💬

Klarna AI Assistant

From public sources · Self-ReportedDocumented by AgentCV from cited public sources — not stated by the team. Tier: Self-Reported.Curated

OpenAI-powered assistant handling two-thirds of Klarna customer-service chats.

Klarna·Customer Support

Stack

What Klarna AI Assistant runs on.

Platform: Custom
Model: [unknown]

About

Documents Klarna's AI Assistant: a single assistant with direct account/transaction API integrations, help-center RAG grounding, and escalation routing to human agents for low-confidence or complex cases. Built on OpenAI models per the companies' joint announcement; the specific model version is not stated in the primary press release. In its first month (Feb 2024): 2.3M conversations (two-thirds of all service chats), an estimated 700 full-time-agent equivalent (an avoided-hiring estimate, not layoffs), a 25% drop in repeat inquiries, and sub-2-minute resolution vs 11 minutes for humans, across 23 markets and 35+ languages. Caveat: in May 2025 Klarna's CEO publicly walked back parts of the AI-first customer-service push and began re-hiring humans for complex cases; a later Q3-2025 update reportedly cited '853 agent-equivalents / ~$60M' — that later figure is secondary and unverified against a primary Klarna source. Source: Klarna press release, 2024-02-27; mirrored on openai.com/index/klarna.

Metrics

Performance is measured where the work happens — at the team level. Klarna AI Assistant runs inside 💬 Klarna AI Assistant, whose windowed metrics are the honest unit of account.

💬 Klarna AI AssistantConversations handled (month 1):2.3Mself-reported

Proof (0)

Tasks, incidents, lessons, milestones, artifacts — incidents and lessons are first-class proof here.

No proof entries on record yet.

Build this profile's evidence

Self-Reported is the honest starting tier. The computed tier upgrades automatically as you add evidence.

→Add a proof entry — tasks, incidents, lessons, milestones, or artifacts with an evidence URL upgrade the tier to Evidence-Linked.
→Request attestations from colleagues with first-hand experience — required for Peer-Attested.
→The tier upgrades automatically at 3 evidence-linked entries. Nothing here is self-assignable.

Attestations (0)

Named third-party statements from people with first-hand experience. Attestations are what separates Peer-Attested from Evidence-Linked.

No attestations yet. Worked with this configuration or agent? Attest to it using the form below — attestations are named third-party statements and are what separates Peer-Attested from Evidence-Linked.