Use Case Intelligence RSS Search use cases Search
OpenAI Travel and Hospitality Asia-Pacific & Oceania

Singapore Airlines

Customer Service Automation · Document Processing · Marketing Personalization

Singapore Airlines wanted to improve customer support and travel discovery while giving employees governed AI tools for everyday work and software delivery.

Read the original story Explore all use cases
2x increase in Kris customer satisfaction score
More than 60% of employees use Jarvis monthly
Up to 20% productivity gains across selected software development lifecycle activities
~10% reduction in average handling time for customer service representatives

Reported impact

Business outcome

Singapore Airlines doubled customer satisfaction for Kris, reduced average handling time for representatives by about 10%, and grew Flight Recommender monthly users nearly threefold. Jarvis is used monthly by more than 60% of employees.

  • Customer Experience
  • Productivity Improvement

Solution

Singapore Airlines uses the OpenAI API for customer-facing services and OpenAI models within Jarvis, its governed internal AI platform. The airline replaced Kris's scripted dialog flows with an LLM-powered chatbot that interprets natural-language intent, grounds answers in a knowledge base, handles multiple topics, and hands context to a human representative when needed. Flight Recommender combines an orchestration layer with fare and availability data to return natural-language travel suggestions. Customer-service representatives use API-powered call summaries, and engineering teams apply models across requirements, architecture review, testing, and production monitoring. Jarvis lets employees work with documents and create workflows in a controlled environment. Input/output validation, PII handling, authenticated access, and human review support responsible use across these deployments.

Data flow

Kris uses the OpenAI API and a knowledge base to answer customer questions; Flight Recommender combines customer intent with fare and availability data; Jarvis applies OpenAI models to employee documents and workflows, with validation and access controls around model inputs and outputs.

Solution architecture

4 components · 2 layers
  1. Compute
    • OpenAI API Provides models for the customer chatbot, call summaries, travel recommendations, and selected software-development activities.
  2. Serving
    • Kris Answers customer queries conversationally, grounds responses in a knowledge base, and passes context to service representatives.
    • Flight Recommender Uses natural-language requests and fare and availability data to recommend travel options.
    • Jarvis Provides employees with a governed AI workspace for documents and custom workflows.

Architecture clues

  • Flight Recommender uses an orchestration layer connected to fare and availability data
  • Guardrails cover validation, malicious queries, hallucinations, PII, and authenticated access
  • Kris shifted from predefined dialog flows to LLM-powered conversation

Evidence from the source

"Built on the OpenAI API, Flight Recommender uses an orchestration layer connected to fare and availability data."
"Singapore Airlines moved Kris to a fully LLM-powered conversational experience using the OpenAI API."
Transparency Evidence & methodology 100/100 reference value · 85% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value100/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    5 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence85%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability25/25
    12 of 12 key fields link to a named source.
  • Direct evidence10/20
    2 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency10/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. OpenAI

    Singapore Airlines elevates travel & work with OpenAI technology

    First-party
    https://openai.com/index/singapore-airlines-travel-work/
    Source type
    Vendor-published customer story
    Published
    Nov 10, 2026
    Supports
    • Customer
    • Region
    • Company size
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • Business outcome
    • Metrics
    • Architecture
    • Publication date

Date evidence

  • Published on source page Nov 10, 2026 · OpenAI · First-party
    Open date source
Not separately sourced Industry. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
OpenAI Mar 6, 2025 Booking.com Travel and Hospitality Global Booking.com needed a better way to understand traveler intent during early trip discovery, because rule-based search and hundreds of fixed filters worked only when customers already knew what they wanted and did not… Booking.com data covers the last 20 years Customer Service AutomationMarketing Personalization AI Trip Planner · GPT models · GPT-4o mini Huawei Cloud Changsha Bank (长沙银行) Financial Services China Rapid growth in digital banking, mobile payments, online wealth services and inclusive finance increased transaction and compute demand. Changsha Bank also needed to operate heterogeneous AI compute efficiently, manage… Average monthly calls exceeded 100,000 Customer Service AutomationDocument Processing Ascend AI computing base · Ascend inference acceleration · Huawei Cloud Stack OpenAI Oct 16, 2026 Itaú Financial Services Latin America Itaú needed to make financial guidance simpler and more personalized for millions of customers while also scaling document-heavy internal workflows, all under the governance, observability, and economic controls… 100% of the customer base is the goal by the end of 2026 Customer Service AutomationDocument Processing Customer DNA · IARA · OpenAI models