Microsoft Energy Brazil

Petrobras

Customer Service Automation · Document Processing · IT Operations Automation

Brazilian oil, natural gas, and energy corporation Petrobras used Azure OpenAI Service to create ChatPetrobras, a text generation tool using natural language processing to streamline workflows, reduce manual tasks, and summarize reports for 110,000 users.

Brazilian oil, natural gas, and energy corporation Petrobras used Azure OpenAI Service to create ChatPetrobras, a text generation tool using natural language processing to streamline workflows, reduce manual tasks
ChatPetrobras is an internal, generative AI tool created by Petrobras used for summarizing reports as well as editing and translating text in documents, emails, and internal messaging systems like Teams.
In November 2022, Petrobras employees started to use new AI services for office tasks like summarizing and rewriting reports and other documents and crafting messages for Microsoft Teams .
Petrobras is looking forward to figuring out how to use ChatPetrobras to answer questions based on the company's internal data and explore different versions of the models for the best results

Reported impact

Business outcome

Brazilian oil, natural gas, and energy corporation Petrobras used Azure OpenAI Service to create ChatPetrobras, a text generation tool using natural language processing to streamline workflows, reduce manual tasks

  • Compliance
  • Productivity Improvement

Solution

Brazilian oil, natural gas, and energy corporation Petrobras used Azure OpenAI Service to create ChatPetrobras, a text generation tool using natural language processing to streamline workflows, reduce manual tasks, and summarize reports for 110,000 users. Petrobras, an energy company, is the biggest company in Brazil and is controlled by the Brazilian federal government. The company has about 50,000 employees, including a large IT department of about 2,000 employees and a 70-year history of innovation. "We believe that digital transformation is not only a matter of technology but also process and culture," says Fernando Carneiro In November 2022, Petrobras employees started to use new AI services for office tasks like summarizing and rewriting reports and other documents and crafting messages for Microsoft Teams .

Data flow

Source content is gathered from the organization's documents and knowledge repositories, Azure OpenAI Service interprets or generates responses from that content, and the resulting answers or assessments are surfaced to employees or citizens through the application workflow.

Solution architecture

1 components · 1 layer
  1. Compute
    • Azure OpenAI Service Runs the large-language-model features for classification, summarization, retrieval, or conversational responses in the solution.

Architecture clues

  • Azure OpenAI Service: Runs the large-language-model features for classification, summarization, retrieval, or conversational responses in the solution.
  • Brazilian oil, natural gas, and energy corporation Petrobras used Azure OpenAI Service to create ChatPetrobras
  • ChatPetrobras is an internal, generative AI tool created by Petrobras used for summarizing reports as well as editing and translating text in documents, emails
  • In November 2022, Petrobras employees started to use new AI services for office tasks like summarizing and rewriting reports and other documents and crafting messages for Microsoft...
  • Petrobras and Microsoft have been partners for many years, with Petrobras using a large variety of Microsoft and Azure services.
  • Petrobras, an energy company, is the biggest company in Brazil and is controlled by the Brazilian federal government.

Evidence from the source

Brazilian oil, natural gas, and energy corporation Petrobras used Azure OpenAI Service to create ChatPetrobras, a text generation tool using natural language processing to streamline workflows, reduce manual tasks
In November 2022, Petrobras employees started to use new AI services for office tasks like summarizing and rewriting reports and other documents and crafting messages for Microsoft Teams .
Petrobras, an energy company, is the biggest company in Brazil and is controlled by the Brazilian federal government. The company has about 50,000 employees
Transparency Evidence & methodology 75/100 reference value · 82% 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 value75/100
  • 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 impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence82%
  • 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 evidence15/20
    3 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 specificity8/10
    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

    Petrobras customer story

    First-party
    https://www.microsoft.com/en/customers/story/1758695276753608190-petrobras-azure-openai-service-energy-en-brazil
    Source type
    Vendor-published customer story
    Published
    Apr 18, 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 Apr 18, 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.