Customer Service Automation
Serre Chevalier needed a smarter way to answer multilingual, context-dependent visitor questions about ski-pass selection and trip planning because its earlier assistant could not keep pace with growing resort complexity and seasonal support demand.
Reported impact
The new AI agent reduced response latency, improved complaint resolution, handled large volumes of visitor conversations, and created a platform the resort can extend into operational workflows beyond customer care.
Serre Chevalier worked with IBM, Next Decision, and IBM Client Engineering to replace its older digital assistant with an agentic support experience built on IBM watsonx Orchestrate and IBM Cloud. The system is structured as cooperating agents that interpret visitor intent, retrieve the most relevant resort knowledge, and invoke supporting tools such as Python-based utilities to answer questions about ski passes, trip planning, and operational details in real time. As the deployment matured, the resort added IBM watsonx.governance for monitoring and visibility and IBM watsonx.ai for recurring data-gathering work such as daily web scraping that feeds operational workflows. Because the AI is embedded directly into the website, visitors get guided help without changing channels, while service teams spend less time on routine inquiries and can focus on the more complex issues that still require human intervention. The same orchestration model is now expanding into snow operations, HR workflows, and predictive equipment dashboards.
Visitor questions arrive through the Serre Chevalier website, watsonx Orchestrate routes them to agents that retrieve resort knowledge and process live inputs, responses are returned in near real time, and supporting watsonx.ai automation and governance feed the operational dashboards and future expansion areas such as snow monitoring and equipment management.
“Since the start of the winter season, the AI agent has handled more than 1,500 customer conversations”
“The AI experience itself is built as a coordinated set of agents rather than a traditional chatbot.”
“The resort now uses IBM watsonx.governance to give marketing and operations teams clearer visibility through improved dashboards and multi-LLM monitoring.”
“reducing response latency from 6–8 seconds to about 1 second”
“the teams aligned early on the objectives, workflows, and data inputs the system would need to coordinate.”
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
IBM Sample May 7, 2026 Riyadh Air Riyadh Air wanted to avoid the legacy-system bottlenecks that slow most airlines and instead build a cloud-native operating model that could coordinate guest journeys, operations and service decisions in real time from… 59 workstreams IBM Cloud Pak for Integration · IBM Consulting · IBM watsonx Orchestrate 
OpenAI Sample Modified · Oct 16, 2026 Localiza Localiza needed to turn generative AI into a company-wide operating model that could improve internal work, create new conversational customer entry points, and support AI-native products without treating the technology… 130 squads ChatGPT · Codex · Liza OpenAI Sample Oct 8, 2026 Virgin Atlantic At Virgin Atlantic, we’ve always seen ourselves as a challenger—willing to take bold bets that help us stand apart. AI fits that philosophy perfectly. ChatGPT Enterprise · Codex · Realtime API 