Ryanair customer service chat agent
Ryanair uses Amazon Bedrock AgentCore and Nova 2 Lite for a multilingual customer-service chat agent at airline scale.
Reported results
- 120,000 daily chat interactions across seven languages
- 80% containment
- 10 million answers generated
- Latency from 18 seconds to 2.9 seconds
As stated by AWS. Not independently verified.
- Company
- Ryanair
- Industry
- Travel & hospitality
- Platform
- AWS Bedrock
- Type
- Company deployment
- Source
- AWS (aws.amazon.com)
- Added
- Oct 14, 2026
What the agent does
Ryanair built a customer-service AI assistant on Amazon Bedrock AgentCore and Amazon Nova 2 Lite with AWS Partner Cation Consulting. The single-agent architecture replaced 12 domain-specific agents, handles baggage, refunds, bookings, and flight disruption queries, and uses guardrail scoring before answers reach customers. AWS reports the system handles 120,000 daily chat interactions across seven languages, achieves 80% containment, generated 10 million answers after launching in October 2024, and reduced response latency from 18 seconds to 2.9 seconds.
Read the source on aws.amazon.comStack
Related cases
LoanPro loan servicing assistant
LoanPro servicing teams use a multi-agent assistant to summarize borrower accounts and recommend next actions during calls.
Siemens global search agents
Siemens runs validation, classification, summarization, and guardrail agents behind its global website search.
Taxbit Assist compliance support agent
Taxbit Assist answers product and integration questions inside Taxbit's dashboard while checking roles, permissions, and regional controls.
HPE Zerto disaster recovery troubleshooting agents
HPE Zerto agents inspect live recovery environments, analyze logs, explain faults, and recommend bounded remediation steps.
Oriserve multilingual engagement agents
Oriserve runs generative AI agents on AWS for multilingual customer engagement across voice, chat, and email.
Southwest always-on traveler service agent
Southwest uses Agentforce on web and mobile to answer routine travel questions and escalate with context when needed.