Use Case Intelligence RSS Search use cases Search
IBM Financial Services France

IRCEM Group

Customer Service Automation · Enterprise Knowledge Search

IRCEM needed to answer growing volumes of customer questions about complex pension, insurance, and social-protection topics without forcing advisors to handle every inquiry manually by email or phone.

Read the original story Explore all use cases
4,000 conversations per month
7 times out of 10
90% completion rate
between 5 and 10% of people finally decide that sending their message is no longer necessary

Reported impact

Business outcome

IRCEM reduced the load on customer-relations teams, improved the consistency of answers, and created an AI-assisted service model that blends self-service automation with advisor augmentation.

  • Customer Experience
  • Productivity Improvement

Solution

IRCEM partnered with IBM Cloud Expert Labs to build a chatbot and then an assisted-messaging capability around IBM watsonx Assistant. The initial chatbot project focused on social-action questions and used existing documentation, FAQs, and prior emails to automate answers and direct users to the right online resources. IBM trained IRCEM teams to configure, test, and tune watsonx Assistant so the organization could gradually internalize both the technology and the AI operating skills. After the first topic was stabilized, IRCEM expanded the bot into areas such as retirement and provident insurance, then added an assisted-messaging flow in which AI analyzes the text of an outbound customer email and surfaces general or personal information from IRCEM data before the message is sent. This architecture blends self-service automation with advisor augmentation, reducing unnecessary messages while preserving a human handoff when the AI cannot fully resolve the request.

Data flow

Documentation, prior emails, and IRCEM data feed watsonx Assistant, which answers customer questions in the chatbot or analyzes draft customer emails in real time and returns relevant general or personal information before the advisor workflow falls back to traditional processing.

Solution architecture

2 components · 2 layers
  1. Serving
    • IBM watsonx Assistant Powers the chatbot and assisted-messaging workflows that answer or augment customer inquiries.
  2. Orchestration
    • IBM Cloud Expert Labs Provided agile co-development, design sessions, and training so IRCEM could deploy and operate the AI solution internally.

Architecture clues

  • IRCEM intentionally transferred knowledge so it could operate and expand the assistant internally.
  • The assisted-messaging flow analyzes emails before they are sent and only hands off when needed.
  • The project used a co-development model pairing IRCEM and IBM developers.

Evidence from the source

IBM Cloud Expert Labs trained the IRCEM teams in the use of watsonx Assistant.
The chatbot now accounts for almost 4,000 conversations a month
The success rate for Chatbot conversations that provide a response to the customer is 90%
between 5 and 10% of people finally decide that sending their message is no longer necessary
when the customer enters the content of his email in a dedicated window, the AI analyzes his texts to provide him, in real time, with general or personal information taken from his IRCEM data.
Transparency Evidence & methodology 100/100 reference value · 89% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value100/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    2 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. IBM

    IRCEM Group customer story

    First-party
    https://www.ibm.com/case-studies/ircem
    Source type
    Vendor-published customer story
    Published
    Jan 6, 2025
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
IBM May 14, 2024 Sicredi Financial Services Brazil Sicredi's support representatives had to answer questions across many financial products, and the previous assistant often required escalation to product specialists, which lengthened wait times for members and made… 1% improvement in net promoter score Customer Service AutomationEnterprise Knowledge Search IBM Watson Discovery · IBM watsonx Assistant · IBM watsonx.ai Google Cloud Archived · Sep 17, 2026 Home Credit Bank Financial Services Kazakhstan Home Credit Bank needed a safer enterprise AI environment that non-technical teams could use to build banking agents quickly without creating data-leak risk or relying on a long custom-development cycle for each new use… Achieved 100% migration to a secure AI environment Customer Service AutomationEnterprise Knowledge Search Agent Designer · Gemini Enterprise OpenAI Jul 7, 2026 MUFG Financial Services Japan MUFG needed to modernize banking operations and customer experiences with AI while satisfying the governance, security, training, and trust requirements expected of a major financial institution. 100% training participation among employees receiving accounts Customer Service AutomationEnterprise Knowledge Search AI bankers · ChatGPT Enterprise · MAP (Money Advisory Platform)