Document Processing
GlasfaserPlus needed a scalable way to read, classify, and document large volumes of unstructured correspondence and field comments so it could assess and predict delays across thousands of fiber rollout projects.
Reported impact
GlasfaserPlus automated project-document analysis, improved workforce allocation and stakeholder communication, and created a stronger operational basis for delay management across its fiber-expansion portfolio.
GlasfaserPlus worked with Capgemini to build a generative AI delay-analysis system for large-scale fiber rollout programs in Germany. The company’s back office was receiving thousands of documents and comments through faxes, letters, emails, and field updates, all of which had to be read, classified, documented, and incorporated into delay calculations. Capgemini proposed an LLM-based approach and developed it iteratively with GlasfaserPlus’ IT team over eight weeks. The system converts unstructured PDF documents into structured records using collaboratively engineered prompts, then extracts the core facts needed to assess delay causes and predict impacts on expansion projects. This structured output gives employees a faster way to review case material, allocate workforce, and communicate proactively with municipalities and partners. After launch, the same foundation began supporting further automation of monitoring, reporting, and additional data-source integrations.
Faxes, letters, emails, PDFs, and field comments are collected from rollout projects, analyzed by an LLM with prompt-driven extraction, stored as structured data, and then used by employees to estimate delays and coordinate follow-up actions.
"After eight weeks of close collaboration, GlasfaserPlus and Capgemini released the Gen AI solution"
"Following this automated review, the Gen AI solution extracts the most important core information and stores it in a predefined, structured format."
"The result was a solution that uses a Large Language Model (LLM) to convert unstructured data – in the form of PDF documents – into structured data."
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.
The official About page states 'ca. 180 Mitarbeiter.'
Related
Capgemini Sample Jun 9, 2026 Federal Ministry of Digitalization and State Modernization (BMDS) 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. more than six months beyond the legally defined limit Capgemini Sample May 8, 2026 Generali GC&C Generali GC&C needed to simplify a complex underwriting and operations landscape spanning CRM, document management, and multiple country processes so underwriters could work faster with better data quality and lower… 1.9 TB of content migrated from multiple countries AGORA · Dynamics 365 · Gen AI-powered assistant 
In-house Sample Dec 23, 2025 Telefónica Brasil Telefónica Brasil needed to monitor and manage electricity consumption across more than 35,000 sites nationwide, including real-time oversight of medium-voltage locations, while also handling over 35,000 monthly utility… Manual loading on databases was reduced from 5% to 1% CME (Energy Monitoring Center) · ETL tools · generative AI 