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

Sicredi

Customer Service Automation · Enterprise Knowledge Search

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 support work more frustrating for employees.

Read the original story Explore all use cases
1% improvement in net promoter score
10%–12% improvement in retention, which are cases where the support rep resolved the member's query without involving a product specialist
20 days of pilot testing
6,500 members served during the pilot

Reported impact

Business outcome

Sicredi shortened response times, reduced escalation to specialists, improved the member experience, and gave its service teams a more scalable way to support a broad product portfolio.

  • Customer Experience
  • Productivity Improvement

Solution

Sicredi partnered with IBM Client Engineering to co-create a generative-AI assistant for its support representatives, focusing first on questions about the cooperative's consortium product. The pilot combined IBM watsonx.ai, IBM Watson Discovery, and IBM watsonx Assistant so staff could submit natural-language questions of varying complexity and receive grounded answers within seconds. In the implemented flow, watsonx Assistant provides the conversational entry point, Discovery searches Sicredi's support documentation, and watsonx.ai helps generate a response that representatives can use while serving members. Sicredi built the first version in three weeks and then tested it over a 20-day pilot with live customer-support traffic. Rather than replacing representatives, the architecture augments them with faster access to product knowledge, reduces unnecessary escalation to specialists, and creates a reusable support pattern the team plans to expand to all financial products.

Data flow

Support representatives ask natural-language questions through watsonx Assistant, Watson Discovery searches Sicredi's support documentation, watsonx.ai helps formulate an answer, and the representative uses that response to resolve the member's issue without waiting for a product specialist.

Solution architecture

3 components · 2 layers
  1. Compute
    • IBM watsonx.ai Helps generate responses to representative questions using the information retrieved from Sicredi's documentation.
  2. Serving
    • IBM Watson Discovery Searches Sicredi's support documentation to retrieve the information needed to answer product questions.
    • IBM watsonx Assistant Provides the natural-language interface through which support representatives submit questions to the assistant.

Architecture clues

  • Responses are generated in seconds from Sicredi's existing support documentation.
  • The assistant is intended for employee-facing augmentation rather than direct customer self-service.
  • The first pilot focused on Sicredi's consortium product before a planned expansion to other financial products.

Evidence from the source

"10%–12% improvement in retention, which are cases where the support rep resolved the member's query without involving a product specialist"
"8% decrease in abandonment of support calls due to wait time"
"The next step for Sicredi, following the pilot, is to begin expanding the bot's scope to include all other financial products."
"enabled by the IBM watsonx.ai IBM Watson Discovery and IBM watsonx Assistant solutions"
"the assistant will query Sicredi's support documentation and generate an answer within a matter of seconds"
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
    4 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

    Sicredi customer story

    First-party
    https://www.ibm.com/case-studies/sicredi-generative-ai-pilot
    Source type
    Vendor-published customer story
    Published
    May 14, 2024
    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 Jan 6, 2025 IRCEM Group Financial Services France 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. 4,000 conversations per month Customer Service AutomationEnterprise Knowledge Search IBM Cloud Expert Labs · IBM watsonx Assistant 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)