improved Efficiency and Task Completion
The implementation of the ElevenAgents platform has led to a notable increase in task completion rates. PostNord reported that the percentage of calls resolved without escalation to human staff rose from 45 percent to 60 percent. This improvement indicates a more efficient handling of customer inquiries by the AI system, freeing up human agents for more complex issues.
The previous AI system was fully decommissioned within approximately 90 days, highlighting a relatively swift transition to the new platform.
Phased Rollout and Continuous Optimization
The deployment of the ElevenAgents system followed a structured four-phase rollout strategy. This began with an isolated weekend test, followed by a hybrid phase that allowed for human handover when necessary. A weekday partial deployment preceded the full production launch, ensuring stability and performance at each stage.
To maintain and improve the system's effectiveness post-launch, PostNord utilizes an A/B testing infrastructure. This setup allows live traffic to be split between different model configurations, enabling continuous optimization and refinement of the AI's performance based on real-world interactions.
The Role of Multi-Agent AI in Customer Support
The adoption of a multi-agent system by PostNord demonstrates a growing trend in leveraging advanced conversational AI for customer service. By segmenting tasks among specialized subagents, these systems can handle a wider range of inquiries with greater accuracy and efficiency than monolithic AI solutions. This approach allows for more targeted responses and a better overall user experience, as callers are directed to the most appropriate AI for their specific need.
Conclusion
PostNord's successful integration of the ElevenLabs ElevenAgents platform marks a significant advancement in its customer support capabilities. The new multi-agent AI system, with its ability to understand natural Swedish, operate 24/7, and efficiently resolve a higher percentage of calls, sets a precedent for how postal services can use artificial intelligence to improve operational efficiency and customer satisfaction. The continuous optimization through A/B testing suggests an ongoing commitment to refining this technology for future enhancements.
Sources
Recommended AI tools
Google Gemini
Conversational AI
Your everyday Google AI assistant for creativity, research, and productivity
ChatGPT
Conversational AI
AI research, productivity, and conversation—smarter thinking, deeper insights.
Perplexity
Search & Discovery
Clear answers from reliable sources, powered by AI.
Claude
Conversational AI
Your trusted AI collaborator for coding, research, productivity, and enterprise challenges
OpenClaw AI Agent
Productivity & Collaboration
The AI that actually does things.
Cursor
Code Assistance
Your coding agent for building ambitious software
About the Author

Albert Schaper is a co-founder of Best-AI.org. He focuses on product strategy, AI adoption, practical tool selection, and educational content that helps users compare AI products with clearer context.
More from AlbertWas this article helpful?
Found outdated info or have suggestions? Send us a note.