跳到正文
OpenAI News·· 12 天前AI 評分51

新加坡航空以 OpenAI 技術改善客戶服務、旅遊探索及員工工作流程

Singapore Airlines elevates travel & work with OpenAI technology

AI 導讀

新加坡航空在客戶服務、旅遊探索及員工工作流程中採用 OpenAI API 和模型,Kris 聊天機械人的客戶滿意度提升至原來的 2 倍。客服平均處理時間減少約 10%,Flight Recommender 過去一年每月用戶增至近 3 倍;部分軟件開發生命週期活動的生產力提升最高達 20%。超過 60% 的員工每月使用由 OpenAI 模型支援的內部平台 Jarvis。

正文

Singapore Airlines elevates travel & work with OpenAI technology

With the OpenAI API and models, Singapore Airlines improves customer support, travel discovery, and employee work, doubling CSAT for the Kris customer service chatbot.

Contact sales

Image 1: Singapore Airlines logo in white on a dark blue curved satin texture.

Company size: Enterprise

Region: Asia-Pacific & Oceania

Industry: Travel

Products: API

2x

Increase in customer satisfaction score (CSAT) with AI-powered Kris chatbot

~10%

Reduction in average handling time for customer service representatives using AI-assisted tools.

~3x

Growth in Flight Recommender monthly users over the past year.

Loading…

Audio 1

Share

Moving from scripted service to conversational support

AI is becoming part of how Singapore Airlines serves customers, empowers employees, and builds technology. The airline uses the OpenAI API for customer-facing experiences and OpenAI models inside Jarvis, its governed internal AI platform for employees. It also uses OpenAI models in its software development workflows to deliver more personalized service, improve productivity, and help teams build more efficiently.

“AI is central to our efforts to deliver more personalized customer experiences and improve productivity across the business. Together with OpenAI, we’re building AI-powered capabilities that make travel more intuitive and seamless for our customers, while enabling our employees to work more efficiently and effectively.”

—George Wang, Senior Vice President Information Technology, Singapore Airlines

Across these deployments, Singapore Airlines pairs OpenAI models with orchestration, internal data controls, validation, and human review, giving teams a consistent way to bring AI into production workflows responsibly.

Moving from scripted service to conversational support

One of Singapore Airlines’ most visible AI applications is Kris, its customer-facing chatbot. After moving Kris from a traditional dialog-flow system to an LLM-powered conversational experience using the OpenAI API, Singapore Airlines saw a 2x increase in customer satisfaction.

Alongside that, the airline deployed AI-assisted tools for customer service representatives, including OpenAI API-powered call summarization, so that representatives spend less time on after-call work and more time on the customer. Singapore Airlines saw an approximately 10% reduction in average handling time for its customer service representatives.

In the earlier dialog-flow based chatbot design, every topic had to be mapped manually, and every flow had to be written in advance. That made coverage difficult to scale. If an intent was missing, the conversation was more likely to end up requiring support from a customer service representative, even when the customer’s request could have been handled through self-service.

Singapore Airlines moved Kris to a fully LLM-powered conversational experience using the OpenAI API. Instead of depending on predefined flows, the chatbot can interpret customer intent in natural language, ground answers in a knowledge base, manage multi-topic conversations, and hand over to a customer service representative with the relevant context when needed.

Today, customers use Kris for general queries, special requests, real-time flight disruption information, and selected transactional workflows. Singapore Airlines is continuing to expand its capabilities to include booking changes, baggage transactions, and more complex agentic interactions.

“Kris has become a more capable self-service channel with OpenAI. It understands customer intent more naturally, helps customers get to the right answer, and gives customer service representatives clearer context when they need to step in.”

—Jude Anand Suresh, Vice President, Customer Service Information Technology, Singapore Airlines

Helping customers discover travel through natural language

Flight Recommender lets customers describe the trip they want in natural language instead of repeatedly adjusting filters, dates, and destinations. Usage has grown nearly 3x over the past year.

“Flight Recommender makes travel discovery feel more like a natural conversation. Powered by OpenAI models through the API, it helps customers describe what they want and find relevant options faster.”

—Andy Koh, Vice President, Application Services (Sales, Marketing & Cargo), Singapore Airlines

Built on the OpenAI API, Flight Recommender uses an orchestration layer connected to fare and availability data. It interprets customer intent, calls the relevant tools, and returns personalized travel recommendations in natural language.

The team has also implemented guardrails for input and output validation, malicious or inappropriate query handling, hallucination reduction, PII handling, and authenticated access to only the context required for each query. Singapore Airlines is preparing to expand the experience into a more conversational chatbot interaction, where customers can keep refining travel ideas rather than restarting a search.

Bringing AI into the software development lifecycle

Beyond customer-facing experiences, Singapore Airlines is also using OpenAI models in parts of the software development lifecycle to help teams plan, refine, test, and review work more efficiently. Across selected software development lifecycle activities, teams have achieved productivity gains of up to 20%.

AI now runs through the entire delivery lifecycle and not just coding. Teams use generative AI models to support requirements refinement, stakeholder-session analysis, product specifications, edge-case identification, test-case creation, architecture review, and the breakdown of complex work into smaller, more testable tasks.

For one commercial feature, the team used the OpenAI API to challenge assumptions, identify ambiguous requirements and surface edge cases before development begins. Once those were well-defined, AI helped translate them into design options, implementation plans, test cases and then code generation.

During deployment and beyond, AI also helps to interpret how the system is behaving in production, and flagging issues that might otherwise go unnoticed. With AI active at every step of the workflow, team members have shifted from producing every artifact themselves, to directing, reviewing and validating what AI produces throughout the delivery lifecycle. This means they can focus on work that truly requires human judgement, such as prioritization, architecture, governance and stakeholder outcomes.

More broadly, OpenAI models are helping Singapore Airlines improve requirements quality, test coverage, and conformance with internal standards. Teams use these workflows to generate edge cases for testing, review architecture plans, and support human validation before work moves further through the development lifecycle.

Making AI easier for employees to use

Beyond engineering teams, Singapore Airlines is making AI accessible across the business through Jarvis, its internal AI platform. Powered by OpenAI models, Jarvis gives employees a governed way to use AI in their day-to-day work, from summarizing documents to creating custom workflows.

Employees use Jarvis to work across PDFs, Word documents, Excel files, PowerPoint decks, and other file types in a secure environment, while creating custom workflows and lightweight knowledge bases for their day-to-day work. Today, more than 60% of Singapore Airlines employees are using Jarvis monthly with adoption continuing to increase.

Results at a glance

  • 2x increase in customer satisfaction score (CSAT) after changing to AI-based Kris chatbot

  • ~10% reduction in average handling time for customer service agents using AI-assisted tools

  • 3x growth in monthly users of Flight Recommender, its customer-facing travel discovery tool, over the past year

What’s next

Singapore Airlines is continuing to expand AI across customer and employee workflows. For Kris, the next phase is deeper self-service, with more transactional capabilities that help customers resolve requests directly in chat. Flight Recommender is moving toward a more conversational travel discovery experience, where customers can refine ideas over multiple turns rather than restarting a search.

With Jarvis available across the business, Singapore Airlines is focused on helping more employees put AI to work in their day-to-day roles. Together with its customer-facing innovations, this is helping the airline build a future where AI makes travel more seamless, employees more productive, and the business more responsive to changing needs.

Join the new era of work

More than 1 million businesses around the world are achieving meaningful results with OpenAI.

Contact sales

Keep reading

Image 2: Localiza customer story — approved larger-logo art card

Localiza reorganizes work around generative AI Oct 16, 2026

Image 3: loveholidays customer story art card v4

How loveholidays is making everyone a builder with Codex Aug 26, 2026

Image 4: Virgin Atlantic ChatGPT Work card image

Virgin Atlantic sharpens customer journeys with ChatGPT Work Aug 10, 2026

Research

Latest Advancements

Safety

Products

API Platform

Business

Developers

Company

Support

More

Terms & Policies

(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)

OpenAI © 2015–2026 Your privacy choices

English United States

來源:OpenAI News · openai.com