Customer support · Production

Klarna reduces Time to Resolution by 10X with ElevenAgents

The problem

Klarna's growing call volume was dominated by informational requests that required customers to queue for a human agent, increasing wait times and operational load despite being straightforward to resolve.

Workflow diagram · grounded in source
1
Customer calls phone support
Trigger
Customers call Klarna's phone support line expecting fast, intuitive support.
▾ source quote
“Klarna serves millions of customers who expect fast, intuitive support when they pick up the phone”
2
Voice AI engages as first touchpoint
Ai action
The ElevenAgents voice AI acts as the first touchpoint for US phone support, engaging customers through low-latency, natural dialogue.
▾ source quote
“The agent now acts as the first touchpoint for US phone support, engaging customers through low-latency, natural dialogue”
3
Agent handles requests and gathers context
Ai action
The agent supports informational requests and gathers relevant context from the customer.
▾ source quote
“It supports informational requests, gathers relevant context, and hands over to human agents when required”
4
Escalation routing on complexity
Routing
When complexity or sensitivity is detected, the agent ensures seamless escalation to human agents.
▾ source quote
“Ensure seamless escalation to human agents when complexity or sensitivity is detected”
Reported outcome

Klarna's voice AI agent resolves customer queries up to 10x faster, reduces phone queues for simple requests, and frees human agents to focus on complex cases, with the solution live for all 35 million US customers.

Reported metrics
Time to Resolutionup to 10x faster
Phone queue reduction for simple requestsReduce phone queues for simple, high-volume requests
Human agent capacity freedFree up human agents to focus on more complex cases
US customers with access to agent35 million
Reported stack
ElevenAgentsElevenLabs
◆ Does this fit your context?

Compare to your context

Tell us your scale, team, and constraints. We'll show what changes at your size, what fails at your scale, and whether this case is a fit, needs adaptation, or won't scale to you. Free demo, no signup.

Compare to your context →
~30 seconds · free
Source
https://elevenlabs.io/blog/klarna
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Klarna's voice AI agent resolves customer queries up to 10x faster, reduces phone queues for simple requests, and frees human agents to focus on complex cases, with the solution live for all 35 million US customers.

What tools did this team use?

ElevenAgents, ElevenLabs.

What results were reported?

Time to Resolution: up to 10x faster; Phone queue reduction for simple requests: Reduce phone queues for simple, high-volume requests; Human agent capacity freed: Free up human agents to focus on more complex cases; US customers with access to agent: 35 million (source-reported, not independently verified).

How is this customer support AI workflow structured?

Customer calls phone support → Voice AI engages as first touchpoint → Agent handles requests and gathers context → Escalation routing on complexity.

Related customer support cases

WHAT TO DO WITH THIS

Now compare it to your context

This case is one data point. Whether its pattern fits you depends on your volumes, your stack, and your exception load — that comparison is the step no case study can do for you.

Browse the Customer support cases →