Klarna Transforms Employee Productivity with GenAI Knowledge Platform Built on Neo4j

Companies today face increasing software sprawl. In 2024, the average SaaS (Software as a Service) spend per employee in the United States was $5,607 — a 7% increase from 2023. It is also estimated that 30-50% of software licenses go unused or underutilized.

Klarna faced this challenge head-on during its rapid expansion. The Swedish company — known for revolutionizing how consumers shop and pay online — watched its data become isolated in enterprise software islands.

Source

These silos created friction for Klarna’s workforce. Employees spent time searching for answers across disconnected platforms. rather than applying those insights to serve customers. A straightforward question about organizational structure often turned into a digital scavenger hunt.

“We started obsessing about the concept of collaboration on information,” explained Sebastian Siemiatkowski, Co-Founder and CEO of Klarna on the Training Data Podcast. “We’ve looked a lot to Wikipedia and other knowledge graphs, and how people collaborate on building great information.”

Knowledge Graphs: From SaaS Chaos to Connected Intelligence

Klarna’s existing information architecture consisted of dozens of enterprise systems, from Salesforce and Workday to various project management tools. Analyzing team structures, understanding processes, or answering cross-functional questions required accessing multiple systems and manually joining information.

Traditional databases struggle with this challenge. Relational databases require complex joins between tables, leading to poor performance as data complexity grows. Document databases better handle unstructured content but lack native relationship modeling. Neither could enable the dynamic, connected view of organizational knowledge Klarna needed.

Source

Unlike relational databases, Neo4j doesn’t require joins—it natively represents connections between data points. This approach aligned with Klarna’s vision of building an interconnected knowledge platform where teams, processes, and information could be linked and traversed.

Klarna began by constructing a knowledge graph of its data sources. 

“We started consolidating; put things together, connect our knowledge, remove the silos,” says Siemiatkowski. “The side consequence of this: liquidation of SaaS—not, but a lot of them. Not for the license fees, though those savings are nice, but for unification and standardisation of knowledge=data.”

Klarna then integrated OpenAI’s large language models (LLMs) to make the knowledge graph accessible to all employees. This integration allowed employees to query the knowledge graph using natural language through a chatbot interface available in Slack and on Klarna’s internal knowledge platform.

“As Klarna continues to discover applications for OpenAI’s tech, there’s the potential to take the business to new heights,” says Siemiatkowski. “We’re aimed at achieving a new level of employee empowerment, enhancing both our team’s performance and the customer experience.”

When an employee needs to understand how teams are structured or find a specific process document, Kiki doesn’t just return isolated data points. It shows how information connects to everything around it—linking people to projects, documents to teams, and processes to outcomes. This approach means employees can see not just what they asked for, but also the surrounding context that makes the information useful.

Kiki Answers 2,000 Questions Per Day

Kiki has transformed how knowledge flows at Klarna. What began as an experiment has evolved into a productivity tool used by 85% of employees. The knowledge graph answers over 2,000 questions per day, with more than 250,000 employee queries processed since its launch in June 2023.

The impact extends far beyond simple information retrieval:

• Adoption: 85% of Klarna employees actively use Kiki, with non-technical teams seeing adoption rates as high as 93% in Communications, 88% in Marketing, and 86% in Legal.
• Simplification: Klarna has deprecated over 1,200 SaaS systems and reduced dependence on enterprise platforms like Salesforce (CRM) and Workday.
• Productivity: Employee questions are answered within 1-5 seconds, eliminating time previously spent searching multiple systems.

For Klarna, the knowledge graph represents more than just a technical solution—it’s a new way of thinking about organizational knowledge as an interconnected whole rather than isolated fragments. By connecting people to information through Neo4j’s graph technology, Klarna has created a foundation for more efficient, collaborative, and innovative work.

“Kiki brings together information across multiple disparate and siloed systems, improves the quality of that information, and explores it, enabling our teams to ask Kiki anything from resource needs to internal processes to how teams should work,” says Siemiatkowski. “It’s having a huge impact on productivity in ways that were not possible to imagine before without graph and Neo4j.”

Get in Touch

Curious about what insights you could unlock for your business with graph-powered solutions? Let’s talk — reach out, and we’ll get in touch.