Document Processing · IT Operations Automation
BMDS needed to reduce long, complex planning and approval procedures for infrastructure projects that routinely exceeded legal timelines and burdened case workers with documentation-heavy manual workflows.
Reported impact
BMDS gained a reusable AI foundation that accelerates approval procedures, reduces administrative burden, and preserves transparency and legal accountability while preparing the solution for reuse across German public administration.
BMDS launched its SPARK initiative with Capgemini and six European technology partners to build a modular AI-enabled approval platform for complex infrastructure permitting. The program began with user research into how case workers handle planning and approval files, then moved through prototype development, integrated testing, and phased rollout. The resulting system supports the full process from document preparation and formal review through substantive review, objection review, and AI-assisted drafting of administrative outputs. Capgemini designed the modules to be configurable, reusable, and connected through standard interfaces so they can fit existing public-administration platforms with minimal disruption. Validation and explainability mechanisms were embedded throughout the workflow so legal robustness, user feedback, and technical evolution could progress together, creating a trustworthy foundation for future administrative AI use cases.
Planning and approval files move through document preparation, formal review, substantive review, objection review, and AI-assisted drafting, with configurable modules handing work across each step and feeding user validation back into the process.
"BMDS aimed to address lengthy and complex planning and approval procedures for critical infrastructure projects, which were often delayed by more than six months beyond the legally defined limit."
"Following the solution’s rollout, the end-to-end system now supports administrative staff throughout the entire approval process, from document preparation and formal review to substantive review, objection review, and AI-assisted drafting of administrative outputs."
"Our technical solution uses so-called agentic AI and shortens procedures that currently take months to days."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Capgemini Sample Dec 5, 2025 German Federal Employment Agency The BA needed a privacy-compliant way to reduce the manual effort of turning Requests for Change and user stories into high-quality Jira tickets under increasing workload and limited staff capacity. Aleph Alpha · CrewAI · Jira 
Mistral Sample May 27, 2026 HTX HTX needed AI that understood Singapore's public-safety context, could be trained on sensitive data inside a secure environment, and would remain under government control rather than depending on generic off-the-shelf… 123B-parameter natively multimodal and multilingual foundation model AI Forge · AI Studio · NGINE 
OpenAI Sample Mar 21, 2025 Commonwealth of Pennsylvania Pennsylvania wanted to reduce time spent on drafting, research, summarization, IT support, procurement, contract analysis, and other administrative work across state agencies while keeping human oversight, transparency,… 175 employees from 14 agencies used ChatGPT Enterprise ChatGPT Enterprise 