Singapore Airlines Elevates Travel and Workplace Experiences with OpenAI
November 10, 2026
Using the OpenAI API and models, Singapore Airlines has improved customer support, trip discovery, and employee workplace experiences, doubling the customer satisfaction score (CSAT) for its customer service chatbot, Kris.

-
Company Size: Enterprise
-
Region: Asia-Pacific & Oceania
-
Industry: Travel
-
Products: API
-
2x: Increase in customer satisfaction score (CSAT) for the AI-powered Kris chatbot
-
~10%: Reduction in average handle time (AHT) for customer service agents using AI-assisted tools
-
~3x: Growth in monthly users for the Flight Recommender over the past year
AI is becoming an integral part of how Singapore Airlines serves customers, empowers employees, and builds technology. The airline uses the OpenAI API for customer-facing experiences and integrates OpenAI models into Jarvis, its governed internal AI platform for employees. It has also introduced OpenAI models into its software development workflows to deliver more personalized services, boost productivity, and help teams build more efficiently.
“AI is central to how we deliver more personalized customer experiences and drive productivity across our business. Through our collaboration with OpenAI, we are building AI-powered capabilities that make travel more intuitive and seamless for our customers, while empowering our people to work more efficiently and effectively.”
—George Wang, Senior Vice President Information Technology, Singapore Airlines
Across these deployments, Singapore Airlines combines OpenAI models with orchestration, internal data controls, validation, and human review, giving teams a consistent way to responsibly bring AI into production workflows.
Moving from Scripted Service to Conversational Support
One of Singapore Airlines’ most visible AI applications is Kris, its customer-facing chatbot. After migrating Kris from a traditional dialog-flow system to a conversational experience powered by large language models (LLMs) using the OpenAI API, Singapore Airlines saw a 2x increase in customer satisfaction.
At the same time, the airline rolled out AI-assisted tools for customer service agents—including call summarization powered by the OpenAI API—allowing agents to spend less time on after-call work and focus more on customers. As a result, Singapore Airlines reduced its agents’ average handle time by approximately 10%.
In earlier dialog-flow chatbot designs, every topic had to be manually mapped and every flow pre-scripted. This made it difficult to scale coverage. If an intent was missing, the conversation would likely end up being handed off to a live agent for support, even when the customer’s request could have been resolved through self-service.
Singapore Airlines used the OpenAI API to upgrade Kris into a fully LLM-powered conversational experience. Instead of relying on predefined flows, the chatbot can now understand customer intent in natural language, ground answers in a knowledge base, manage multi-topic conversations, and seamlessly hand off to live agents with relevant context when needed.
Today, customers use Kris for general inquiries, special assistance requests, real-time flight delay information, and selected transactional workflows. Singapore Airlines continues to expand its capabilities to cover rebooking, baggage transactions, and more complex agentic interactions.
“With OpenAI, Kris has become a much more capable self-service channel. It understands customer intent more naturally, helps customers find the right answers, and provides clearer context when a human agent needs to step in.”
—Jude Anand Suresh, Vice President Customer Services IT, Singapore Airlines
Helping Customers Explore Travel in Natural Language
The Flight Recommender lets customers describe the trip they want in natural language rather than repeatedly adjusting filters, dates, and destinations. Over the past year, usage of the feature has grown nearly 3x.
“The Flight Recommender makes trip discovery feel more like a natural conversation. Powered by OpenAI models via the API, it helps customers describe what they are looking for and find relevant options faster.”
—Andy Koh, Vice President Application Services (Sales, Marketing & Cargo), Singapore Airlines
Built on the OpenAI API, the Flight Recommender uses an orchestration layer connected to fare and seat availability data. It understands customer intent, invokes the relevant tools, and returns personalized travel recommendations in natural language.
The team also implemented guardrails for input and output validation, handling malicious or inappropriate queries, reducing hallucinations, managing personally identifiable information (PII), and ensuring authenticated access to only the context required for each query. Singapore Airlines is preparing to expand the experience into a more conversational chatbot interaction, allowing customers to refine their travel ideas without having to start their search over.
Bringing AI into the Software Development Lifecycle
Beyond customer-facing experiences, Singapore Airlines uses OpenAI models across parts of its software development lifecycle (SDLC) to help teams plan, refine, test, and review work more efficiently. In selected SDLC activities, teams have achieved productivity gains of up to 20%.
Today, AI spans the entire delivery lifecycle rather than just code generation. Teams use generative AI models to support requirements…