Finnair's AI Agent Sisu Resolves 80% of Customer Service Chats with Agentforce
Finnair built Sisu, an AI agent powered by Salesforce Agentforce, to instantly answer customer questions about luggage, check-in and flight extras on its website and app, unifying data from Service Cloud, Amadeus reservations and Finnair Plus loyalty details via Data 360, and escalating complex cases to reps with full context, resolving 80% of customer service chat inquiries.
Overview
Finnair built Sisu, an AI agent powered by Salesforce Agentforce, to instantly answer customer questions about luggage, check-in and flight extras on its website and app, unifying data from Service Cloud, Amadeus reservations and Finnair Plus loyalty details via Data 360, and escalating complex cases to reps with full context, resolving 80% of customer service chat inquiries.
This entry has 15 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Finnair's multilingual reps, fluent in 13 languages with a one-year onboarding process, had to navigate hundreds of internal knowledge sources, airport-specific information and international travel guidelines across multiple systems, a time-consuming and labor-intensive process. Finnair's previous chatbot handled simple, clearly worded queries but struggled with anything more conversational or nuanced, so many customers ended up calling in or searching for answers themselves.
The solution
Finnair's AI agent Sisu, powered by Agentforce, instantly answers general questions on the website and mobile app, responding in English and Finnish with more languages coming soon. Agentforce unifies information from Finnair's website, customer insights in Service Cloud, reservation data from Amadeus, and Finnair Plus loyalty details via Data 360, so Sisu can personalize service. When a case needs further assistance, Agentforce escalates to a rep with full context. Agentforce also generates case "mid-summaries" and "close summaries" from case details, transcripts and email threads, and automatically classifies every case.
Reported business value
Sisu's conversation volume increased nearly 7x over seven months, and in just four months Finnair doubled its first-contact resolution rate with Agentforce. Agentforce makes nearly 2 million secure LLM calls every month, cutting reps' time spent drafting by more than 20% and decreasing new-hire onboarding time by 25%.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other travel & hospitality entries in the register.
Transforming customer service with agentic AI and Amazon Nova at Ryanair
Ryanair, Europe's largest airline, built a customer service AI assistant on Amazon Bedrock AgentCore powered by Amazon Nova 2 Lite, working with AWS Partner Cation Consulting, to replace an earlier architecture of 12 domain-specific agents with a single consolidated agent. The assistant handles 120,000 daily chat interactions across seven languages with an 80% containment rate and 94% accuracy, cut response latency from 18 seconds to 2.9 seconds, and combined with Amazon Connect voice automation has reduced customer service agents per passenger carried by 70% while saving over 500,000 agent hours.
Skyscanner Scales Smarter Travel Search with the Databricks Data + AI Platform
Skyscanner, which handles 35 million searches and tens of billions of events daily, built bronze, silver and gold data layers on the Databricks Data + AI Platform to create shared Cornerstone Data Products powering multiple use cases, including a flight ranking model serving 180 million predictions daily. Unity Catalog provides governance, and the company is adopting emerging agentic AI capabilities to experiment safely and surface more relevant search results for travelers.
JetBlue Accelerates Innovation With AI
JetBlue uses the Databricks Data + AI Platform to unify flight, aircraft, and customer data, powering its operational digital twin, Blue Sky. By streaming half a terabyte of data per flight, JetBlue gains real-time insights that enhance safety, efficiency, and customer experience, with generative AI allowing teams to query data in natural language.
Optimizing global journeys through secure data connectivity
Amadeus, which serves more than 400 airlines and over 1 million hotels across 190+ countries, built a Data Mesh on the Databricks Data + AI Platform on Azure with Delta Lake, Delta Sharing and Unity Catalog to process over 10 petabytes of travel data and predict traveler behavior for personalized experiences and dynamic pricing. Amadeus now runs over 100 use cases in production with 950 internal users operating over 20,000 clusters and 60,000 virtual machines daily.
Was this helpful?
Your feedback helps us improve our use case database
