← Back to IRCEM's AI chatbot handles 4,000 customer conversations monthly with a 90% completion rate

Source proof for IRCEM's AI chatbot handles 4,000 customer conversations monthly with a 90% completion rate

Source-bound proof

Verified source excerpts for every supported field

Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.

12 fields supported

Title

IRCEM's AI chatbot handles 4,000 customer conversations monthly with a 90% completion rate

derived · high
…es on which the operational and IT managers found themselves in agreement". 4,000 Conversations per month The chatbot relieves customer relations teams of 4,000 conversations each month 90% Completion Rate The success rate for Chatbot conversations that provide a response to the custo…

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.

derived · high
…ditional way by an advisor. "Since the launch of this service 9 months ago, we have observed that the assistant is activated 7 times out of 10. And following its intervention, between 5 and 10% of people finally decide that sending their message is no longer necessary," summarizes Ludovic Decarpigny. Recruiting employees to manage customer re…

Company

IRCEM

quote · high
…ervice, while offering our advisors a more attractive mission." About IRCEM Groupe IRCEM is a non-profit, jointly-managed social protection group dedicated to the home and family employment sector. Founded in 1973, it protects its members from life's risks and supports the mos…

Country

France

classification · medium
…me Case Studies IRCEM AI: operational excellence support for customer relations The use of personal services is expected to increase by more than 35% by 2050 according to INSEE. IRCEM is on the front line to support employees and employers in this sector. W…

Industry

Insurance

classification · medium
…ty-free life expectancy of its members" at the heart of its 3 institutions: IRCEM Retraite, IRCEM Prévoyance and IRCEM Mutuelle. IRCEM's mission is to protect over 1.4 million childcare assistants and employ…

Problem

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.

derived · high
…services to the new challenges of tomorrow . In the personal assistance sector, the need for information from clients is growing - and information is part of IRCEM's mission. Firstly, because both employers and employees are private individuals. Unlike…

Solution

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.

derived · high
…technical part, linked to the chatbot's GUI and its integration into the site. For each of these tasks, a team was formed comprising an IRCEM developer and an IBM Cloud Expert Labs developer. The team was headed by a project manager. This co-development organization was…

Business value

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.

derived · high
…es on which the operational and IT managers found themselves in agreement". 4,000 Conversations per month The chatbot relieves customer relations teams of 4,000 conversations each month 90% Completion Rate The success rate for Chatbot conversations that provide a response to the custo…

AI capabilities

Conversational AI, Natural Language Processing

classification · high
…and customer relations experts were brought in to test the chatbot. Then, once the AI's understanding was deemed sufficient, the decision tree was moved into production for the public launch. "IBM's cloud-based feedback tools enabled us to trac…

Technology

IBM watsonx Assistant, IBM Cloud Expert Labs, IBM Cloud Orchestrator

classification · high
…idual employers, as well as 750,000 pensioners. More information about ircem.eu Solution components IBM Cloud Expert Labs IBM watsonx Assistant IBM Cloud Orchestrator Learn more Contact IBM Apollonia Sbragia Designer @IBM Cloud Expert Labs AI…

Headline outcome

derived · high
…The chatbot relieves customer relations teams of 4,000 conversations each month 90% Completion Rate The success rate for Chatbot conversations that provide a response to the customer is 90% We had made a considerable effort to put documentation for our customers online…

Use case type

Conversational assistant

classification · high
…rse IT Service Manager at IRCEM A chatbot at the service of customer excellence It was the chatbot project that was finally selected. Its objective: to automate certain responses and point to online documentation of IRCEM sites . The project was split into two parts: an artificial intelligence part and a m…
Capture details
Captured
10 Sept 2026, 06:05 UTC
Extractor
fetch-strip@1
Snapshot hash
6d19439f48c34ca551113df110e5b2862f33a5a216c01f5020951f5daebfff86