Last updated: September 23, 2026
AI at Allianz:
Enterprise Knowledge Assistant enhances call center productivity
Knowledge may or may not be power, but either way, it is useless unless it can be accessed. Allianz has developed Enterprise Knowledge Assistant (EKA). This cutting-edge AI solution streamlines data retrieval to enable call center agents and operational experts to quickly and accurately access essential information.
Customer care agents across Allianz entities in Germany rely on the AWISO knowledge library for guidance. Traditionally, navigating this extensive repository of thousands of documents has been time-consuming, particularly for new team members. EKA changes this dynamic by providing a user-friendly chatbot interface that enables agents to query customer issues and receive precise answers instantly.
“The typical user is an Allianz employee managing vast amounts of business-related documents –whether they be customer service agents, back-office staff, or underwriters,” explains Dong Chen, Head of Advanced Methods in Allianz Group Data and AI. “EKA enables them to extract information and answer questions efficiently, significantly reducing the time they spend searching through extensive documentation.”
EKA is powered by Large Language Model applications, and leverages Retrieval Augmented Generation (RAG), model finetuning and multi-agent design to maximize answer accuracy for each given business application. It finds the relevant documents, highlights relevant information and provides summaries and links directly to the complete content. EKA understands the context and recognizes similar terms, ensuring agents can respond faster, improving first-contact resolution rates and enhancing customer satisfaction.
Always learning
EKA is designed to improve continuously. Agents can offer feedback within the system, helping refine its capabilities over time. This iterative approach ensures the assistant remains accurate, reliable, and aligned with the evolving needs of call centers. With an accuracy rate exceeding 90% for common queries, EKA has become an indispensable tool for many teams.
The system was first developed as a pilot starting in July 2023 and went live a year later with Allianz Leben in Germany, followed by Allianz Versicherung and Allianz HR Service in India. Chen explains that the solution was designed for a rapid uptake during the scaling phase. Currently, EKA is tested in more than ten use-cases in Allianz operational entities like Italy, India, Mexico, Portugal, the Benelux and the UK are all scheduled for this year., including Allianz Commercial entities.
“EKA is not an experiment – it is a proven solution with significant business impact,” Chen says. “The AI processes vast datasets – up to 90,000 paragraphs of text – transforming them into manageable chunks that are easily accessible for agents. This ensures that users can find insights in seconds rather than wading through lengthy documents.”
The versatility of EKA is that it allows integration with diverse document databases and customization for specific operational areas, such as health, and property and casualty (P&C) operations. Additionally, localized implementations ensure seamless adoption in regions with unique infrastructure requirements, as demonstrated by Allianz US Life’s adaptation of the EKA framework.
Tangible benefits for agents and customers
EKA’s impact extends beyond productivity improvements. By significantly reducing the time spent searching for information, EKA enables agents to resolve customer queries faster and more efficiently, improving the first contact resolution rate. Its advanced semantic search capabilities minimize errors, ensuring customers receive accurate and relevant responses consistently. Additionally, the streamlined workflows and immediate access to information foster a smoother interaction, improving the overall quality of customer engagements and enhancing their experience.
Developed by the Advanced Methods team within the Allianz Group Data and AI unit, EKA leverages a blend of commercial and open-source AI technologies within Allianz’s Future Cloud platform. This robust infrastructure supports scalability, reliability, and adaptability, ensuring EKA’s alignment with Allianz’s digital transformation goals.
Driving future customer care
As Allianz continues to scale EKA across its global operations, the solution represents a leap forward in customer service innovation. EKA enhances productivity by enabling agents to work smarter and faster and reinforces Allianz's commitment to delivering exceptional customer experiences.
Further information
About Allianz
The Allianz Group is one of the world’s leading insurers and asset managers, active in almost 70 countries and serving around 97 million private and corporate customers*. Our customers benefit from a broad range of personal and corporate insurance services, including property, life and health insurance, as well as assistance services, credit and global business insurance. Recognized for the seventh consecutive year as the number one global insurance brand in Interbrand’s Best Global Brands 2025 ranking, Allianz’s success is built on technology-enabled customer centricity – providing peace of mind, protection, and prevention for our customers and strengthening the resilience of individuals, communities, and societies. We are one of the world’s largest investors, managing around 791 billion euros** on behalf of our insurance customers. Furthermore, our asset managers PIMCO and Allianz Global Investors manage about 2.2 trillion euros** of third-party assets. Thanks to our systematic integration of environmental and social criteria in our business processes and investment decisions, Allianz received an MSCI ESG Rating of AAA (as of March 2026). In 2025, our 156,000 dedicated employees achieved a total business volume of 186.9 billion euros and an operating profit of 17.4 billion euros for our shareholders.
* As of December 31, 2025. Customer count reflects Allianz customers in consolidated entities that are part of the customer reporting scope only.
** As of June 30, 2026.
Cautionary note regarding forward-looking statements
As with all content published on this site, these statements are subject to our cautionary note regarding forward-looking statements:
