## Overview Allianz, the world's #1 insurance brand with over 150,000 employees worldwide, faced a significant challenge in their Benelux operations (Netherlands, Belgium, and Luxembourg). Their complex product portfolio—spanning property, accident, life, health, and other insurance types—made it extremely difficult for customers to find the correct claim forms or support numbers when they needed assistance. This case study documents how Allianz Benelux implemented a conversational chatbot solution to simplify their claims navigation process. It is important to note that while this case study is presented on Landbot's website (a chatbot platform vendor), the solution described appears to be primarily a rule-based conversational chatbot rather than a sophisticated LLM-powered AI system. The text mentions "AI Agent Chatbots" in Landbot's product marketing materials, but the actual Allianz implementation focuses on keyword matching and decision-tree navigation rather than generative AI capabilities. This distinction is important for understanding the technical nature of the deployment. ## The Business Problem The insurance industry's complexity presented several challenges for Allianz Benelux: - Product proliferation over years of acquisitions led to numerous variations of the same insurance product - Each product variation had its own claim form and/or support number - The team collected over 92,000 unique search terms that customers used on their website, demonstrating the diversity of ways customers sought help - Customers often struggled to identify the correct form or contact method during stressful claims situations - Traditional web forms provided poor user experience and required significant customer effort Stefan van Ballegooie, Conversion Specialist at Allianz Benelux, described the core problem: customers found it "barely possible" to call the right support number or choose the correct form to file their claim. This friction during the claims process—often occurring during moments of customer distress—represented a significant customer experience issue for the insurance giant. ## Solution Architecture and Implementation ### Team Collaboration and Development Timeline The solution was developed through collaboration between two internal teams: the Business Transformation Unit (BTU) and the Customer Care Center (CCC). Rather than engaging external consultants or lengthy enterprise software implementations, these teams worked outside their regular 2020 projects to develop, test, and implement the chatbot within just three weeks. ### Technical Approach: Keyword Categorization and Mapping The core technical approach involved leveraging existing data assets—specifically, the 92,000+ unique search terms collected over years from their website's search engine. This data-driven approach included: - Analyzing and categorizing all keywords related to insurance products - Linking categorized keywords to specific insurance products - Mapping products to appropriate web destinations (forms, support numbers, etc.) - Building decision-tree logic to guide customers to correct outcomes This approach represents a more traditional natural language understanding (NLU) methodology based on keyword matching and intent classification rather than generative AI. While Landbot now offers AI-powered chatbot features, the Allianz implementation appears to rely primarily on structured conversation flows with keyword-based routing. ### Platform and Integration Stack The solution was built using Landbot's no-code chatbot builder, which enabled: - Drag-and-drop bot construction without requiring software development expertise - Built-in data analysis capabilities for monitoring chatbot performance - Drop-off analysis to identify where customers were abandoning conversations - Native integrations with enterprise tools The integration architecture connected the chatbot to operational systems through: - **Slack Integration**: Real-time feedback from customers was relayed directly to the team's Slack channel, enabling immediate visibility into customer satisfaction and issues - **Trello Integration**: Feedback automatically triggered ticket creation in Trello, where improvement items were tracked and managed - **24-hour Improvement Cycle**: The team committed to converting negative feedback into implemented improvements within 24 hours of notification ### Localization and Multi-Region Scaling A notable aspect of the implementation was the rapid scaling across the Benelux region. Stefan van Ballegooie worked with a colleague from the Belgium department to synchronously develop localized versions of the bot. This was accomplished through an intensive 48-hour hackathon that produced: - Dutch language version for Netherlands customers - German language version for Belgian customers - Testing with various departments from the Belgium office The no-code nature of Landbot's platform enabled this rapid localization without requiring translation of code or extensive technical modifications. ## Operational Monitoring and Continuous Improvement ### Real-Time Analytics and Feedback Loops One of the more interesting operational aspects of this deployment was the emphasis on continuous improvement through automated feedback mechanisms. The chatbot collected customer satisfaction ratings directly, and negative feedback triggered an automated workflow: - Customer provides rating through chatbot - Negative feedback is immediately pushed to team Slack channel - Trello ticket is automatically created for the issue - Team targets resolution within 24 hours This represents a practical example of operationalizing customer feedback for conversational systems, even if the underlying technology is rule-based rather than AI-powered. ### Drop-off Analysis Landbot's built-in analytics enabled the team to identify conversation drop-off points—places where customers abandoned the chatbot before reaching their destination. This data informed iterative improvements to conversation flows, keyword matching, and navigation paths. ## Results and Outcomes The case study reports several key metrics: - **18,000+ customers** used the chatbot - **90% positive feedback rating** (exceeding their >85% target) - **100 feedback points** converted into improvements within 24 hours - **3-week development timeline** from inception to deployment - **Dutch version achieved 93% positive rating** after going live in 2020 An unexpected benefit was product discovery: the chatbot revealed that customers were searching for insurance products that the team didn't realize existed in their portfolio, providing valuable business intelligence. ## Critical Assessment While this case study demonstrates a successful digital transformation initiative, several caveats are worth noting: The solution described is fundamentally a rule-based decision-tree chatbot with keyword matching rather than an LLM-powered conversational AI system. While Landbot's marketing materials reference "AI Agent Chatbots" and "Generative AI," the actual Allianz implementation appears to predate widespread LLM adoption (the Dutch version launched in 2020) and relies on traditional chatbot architecture. The metrics provided come from a vendor case study and should be interpreted with appropriate context. The 90% positive rating is impressive but the definition of "positive" and the methodology for collecting ratings are not specified. Additionally, the 18,000 customer usage figure lacks context about what percentage of total claims interactions this represents. The 24-hour improvement turnaround is an aspirational operational goal, and the case study notes that "100 points of feedback" were converted into improvements within 24 hours, suggesting this was an initial achievement rather than ongoing operational SLA. ## Relevance to LLMOps This case study represents an earlier generation of conversational AI deployment—primarily rule-based chatbots with NLU for intent classification—rather than LLM-powered solutions. However, several operational patterns remain relevant for LLMOps practitioners: - **Rapid prototyping and deployment** using no-code platforms can accelerate time-to-value - **Integration with operational tools** (Slack, Trello) creates visibility and accountability - **Continuous improvement loops** based on user feedback are essential for conversational systems - **Localization and scaling** require deliberate planning and cross-functional collaboration - **Analytics and drop-off analysis** inform iterative improvements to conversation design For organizations considering LLM-powered chatbots today, this case study provides a baseline for comparison: how do modern AI-powered solutions compare in development time, accuracy, customer satisfaction, and operational overhead versus traditional rule-based approaches? The Allianz Benelux experience suggests that even without sophisticated AI, well-designed conversational interfaces built on solid domain knowledge (the 92,000 search terms) can significantly improve customer experience. The question for LLMOps practitioners is whether LLM-based approaches can further improve these outcomes while managing the additional complexity of prompt engineering, hallucination risks, and model monitoring.