Use Case Intelligence RSS Search use cases Search
Microsoft Commercial and Professional Services United States

H&R Block

Application Refactoring

H&R Block wanted to build its first AI-assisted tax preparation solution for individual filers.

Read the original story Explore all use cases
Half of 150 million US taxpayers file their own returns. H&R Block, a tax preparation company, focuses on building customer confidence as they go through the process. For the 2024 tax season, H&R Block launched AI Tax Assist, a generative AI tool that streamlines online tax filing by empowering customers to ask questions during the workflow. Vin Kamat, Principal Architect at H&R Block, shares why his team built the solution in Microsoft Azure cloud-native services and developed it in .NET, using Azure OpenAI Service—and why .NET offers a significant opportunity for AI innovation.

Reported impact

Business outcome

Now, with GitHub Copilot , developers have even more productivity and efficiency gains.

  • Compliance
  • Customer Experience
  • Productivity Improvement
  • Scalability

Solution

H&R Block, a Financial Services organization in United States, modernized this application refactoring workload with Azure OpenAI Service, Azure App Service, Azure Functions, GitHub, and Azure SDK. H&R Block wanted to build its first AI-assisted tax preparation solution for individual filers. Azure OpenAI Service runs the large language model workloads that power summarization, generation, or conversational reasoning in the solution. Azure App Service hosts the web applications and APIs that deliver the business service to users. Azure Functions executes event-driven business logic and integrations without dedicated server management. Operational data and user activity flow through Azure OpenAI Service, Azure App Service, and Azure Functions, where the platform processes information and serves outputs back to business users. Now, with GitHub Copilot , developers have even more productivity and efficiency gains.

Data flow

Operational data and user activity flow through Azure OpenAI Service, Azure App Service, and Azure Functions, where the platform processes information and serves outputs back to business users.

Solution architecture

5 components · 4 layers
  1. Compute
    • Azure OpenAI Service runs the large language model workloads that power summarization, generation, or conversational reasoning in the solution.
    • Azure Functions executes event-driven business logic and integrations without dedicated server management.
  2. Serving
    • Azure App Service hosts the web applications and APIs that deliver the business service to users.
  3. Orchestration
    • GitHub supports code collaboration and developer workflow automation around the solution.
  4. Uncategorized
    • Azure SDK supports part of the customer’s Microsoft-based application and data workflow.

Evidence from the source

Azure App Service
Azure Functions
H&R Block wanted to build its first AI-assisted tax preparation solution for individual filers.
Half of 150 million US taxpayers file their own returns. H&R Block, a tax preparation company, focuses on building customer confidence as they go through the process. For the 2024 tax season, H&R Block launched AI Tax Assist, a generative AI tool that streamlines online tax filing by empowering customers to ask questions during the workflow. Vin Kamat, Principal Architect at H&R Block, shares why his team built the solution in Microsoft Azure cloud-native services and developed it in .NET, using Azure OpenAI Service—and why .NET offers a significant opportunity for AI innovation.
Now, with GitHub Copilot , developers have even more productivity and efficiency gains.
Transparency Evidence & methodology 53/100 reference value · 87% 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 value53/100
  • Problem clarity12/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth15/25
    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 impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence87%
  • 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 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

    H&R Block customer story

    First-party
    https://www.microsoft.com/en/customers/story/18838-h-and-r-block-dotnet
    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 Jun 3, 2025 Infosys Commercial and Professional Services global Infosys wanted to move beyond basic AI augmentation in the software development life cycle because developers still had to manually review, validate, integrate, and fix generated code in large enterprise applications,… Creating end-to-end unit test cases took about 45 minutes with AI assistance, compared to a couple of weeks it… Application Refactoring GitHub Copilot agent mode · iLEAD platform · model context protocol servers OpenAI Oct 8, 2026 Endava Commercial and Professional Services Global Endava needed to remain relevant in an AI-centric market by redesigning software delivery and cross-functional workflows, not just adding point tools to existing engineering processes. 11,000-person global workforce Application RefactoringIT Operations Automation AI agents · ChatGPT Enterprise · Codex ServiceNow Modified · Jul 30, 2026 Syslabo Commercial and Professional Services Tokyo, Japan Syslabo needed to replace a 30-year-old legacy sales support stack, remove silos between separate sales tools, and give business users a practical way to build and improve internal applications without long specialist… 2x Faster onboarding for App Engine with AI Agents Application RefactoringSales Automation AI Agents · App Engine · Now Assist for Creator