{"slug":"ircem-s-ai-chatbot-handles-4-000-customer-conversations-monthly-with-a-90-completion-rate","url":"https://findausecase.com/use-cases/ircem-s-ai-chatbot-handles-4-000-customer-conversations-monthly-with-a-90-completion-rate","title":"IRCEM's AI chatbot handles 4,000 customer conversations monthly with a 90% completion rate","description":"IRCEM, a French non-profit social protection group serving 1.4 million childcare assistants and household employees plus 750,000 pensioners, worked with IBM Cloud Expert Labs to build a chatbot using IBM watsonx Assistant to automate responses to customer queries and point users to online documentation. The chatbot relieves customer relations teams of 4,000 conversations each month, with a 90% success rate for conversations that provide a response to the customer. IRCEM later extended AI into an assisted messaging system that analyzes a customer's draft email in real time to surface relevant information before it is sent; since its launch, the assistant activates 7 times out of 10, and 5-10% of users decide sending their message is no longer necessary after the AI's intervention.","company":"IRCEM","industry":"Insurance","country":"France","aiCapabilities":["Conversational AI","Natural Language Processing"],"technology":["IBM watsonx Assistant","IBM Cloud Expert Labs","IBM Cloud Orchestrator"],"deployment":"Unknown","problemStatement":"In the personal assistance sector, the need for information from clients is growing - and information is part of IRCEM's mission - because both employers and employees are private individuals who are not experts in complex and frequently changing pension, provident and insurance regulations.","solutionApproach":"IRCEM co-developed a chatbot with IBM Cloud Expert Labs using IBM watsonx Assistant, following Design Thinking sessions to identify the approach; a mixed IRCEM/IBM team built and trained the AI, testing it with business and customer relations experts before moving the decision tree into production, then later extended it into an assisted-messaging system that analyzes a customer's draft email in real time to surface relevant information before sending.","businessValue":"The chatbot relieves customer relations teams of about 4,000 conversations each month with a 90% completion rate; the assisted-messaging system, launched 9 months prior, activates 7 times out of 10, and 5-10% of users decide sending their message is no longer necessary after its intervention.","evidence":{"band":"high"},"sourceUrl":"https://www.ibm.com/case-studies/ircem","dates":{"publishedAt":"2026-09-15T09:05:29.354Z","publishedAtSource":"pipeline","updatedAt":"2026-09-15T09:05:29.354Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/ircem-s-ai-chatbot-handles-4-000-customer-conversations-monthly-with-a-90-completion-rate. Bulk republication requires permission."}