Use Case Intelligence RSS Search use cases Search
Microsoft Financial Services Germany

DATEV

Document Processing · Enterprise Knowledge Search · IT Operations Automation

The challenge: Shortage of skilled workers is making it harder for tax accountants to do their job

Read the original story Explore all use cases
And we’re talking about a great many heads indeed: in Germany, for instance, some 46 million people pay private income tax, according to the German Economic Institute.
Such documents can be up to 30 pages long—a veritable flood of information—and managing them takes up a great deal of time.
That makes 46 million tax declarations that have to be filled out and filed every year.
Then there are the 4.1 million companies required to pay trade tax—from neighborhood bakeries to global corporations.

Reported impact

Business outcome

Most of the solutions that emerge from our AI Workshop are based on Azure OpenAI Service and help tax accounting firms boost their efficiency in all manner of ways.

  • Compliance
  • Cost Reduction
  • Customer Experience
  • Productivity Improvement

Solution

DATEV built this solution on Azure OpenAI Service. The challenge: Shortage of skilled workers is making it harder for tax accountants to do their job. Azure OpenAI Service provides the generative AI model layer used for summarization, drafting, classification, or copilots in the workflow. Please check this tax assessment and submit an appeal if necessary.” One simple prompt and the automated appeal generator gets the job done. AI solutions like this lighten the workload for tax accounting firms—and the DATEV AI Workshop is where they are created. Business results include most of the solutions that emerge from our AI Workshop are based on Azure OpenAI Service and help tax accounting firms boost their efficiency in all manner of ways.

Solution architecture

1 components · 1 layer
  1. Compute
    • Azure OpenAI Service Provides the generative AI model layer used for summarization, drafting, classification, or copilots in the workflow.

Architecture clues

  • The implementation relies on Azure OpenAI Service as a core technical building block.

Evidence from the source

And we’re talking about a great many heads indeed: in Germany, for instance, some 46 million people pay private income tax, according to the German Economic Institute.
Most of the solutions that emerge from our AI Workshop are based on Azure OpenAI Service and help tax accounting firms boost their efficiency in all manner of ways.
The challenge: Shortage of skilled workers is making it harder for tax accountants to do their job
Then there are the 4.1 million companies required to pay trade tax—from neighborhood bakeries to global corporations.
“Please check this tax assessment and submit an appeal if necessary.” One simple prompt and the automated appeal generator gets the job done.
Transparency Evidence & methodology 43/100 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 value43/100
  • 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 scale0/10
    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

    DATEV customer story

    First-party
    https://www.microsoft.com/en/customers/story/1776974722213415807-datev-eg-azure-openai-service-banking-and-capital-markets-en-germany
    Source type
    Vendor-published customer story
    Published
    Jun 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 Jun 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 Dec 3, 2024 British Columbia Investment Management Corporation Financial Services Canada BCI is removing manual tasks through automation and Copilot features that streamline report writing, offering employees more time for strategic and creative tasks. BCI increased productivity by 10%-20% for 84% of Copilot users and increased their job satisfaction by 68%. The… Document ProcessingEnterprise Knowledge Search Azure OpenAI Service · Microsoft 365 · Microsoft 365 Copilot Microsoft Nov 18, 2025 Levi Strauss & Co. Retail Global Levi Strauss & Co.'s push to become a fan-obsessed, direct-to-consumer brand created an influx of data that overwhelmed inconsistent end-user devices—employees experienced crashes when handling 20,000-line reporting… Monthly reporting task involves about 20,000 lines of data Document ProcessingEnterprise Knowledge Search Copilot agents · Microsoft 365 Copilot · Microsoft Intune Microsoft Apr 30, 2025 NatWest Group Financial Services United Kingdom NatWest Group wanted to give colleagues secure, compliant generative AI tools that help them find information, summarize documents, draft content, and work more efficiently at bank-wide scale. 99% of our colleagues Document ProcessingEnterprise Knowledge Search AI Digital Enabler for NatWest · Microsoft Copilot Chat