Customer Service Automation · Enterprise Knowledge Search
Customer care agents and operational experts across Allianz entities in Germany had to navigate the AWISO knowledge library, an extensive repository of thousands of documents, making information retrieval slow and difficult, especially for new team members handling customer issues.
Reported impact
EKA reduces the time employees spend searching through documentation, improves answer accuracy, helps agents resolve customer queries faster, supports higher first-contact resolution, and improves customer and employee experience while scaling across Allianz operations.
Allianz built the Enterprise Knowledge Assistant (EKA) as an internal AI knowledge assistant for call center and operations teams. The system sits on Allianz’s Future Cloud platform and uses large language model applications with Retrieval Augmented Generation (RAG), model finetuning, and a multi-agent design to turn large internal document collections into an interactive chatbot experience. EKA searches the AWISO knowledge library and other document databases, identifies relevant passages, highlights the right information, generates summaries, and links users back to the original source content. The platform processes large text corpora by chunking up to 90,000 paragraphs into retrievable units, then serves precise answers through a conversational interface for agents, back-office staff, and underwriters. Built-in user feedback helps continuously refine response quality, while localized implementations allow the same framework to be adapted for different Allianz entities and infrastructure environments.
Guidance documents from the AWISO knowledge library and other document databases are processed into manageable chunks on Allianz’s Future Cloud platform. EKA uses RAG, finetuning, and multi-agent logic to retrieve relevant passages, generate contextual answers and summaries, and return links to full source content through a chatbot used by call center agents and other staff.
“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.”
“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.”
“EKA changes this dynamic by providing a user-friendly chatbot interface that enables agents to query customer issues and receive precise answers instantly.”
“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.”
“The AI processes vast datasets – up to 90,000 paragraphs of text – transforming them into manageable chunks that are easily accessible for agents.”
“With an accuracy rate exceeding 90% for common queries, EKA has become an indispensable tool for many teams.”
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
In-house Sample Apr 8, 2025 Bank of America Bank of America needed to improve employee productivity and client service at scale across a global workforce of 213,000 people, while reducing routine support demand, accelerating employee access to information,… 20 million clients now actively using the virtual assistant Erica · Erica for Employees · PRIVATE BANK In-house Sample Feb 14, 2025 BBVA BBVA wanted to make digital banking interactions more natural and personalized for customers, while also giving branch employees faster access to current product and service information so they could handle requests… answering over 3,000 questions AI-based assistant · Blue · large language models (LLM) In-house Sample May 8, 2024 Mapfre Mapfre wanted to improve customer experience and streamline insurance operations such as claims handling, risk assessment, underwriting support, document management, internal knowledge access, and digital content… 75 use cases under study for the application of generative AI ControlExpert · Cyberwrite · Holistic AI 