Microsoft Public Sector Mexico

Supreme Court of Justice of the Nation

Document Processing · Enterprise Knowledge Search

Mexico's Supreme Court, the Supreme Court of Justice of the Nation (SCJN), digitized millions of physical files and built a legal search engine for the public using language models created with artificial intelligence and Azure cognitive services.

Reported impact

Business outcome

Today, the model is trained to identify the names of organizations, suggest precepts in the field of human rights, identify executory statements using common language, and to classify articles of the American Convention on Human Rights, the UN Universal System of Human Rights, the Constitutional Courts of Spain and Chile, and the Courts of different other countries.

  • Cost Reduction
  • Scalability

Solution

Mexico's Supreme Court, the Supreme Court of Justice of the Nation (SCJN), digitized millions of physical files and built a legal search engine for the public using language models created with artificial intelligence and Azure cognitive services. “In Azure and particularly, with Databricks Machine Learning we could quickly build an architecture for data processing and model training.” The Supreme Court of Justice of the Nation (SCJN) is the Highest Constitutional Court of Mexico and head of the Judiciary of the Mexican Federation. Through its judicial resolutions, the court defends the Political Constitution of the United Mexican States and maintains balance between the different powers and spheres of Mexico’s government.

Solution architecture

2 components · 2 layers
  1. Compute
    • Azure Provides the scalable cloud foundation hosting the organization’s applications, data, and integrations.
  2. Storage
    • SharePoint Hosts source documents and collaboration content that downstream apps automate or analyze.

Architecture clues

  • Azure: Provides the scalable cloud foundation hosting the organization’s applications, data, and integrations.
  • Integrates with SharePoint.
  • SharePoint: Hosts source documents and collaboration content that downstream apps automate or analyze.

Evidence from the source

Mexico's Supreme Court, the Supreme Court of Justice of the Nation (SCJN), digitized millions of physical files and built a legal search engine for the public using language models created with artificial intelligence and Azure cognitive services.
The Supreme Court of Justice of the Nation (SCJN) is the Highest Constitutional Court of Mexico and head of the Judiciary of the Mexican Federation. Through its judicial resolutions, the court defends the Political Constitution of the United Mexican States and maintains balance between the different powers and spheres of Mexico’s government.
The digital transformation of SCJN began in 2013, by implementing collaborative environments using Microsoft Office 365, Outlook, and Sharepoint. Under SCJN President Arturo Zaldivar in 2019, the court embarked on an ambitious project to use disruptive technologies, such as cloud computing and artificial intelligence to make the most of the court’s legal record.
Today, the model is trained to identify the names of organizations, suggest precepts in the field of human rights, identify executory statements using common language, and to classify articles of the American Convention on Human Rights, the UN Universal System of Human Rights, the Constitutional Courts of Spain and Chile, and the Courts of different other countries.
“In Azure and particularly, with Databricks Machine Learning we could quickly build an architecture for data processing and model training.”
Transparency Evidence & methodology 70/100 reference value · 85% 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 value70/100
  • 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 impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence85%
  • 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 specificity6/10
    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

    Supreme Court of Justice of the Nation customer story

    First-party
    https://www.microsoft.com/en/customers/story/1656442281606099981-supreme-court-of-justice-of-the-nation-national-government-microsoft-azure
    Source type
    Vendor-published customer story
    Published
    Jul 8, 2023
    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 Jul 8, 2023 · 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.