Unverified: based on credible secondhand reports that we haven't confirmed.
Ryanair runs one consolidated customer-service chat agent on Amazon Bedrock AgentCore and Amazon Nova 2 Lite that handles about 120,000 chats a day across seven languages at a reported 80% containment
Ryanair, Europe's largest airline, replaced a static legacy chatbot with an AI customer-service agent built on Amazon Bedrock AgentCore and Amazon Nova 2 Lite with AWS Partner Cation Consulting. It covers baggage, refunds, bookings and flight disruptions. AWS's case study reports 120,000 chats a day in seven languages at an 80% containment rate, and 10 million answers at 94% accuracy since the October 2024 launch (reported by AWS, the vendor; PYMNTS re-reported the case study and added no independent data). Response time fell from 18 to 2.9 seconds after a five-model evaluation, and twelve domain agents were merged into one in February 2026. The 500,000+ agent hours saved and the 70% cut in agents per passenger combine this chat agent with Amazon Connect voice work, so they are not chat-only results
Ryanair serves over 700,000 customers a day, and customer-service volume grew in line with passenger numbers. Scaling human agents linearly was not sustainable for a low-cost carrier, and the legacy chat bot gave static answers that customers abandoned (reported by AWS)
Wrong answers about refunds or disruptions at very high volume
Containment can hide frustrated customers who give up rather than get resolved
Limitations
Sources are AWS's own case study and a PYMNTS piece that re-reports it; no independent measurement
Wording is 'answers' and 'containment', and the page doesn't say which transactions, if any, the agent completes itself
The 500,000+ agent hours and the 70% cut in agents per passenger combine this chat agent with Amazon Connect voice work, so they are excluded as chat-agent outcomes
Unverified: these claims come from secondhand reports and haven't been confirmed.
About 120,000 customer chats a day across seven languages at an 80% containment rate, a vendor-reported figure that PYMNTS repeated without independent data Reported by AWS · Source (aws.amazon.com)
10 million answers at 94% accuracy since the October 2024 launch; accuracy is AWS's measure and the method isn't described Reported by AWS · Source (aws.amazon.com)
Response time cut 84%, from 18 seconds to 2.9 seconds, after moving to Amazon Nova 2 Lite, which was chosen from five models tested on 12,000 real customer questions Reported by AWS · Source (aws.amazon.com)
Since launching in October 2024, Ryanair's AI-powered customer service solution has generated 10 million chatbot answers, achieving a 94% accuracy rate.
Ryanair’s artificial intelligence now handles 120,000 customer chats a day across seven languages and resolves 80% of these conversations without a human agent, according to a case study published by Amazon Web Services.
Air India began building AI.g on Azure OpenAI after Microsoft launched the service in November 2022, and calls it the first airline generative AI customer-service deployment at scale. Microsoft's customer story (February 11, 2026) says AI.g handles about 40,000 queries a day across more than 1,300 question types, from booking changes to refund requests. It has resolved 13 million+ conversations at a 97% success rate, so only 3% go to a human (reported by Microsoft, the vendor). In the same story, CDTO Dr. Satya Ramaswamy cites '97% of 4 million-plus customer queries', which doesn't match the 13 million figure. It is mainly an answer assistant; agents that run full workflows such as refund processing are still in trial
Airbnb started its AI strategy at the bottom of the funnel with customer service. It rolled out an AI customer service agent in spring 2025 and expanded it to all US English users in May 2025. The agent is built on 13 models from OpenAI, Alibaba, Google and open-source providers, relying mostly on Qwen because it is 'fast and cheap'. It shows action buttons and links so guests can complete tasks such as reservation changes or cancellations. It must also work across languages, follow nearly 100 policies and escalate accurately to humans, especially for trust and safety incidents. In October 2025 Airbnb said the agent had cut users needing a live representative by 15% and average resolution time from nearly three hours to six seconds (reported by Fortune/Bloomberg). On the Q1 2026 earnings call CEO Brian Chesky said it resolved over 40% of inquiries, up from about a third the prior quarter. He also said cost per booking fell about 10% year over year, which can't be attributed to the agent alone (reported by CX Dive). The figures are company-reported, but they come from earnings disclosures over about a year of production
Ally Financial built Ally.ai, an internal platform that routes work to LLMs including OpenAI models on Microsoft Azure, and its first production use case drafts summaries of customer care calls that reps review and accept or edit instead of writing notes by hand (reported by American Banker). After about a year and a half in production, CIO Sathish Muthukrishnan said rep acceptance of AI summaries rose from the mid-teens to 90% and summary accuracy from 40% to above 80%, and the use case expanded from banking to insurance and auto (reported by American Banker, July 31, 2025; accuracy is Ally's own internal measure). In 2026 he put accuracy at around 85% with three to five minutes saved per call across roughly 10,000 calls a week (reported by American Banker, June 1, 2026; per-call savings are Ally's estimate, not an audited figure).
easykind, a telehealth start-up launched in 2023, had two Patient Support Coordinators manually triaging the inbox each morning and could only promise 24-hour replies, with phones limited to 9-to-5. Lorikeet's agent now reads every incoming email, tags it Tier 1, 2 or 3 and routes it to the right coordinator queue. 'Buddie', embedded in the logged-in patient experience, answers FAQs around the clock under guardrails required by Australian rules: it never names a product, and if a patient reports concerning side effects it tells them to stop the medication and call emergency services, and escalates to a human. Lorikeet built a Salesforce Service Cloud integration. Email response time fell 92% from 24 hours to roughly two (reported by Lorikeet); Head of Patient Support Steph Galileos estimates four additional hires would be needed to match Buddie's capacity (an estimate of avoided hires, reported by Lorikeet; vendor-published)
Riachuelo, a Brazilian fashion retailer, replaced its previous chatbot with a Genesys agentic virtual agent on WhatsApp. Intelligent CIO reports self-service at 84% versus 30% with the old chatbot, customer satisfaction up 60% and technology costs down 26% (reported by Intelligent CIO LATAM, October 15, 2026, César Nicoletti quoted). The article gives no measurement window, and the CSAT and cost changes also reflect the wider platform change, not the agent alone.