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

Bradesco

Customer Service Automation · Document Processing · Enterprise Knowledge Search

Phelipi Dal'Olio Santos, Data Manager at Bradesco, highlighted the challenge: "It was very new and challenging.

Read the original story Explore all use cases
82% resolution rate in the first level of service.
89% client retention rate.
According to Augusto Vieira, Data Manager at Bradesco, updating answers and documents used to take 3-5 days.
The implementation of Microsoft Azure's generative AI by Bradesco resulted in a reduction in the response time from days to hours and an 8x growth in the use...

Reported impact

Business outcome

We had to make a solution in a dynamic market with many changes, but we successfully brought all these innovations to BIA." To streamline queries on internal regulations and boost managers' productivity, Bradesco harnessed the power of generative AI to quickly and accurately generate answers and documents, eliminating time-consuming...

  • Customer Experience
  • Productivity Improvement
  • Revenue Growth
  • Risk Reduction

Solution

Bradesco used Microsoft Fabric, Azure Databricks, Azure OpenAI Service to replace disconnected manual workflows with a more consistent digital operating model. Where generative AI is involved, Azure OpenAI handles the language understanding layer while connected data and workflow services keep responses grounded in enterprise context. We had to make a solution in a dynamic market with many changes, but we successfully brought all these innovations to BIA." To streamline queries on internal regulations and boost managers' productivity, Bradesco harnessed the power of generative AI to quickly and accurately generate answers and documents, eliminating time-consuming...

Data flow

Data flows from operational systems through source-system connectors into Microsoft Fabric, where Azure Databricks prepares and enriches it; Microsoft Fabric then exposes governed analytics and decision support to end users.

Solution architecture

5 components · 3 layers
  1. Compute
    • Azure Databricks Transforms large-scale data and runs analytical or machine-learning workloads.
    • Azure OpenAI Service Runs large language model inference for summarization, extraction, conversational AI, and grounded answers.
    • Azure AI Services Supplies prebuilt AI capabilities such as language, speech, or vision services within the application flow.
  2. Storage
    • Microsoft Fabric Unifies lake, warehouse, analytics, and BI workloads on a single managed data platform.
  3. Serving
    • Azure AI Search Indexes enterprise content and retrieves grounding context for assistants and search experiences.

Architecture clues

  • Applies retrieval-based grounding with Azure AI Search before answer generation.
  • Consolidates analytics and BI workloads on Microsoft Fabric as a shared data foundation.
  • Uses Azure OpenAI for grounded generation or large-scale extraction workloads.

Evidence from the source

Phelipi Dal'Olio Santos, Data Manager at Bradesco, highlighted the challenge: "It was very new and challenging.
The fact that this is already a reality makes us proud." Discover more details CUSTOMER Banco Bradesco SA PRODUCTS Azure Azure AI Search Azure AI Services Azure Databricks Azure Data Lake Storage Azure Service Fabric ORGANIZATION SIZE...
The implementation of Microsoft Azure's generative AI by Bradesco resulted in a reduction in the response time from days to hours and an 8x growth in the use of BIA, significantly improving the operational efficiency and client...
This integration leverages the full Microsoft Azure suite, including Microsoft Azure AI Services Microsoft AI Search Microsoft OpenAI Service Microsoft Data Lake Storage Microsoft Azure Databricks , and Microsoft Azure Service Fabric , all...
We had to make a solution in a dynamic market with many changes, but we successfully brought all these innovations to BIA." To streamline queries on internal regulations and boost managers' productivity, Bradesco harnessed the power of...
Transparency Evidence & methodology 95/100 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 value95/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth20/25
    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
    5 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. Microsoft

    Bradesco customer story

    First-party
    https://www.microsoft.com/en/customers/story/19177-banco-bradesco-sa-azure-ai-services
    Source type
    Vendor-published customer story
    Published
    Oct 17, 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

  • Published on source page Oct 17, 2024 · Microsoft · First-party
    Open date source
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
Microsoft Jan 28, 2025 U.S. Venture Financial Services United States U.S. AutoForce pays thousands of invoices per day and 50% of orders are for same day delivery. Its legacy supply chain and warehouse management tools could no longer reliably perform at this volume and the finance team… A difference on day one with Microsoft 365 Copilot for Finance Customer Service AutomationDocument Processing Dynamics 365 Finance · Microsoft 365 · Microsoft 365 Copilot Microsoft Jul 30, 2024 PKSHA Technology, Inc. Financial Services Japan PKSHA Technology develops algorithmic solutions and AI technologies that help companies become more efficient and improve their processes—they believe in the power of algorithms to solve some of the world’s biggest… PKSHA leans on Copilot for Microsoft 365 as part of their team Customer Service AutomationDocument Processing Microsoft 365 · Microsoft 365 Business · Microsoft Copilot for Microsoft 365 Microsoft Jan 25, 2024 Nsure.com Financial Services United States Most recently, it has used the generative AI capabilities in Power Automate, including text recognition and sentiment analysis, to reduce manual processing time by 60% while also reducing associated costs by 50%. Even with extensive automation in place, more than 100 customer representatives were processing over 100,000… Customer Service AutomationDocument Processing Azure AI Foundry · Microsoft Copilot Studio · Microsoft Fabric