Use Case Intelligence RSS Search use cases Search
EY Software / SaaS global

Microsoft

Document Processing · Security and Compliance

Microsoft's Corporate, External, and Legal Affairs organization needed to monitor and interpret fast-changing regulations at high quality and speed, but manual legal review took hours per regulation and made it difficult to scale compliance analysis consistently across the department.

Read the original story Explore all use cases
four months of development and multiple sprints of rapid iteration
intensive two-day workshop
over 250 potential use cases gathered from CELA
task that previously took hours to minutes

Reported impact

Business outcome

Microsoft shortened regulatory-compliance analysis from hours to minutes, created a pilotable GenAI workflow for legal work and established reusable compliance skillsets that can accelerate additional Azure-based AI deployments across CELA.

  • Compliance
  • Productivity Improvement
  • Scalability
  • Speed to Market

Solution

Microsoft's CELA organization worked with EY Law and technology teams to build a generative AI workflow for regulatory compliance. After reviewing more than 250 potential use cases, the teams ran an intensive two-day workshop on data strategy, privacy, confidentiality and legal work product, then designed a regulatory-space proof of concept integrated with the EY Global Tax Platform. The solution uses Microsoft Azure Open AI and Microsoft Semantic Kernel to ingest new regulations, summarize them, identify next steps and generate formatted emails and implementation guidance artifacts for CELA stakeholders. Beyond chat, the workflow captures scope, compliance dates, trust domains, citations, defined terms and fields from regulatory text. Rapid iteration with lawyers and product teams turned the POC into a pilot implementation in the legal department and yielded reusable skillsets for document understanding, automated document generation, predictive action and position tracking.

Data flow

New regulations are ingested into the regulatory space workflow, where Azure Open AI and Semantic Kernel summarize the text, extract key compliance fields and identify next actions. The integrated solution then populates implementation-guidance artifacts and email outputs for CELA stakeholders, and lawyers refine the workflow through pilot feedback and additional use-case expansion.

Solution architecture

4 components · 4 layers
  1. Compute
    • Microsoft Azure Open AI Provides the core generative AI capability for summarizing regulations and drafting compliance outputs.
  2. Storage
    • EY Global Tax Platform Supplies the platform integration point used to systematize regulatory-compliance automation and downstream legal artifacts.
  3. Serving
    • regulatory space solution Delivers the legal-team workflow that summarizes regulations, generates forms and automates stakeholder communications.
  4. Orchestration
    • Microsoft Semantic Kernel Coordinates workflow logic that turns regulatory content into structured legal tasks and outputs.

Architecture clues

  • Four reusable GenAI skillsets emerged from the implementation: document understanding, automated document generation, predictive action, and position and version tracking.
  • The compliance workflow is powered by Microsoft Azure Open AI and Microsoft Semantic Kernel.
  • The solution was integrated with the EY Global Tax Platform rather than left as a standalone chat experiment.
  • The tool summarizes new regulations, identifies required next steps and generates formatted outputs for stakeholders.

Evidence from the source

"Impact: This automation allows lawyers to quickly understand the regulation's implications for Microsoft, transforming a task that previously took hours to minutes."
"The work also resulted in four primary, scalable GenAI skillsets that can be applied to fast-track deployment of further Microsoft Azure-driven solutions for different use cases within the legal department."
"This tool is powered by Microsoft Azure Open AI and Microsoft Semantic Kernel."
"Within weeks, the EY technology team developed the necessary skillsets for the desired automation, which cleared the way for Microsoft to move forward with a pilot implementation of the GenAI solution in the legal department."
Transparency Evidence & methodology 75/100 reference value · 83% 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 confidence83%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability25/25
    12 of 12 key fields link to a named source.
  • Direct evidence20/20
    4 direct source quotes retained.
  • Date provenance0/10
    The publication date has no documented provenance.
  • Source transparency10/10
    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. EY

    How Microsoft uses GenAI for compliance | EY - Global

    First-party
    https://www.ey.com/en_gl/insights/law/how-microsoft-streamlined-regulatory-compliance-with-gen-ai
    Source type
    Vendor-published customer story
    Supports
    • Customer
    • Industry
    • Region
    • Company size
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • Business outcome
    • Metrics
    • Architecture
    • evidence quotes

Date evidence

  • First archived Nov 4, 2024 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
    Open date source

Related

Similar use cases

See all like this
Google Cloud Archived · Sep 17, 2026 Parsewise Software / SaaS United Kingdom For risk specialists in the financial services and insurance industries, reading can feel like a full-time job. Whether assessing an insurance claim or approving a loan, these subject matter experts must search through… 29% lower error rate than best-performing LLM on grounded-reasoning benchmark Document ProcessingRisk Management Gemini · Gemini 3.0 Flash · Gemini 3.5 Flash Google Cloud Modified · Jul 13, 2026 UJJI AI Software / SaaS United Kingdom Before the strategic partnership between UJJI AI and Google Cloud, the development of a single corporate training, especially for banks and financial entities, struggled with slow and linear production cycles, requiring… , guaranteeing 99.9% availability Document ProcessingIT Operations Automation Cloud Run · Gemini · Gemini Enterprise NVIDIA Jun 23, 2026 Rafiqspace.ai Software / SaaS Indonesia Rafiqspace.ai needed to deliver compliance-grade Bahasa Indonesia transcription and speaker attribution for government and regulated-enterprise meetings, but manual transcription was slow and inaccurate and commercial… 1.65x real-time streaming Document ProcessingSecurity and Compliance NVIDIA H100 GPUs · NVIDIA L40S GPUs · NVIDIA NeMo ClusterDiarizer