Singapore Airlines Reports Doubled Customer Satisfaction for Kris Chatbot After Switching to OpenAI-Powered LLM Experience

Singapore Airlines published a case study via OpenAI on November 10, 2026, disclosing that it doubled the customer satisfaction score (CSAT) for its Kris chatbot after migrating from a traditional scripted dialog-flow system to a large language model (LLM)-powered conversational experience using the OpenAI API. Additionally, the airline reported an approximately 10% reduction in average handling time for customer service representatives who use AI-assisted tools, such as call summarization powered by the OpenAI API.

In terms of travel discovery, Singapore Airlines' Flight Recommender feature allows customers to describe their trip needs in natural language rather than adjusting filters repeatedly. Monthly active users for this feature have grown nearly 3x over the past year. Built on the OpenAI API, the recommender uses an orchestration layer connected to fare and availability data to interpret intent and return personalized recommendations.

Beyond customer-facing applications, Singapore Airlines is using OpenAI models within Jarvis, its governed internal AI platform for employees. Jarvis enables staff to process documents like PDFs and Excel files and create custom workflows. More than 60% of Singapore Airlines employees now use Jarvis monthly. The airline also employs OpenAI models in parts of its software development lifecycle for tasks like requirements refinement and test-case generation, claiming productivity gains of up to 20% in selected activities.

All cited performance metrics are self-reported by Singapore Airlines and have not been independently verified. George Wang, Senior Vice President of Information Technology at Singapore Airlines, stated that AI is central to their efforts to deliver personalized customer experiences and improve productivity across the business.