Use Case Intelligence RSS Search use cases Search
IBM Public Sector Austria

Austrian Armed Forces

Enterprise Knowledge Search · Security and Compliance

The Austrian Armed Forces needed a trustworthy way to query large volumes of open-source and internal documentation because users required fact-based answers with traceable sources, low hallucination risk, and human oversight.

Read the original story Explore all use cases

Reported impact

Business outcome

The ministry gained a trusted AI interface for evidence-backed information retrieval while preserving human review, source traceability, and alignment with public-sector security requirements.

  • Compliance
  • Productivity Improvement
  • Risk Reduction

Solution

IBM Austria and the Federal Ministry for National Defence created ChatZentDoc as a minimal viable product for trusted generative AI over defense documentation. The ministry already used IBM Watson Explorer for natural-language processing and data collection, so IBM Client Engineering extended that foundation with IBM watsonx.ai to add source-grounded answer generation. The resulting front end lets users query the knowledge base in natural language, filter results, and export answers together with the cited source documents. The system also refreshes its information daily and includes a feedback loop so the ZentDok team can continuously improve response quality. By combining legacy NLP assets with newer generative AI under a human-in-the-loop operating model, the ministry built an OSINT-style knowledge service that supports defense analysts without relinquishing transparency or legal control.

Data flow

Daily-updated source documents flow into the ZentDok knowledge base, Watson Explorer and watsonx.ai process the content for retrieval and answer generation, and ChatZentDoc returns filterable, exportable responses with cited sources for user review.

Solution architecture

4 components · 3 layers
  1. Compute
    • IBM Watson Explorer Supplies the established NLP and data-collection foundation used by ZentDok before the generative AI extension.
    • IBM watsonx.ai Adds fact-based response generation over the defense knowledge base.
  2. Serving
    • ChatZentDoc Provides the user-facing interface that answers questions over the ministry's documentation in natural language.
  3. Orchestration
    • IBM Client Engineering Co-developed the MVP with the ZentDok team and translated the trust requirements into a working solution.

Architecture clues

  • Responses are grounded in cited source documents that can be exported with the answer.
  • The knowledge base is updated daily to preserve timeliness for defense use cases.
  • The operating model is explicitly human-in-the-loop and designed to minimize hallucination risk.

Evidence from the source

"ChatZentDoc runs using information that is updated daily"
"The responses can be exported along with the source documents."
"a so-called OSINT (Open-Source Intelligence Tool) was created"
"the human-in-the-loop principle"
Transparency Evidence & methodology 71/100 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 value71/100
  • 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 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
    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 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. IBM

    Austrian Armed Forces customer story

    First-party
    https://www.ibm.com/case-studies/the-federal-ministry-for-national-defence-bmlv
    Source type
    Vendor-published customer story
    Published
    May 2, 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

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
NVIDIA Jul 7, 2026 Public Ministry of Rio Grande do Sul (MPRS) Public Sector Brazil MPRS needed to manage rising legal caseloads, archived police inquiries, and public-service requests more efficiently, but the volume of legal documents and the need for compliant, locally controlled analysis made… 497 municipalities Document ProcessingEnterprise Knowledge Search Archiving Intelligence Assistant (AIA) · Citizen Access Agent · Justice Intelligence platform IBM Oct 7, 2025 Dynamiq Software / SaaS United States Dynamiq needed a way to help legal teams process large volumes of contracts, compliance reports, and regulatory documents faster, while reducing manual review work and improving the consistency of compliance decisions. 50% reduction in contract review, down from 1.5 hours to 45 minutes Document ProcessingEnterprise Knowledge Search IBM Granite · IBM watsonx Orchestrate · IBM watsonx.data AWS Apr 15, 2024 InfoCert Public Sector Italy Training and deploying these models was a lengthy, costly process, which limited access to this set of capabilities to larger companies. While InfoCert was searching for a way to streamline such ML integrations, AWS… Additionally, InfoCert expects to reduce financial overhead by 80 percent for startup, development, and… Document ProcessingEnterprise Knowledge Search Amazon Bedrock