Use Case Intelligence RSS Search use cases Search
Microsoft Software / SaaS United States

Harvey

Document Processing · Enterprise Knowledge Search

In an industry traditionally underserved by digital innovation, the founders at Harvey are delivering professional-class AI to lawyers around the world.

Read the original story Explore all use cases
In fact, one corporate lawyer said using Harvey saved them 10 hours of work per week.

Reported impact

Business outcome

In fact, one corporate lawyer said using Harvey saved them 10 hours of work per week.

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

Solution

Harvey built its Microsoft solution to improve knowledge retrieval and expert-assistance workflows. In an industry traditionally underserved by digital innovation, the founders at Harvey are delivering professional-class AI to lawyers around the world. Key components included Azure OpenAI Service ran model inference or heavy processing, and Azure Kubernetes Service coordinated workflows, prompts, or deployment. User prompts and domain content are orchestrated through Azure OpenAI Service, processed by Azure OpenAI Service, and then delivered through Azure Kubernetes Service so Harvey can return context-aware answers or automation in the flow of work. The governed Microsoft stack gave Harvey a reusable foundation for generative ai / llm, ai and machine learning while keeping deployment, security, and day-to-day operations inside the Microsoft estate. In fact, one corporate lawyer said using Harvey saved them 10 hours of work per week.

Data flow

User prompts and domain content are orchestrated through Azure OpenAI Service, processed by Azure OpenAI Service, and then delivered through Azure Kubernetes Service so Harvey can return context-aware answers or automation in the flow of work.

Solution architecture

2 components · 2 layers
  1. Compute
    • Azure OpenAI Service Runs large language models that generate grounded responses, summaries, and copilots.
  2. Orchestration
    • Azure Kubernetes Service Operates containerized application and AI workloads in a managed Kubernetes environment.

Architecture clues

  • "Azure makes that easy" With Harvey on Azure and serving law firms and other legal industry customers across the world, its technology team needed to deploy AI models for the platform in different regions while adhering to varied security requirements and keeping the sensitivity of customer data top of mind.
  • "Having all the scaling and security capabilities around the models and the ability to spin up the rest of our infrastructure around Harvey in every region has also been super valuable, and at the time we switched, it wasn't possible with a lot of other vendors." Harvey's engineers primarily use Azure OpenAI Service o1-preview and o1-mini models, which can better tackle reasoning and problem-solving tasks with increased focus, along with the latest GPT-series models on Azure OpenAI infrastructureoptimized for chat and high accuracy.
  • For example, European customers require that models be hosted in Europe, while other customers need data hosted in specific regions.
  • The Harvey technology stack is rounded out by Azure Communication Services Azure Kubernetes Service (AKS) Azure Container Registry Azure Database for PostgreSQL Azure Traffic Manager , and a complementary mix of infrastructure and platform services.

Evidence from the source

"Having all the scaling and security capabilities around the models and the ability to spin up the rest of our infrastructure around Harvey in every region has also been super valuable, and at the time we switched, it wasn't possible with a lot of other vendors." Harvey's engineers primarily use Azure OpenAI Service o1-preview and o1-mini models, which can better tackle reasoning and problem-solving tasks with increased focus, along with the latest GPT-series models on Azure OpenAI infrastructureoptimized for chat and high accuracy.
In an industry traditionally underserved by digital innovation, the founders at Harvey are delivering professional-class AI to lawyers around the world.
In fact, one corporate lawyer said using Harvey saved them 10 hours of work per week.
The Harvey technology stack is rounded out by Azure Communication Services Azure Kubernetes Service (AKS) Azure Container Registry Azure Database for PostgreSQL Azure Traffic Manager , and a complementary mix of infrastructure and platform services.
Transparency Evidence & methodology 76/100 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 value76/100
  • 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 specificity16/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact15/25
    1 metric describe measurable impact.
  • Deployment scale5/10
    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
    4 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

    Harvey customer story

    First-party
    https://www.microsoft.com/en/customers/story/19750-harvey-azure-open-ai-service
    Source type
    Vendor-published customer story
    Published
    Dec 3, 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 Dec 3, 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 Dec 3, 2024 KMS Lighthouse Software / SaaS Global Always seeking innovation, it aimed to enhance its knowledge management platform to provide more efficient content creation and advanced AI capabilities for its global clientele across various industries. "Our net new business exceeded $1 million in the first few months." We've seen an increase in demand for our… Customer Service AutomationDocument Processing Azure Marketplace · Azure OpenAI Service · Dynamics 365 Field Service Microsoft Oct 18, 2024 Orbital Witness Software / SaaS United Kingdom "At the time it was a difficult decision with an uncertain outcome. But, with 70 percent time savings when performing due diligence, our customers want these tools at their… Document ProcessingEnterprise Knowledge Search Azure AI Vision · Azure App Service · Azure OpenAI Service Microsoft Sep 16, 2024 Finastra Software / SaaS Global Finastra wanted to improve its marketing processes, with campaign creation often taking up to several months. Depending on the task, Copilot saves 20% to 50% of employees' time, allowing for strategic work. Customer Service AutomationDocument Processing Microsoft Copilot · Microsoft Viva Engage · Power BI