Document Agents
Understand documents through real language comprehension. Recognition of type, content, and context – not template matching. Every extraction verified through the Decision Layer.
Document Agents in detailOn your infrastructure. Under your control.
Germany combines three properties that exist together in no other EU country: maximum corporate density across multiple sectors, a binding works council co-determination right under Section 87(1) No. 6 of the Works Constitution Act, and a federal supervisory structure with BaFin, BSI, BfDI and sixteen additional state data protection authorities. The corporate landscape reaches from automotive (VW, BMW, Daimler, Porsche, Continental, Bosch, ZF) to chemicals (BASF, Bayer, Evonik, Merck, Covestro), machinery (Siemens, Trumpf, Durr, Kuka, Festo), banking (Deutsche Bank, Commerzbank, the Sparkassen, the cooperative Volks- und Raiffeisenbanken), insurance (Allianz, Munich Re, Ergo, HDI, R+V), energy (RWE, E.ON, EnBW) and retail (Otto, Zalando, Lidl/Kaufland, Rewe, Edeka). Gosign is part of this market with headquarters in Hamburg and an office in Berlin - and the architecture is built precisely for it.
First, the Works Constitution Act: Section 87(1) No. 6 BetrVG gives the works council a co-determination right over the deployment of technical systems that can monitor employee behaviour or performance. AI systems in HR, in shift planning, in performance analytics, in service-desk routing - all fall inside its scope. A productive deployment without a works agreement is not legally defensible in German corporate groups. The Decision Layer with enforced Human-in-the-Loop is therefore not an architectural feature here, but the precondition for works council approval.
Second, GDPR together with the BDSG and the federal data protection supervision: BfDI at federal level, plus sixteen state data protection commissioners, plus the specifics of the Federal Data Protection Act. For automated decision-making in the sense of Article 22 GDPR, German data protection authorities expect documented legal bases, retrievable explanations, and a complete Audit Trail. The German specificity: the Data Protection Impact Assessment must be completed before go-live for high-risk applications, not in parallel with the rollout.
Third, BaFin, BSI, BNetzA and the EU AI Act: BaFin supervises the financial sector and expects a demonstrable human final decision on risk cases in AML, KYC, credit scoring and claims handling. BSI defines the minimum IT security requirements for KRITIS enterprises. The EU AI Act is being implemented in Germany through the forthcoming Act on the Execution of the AI Regulation - with a focus on high-risk applications in HR, banking, insurance and critical infrastructure. Starting without Cert-Ready by Design means building on an architecture that will need to be retrofitted no later than the first BaFin audit.
Allianz and Munich Re claims handling: the German insurance leaders process thousands of claims a day. Workflow Agents classify inbound cases by tariff, region and complexity, the Decision Layer routes risk cases to human case managers, and the Audit Trail documents every decision for internal audit and BaFin inspections.
Commerzbank and the Sparkassen AML operations: across millions of transactions per day, Document Agents check identification markers, the Decision Layer routes suspicious cases along the BaFin thresholds, with Human-in-the-Loop on every final escalation.
VW, BMW and Daimler HR operations: German automotive groups have hundreds of thousands of employees and correspondingly complex HR processes. Workflow Agents support recruiting and internal mobility, with enforced human final decisions on personnel measures - a mandatory precondition for works council acceptance under Section 87 BetrVG.
BASF and Bayer production documentation: German chemicals groups generate enormous volumes of safety and quality documentation daily. Document Agents extract regulatorily relevant specifications and reconcile them against REACH, CLP and CE requirements, with a complete Audit Trail back to the source record.
Gosign is headquartered in Hamburg (Hallerstrasse 8) with an office in Berlin (Nogatstrasse 46) and a training centre in Hamburg at Grindelberg 77. Discovery workshops happen on site at client locations - in Munich, Frankfurt, Stuttgart, Dusseldorf, Cologne, Hanover or directly in Hamburg and Berlin. The build then runs remote with German-language documentation, weekly sprint reviews over video, a dedicated point of contact, and on-site visits every four to six weeks. Meetings with the works council, data protection officer and compliance functions are standing items in every project. On-site meetings with BaFin, BSI or state data protection authorities are supported on request jointly with internal legal.
Germany is not the easiest but the hardest EU market for Enterprise AI compliance. That is precisely what makes it the best starting point. An AI agent that satisfies GDPR, BDSG, BetrVG, BaFin and BSI requirements plus the EU AI Act has been built on an architecture that is only a configuration change away from any other EU country. German compliance culture and works council co-determination enforce Governance by Design - no other EU country demands this with the same consistency.
For DAX groups, MDAX companies and the German Mittelstand with 200 or more employees, this discipline is not a burden but a competitive advantage: what goes productive in Germany goes productive in the EU. An architecture that satisfies BaFin also satisfies the Dutch DNB, the Austrian FMA and the French ACPR. A solution aligned with the works council of a German industrial group can be negotiated with the Rada Zakladowa in Poland, the Comite de Empresa in Spain and the CSE in France without a fundamental re-build. As a Hamburg company, Gosign is part of this market - the architecture is not born from a textbook but from projects inside German corporate groups whose audit expectations shaped every first productive day. Cert-Ready by Design is not a sales argument here but a structural necessity. More context on the EU AI Act and the German implementation is in the Governance area.
Not because of technology – but because of missing governance. Without clear rules defining who makes which decision, every AI agent stays a pilot project.
That is why we build every agent exclusively with a Decision Layer. It breaks down every business process into individual decision steps and defines for each step: human, rule engine, or AI. No agent goes into production without this layer.
Understand documents through real language comprehension. Recognition of type, content, and context – not template matching. Every extraction verified through the Decision Layer.
Document Agents in detailSteer business processes across multiple systems and decision points. One agent, complete orchestration. Every step in the audit trail.
HR AI AgentsAnswer questions from enterprise knowledge – with source reference, rule version, and validity date. No verified source, no answer.
Knowledge Agents in detailAuditable. Compliant. Enterprise-grade.
Human-in-the-Loop architecturally enforced – not optional
Complete audit trail for every agent decision
GDPR compliant by design – all data on your infrastructure
Works council compatible – agreements as constraints in the Decision Layer
EU AI Act compliant by design – transparency, explainability, human oversight
Model-agnostic – no vendor lock-in, you own the source code
1 week
Process analysis, understand rule sets, prioritise use cases.
3–4 weeks
Productive PoC. One agent, one process, live on your infrastructure.
Continuous
More agents, more processes. Same governance, same auditability.
After 12–18 months, you operate your agents independently. Source code, prompts, and rule sets are yours.
Analysis and insights on enterprise AI, governance, and agent architecture.
Most AI projects fail not because of technology but because nobody defined the rules. Why the operating model matters more than the language model.
The EU AI Act directly affects HR processes. Risk classification, bias monitoring, human oversight - what is now mandatory and how to prepare.
Agent governance is not an IT topic. It's an HR leadership topic. What CHROs need to know before AI agents enter core HR processes.
“Even as a global market leader, you want to keep moving forward. It is reassuring to have the technological expertise and infrastructure experience of Gosign on our side.”
Head of Innovation, Sony Music Entertainment
“Gosign is not just about speed. It's about how much essential work happens in this time.”
Head of Customer Service & Technical Support, Libri GmbH
Headquarters Hamburg (Hallerstrasse 8), office Berlin (Nogatstrasse 46), training centre Hamburg (Grindelberg 77). Clients in Munich, Frankfurt, Stuttgart, Dusseldorf, Cologne, and Hanover are served with dedicated project management.
Yes. The works council (Betriebsrat) holds co-determination (Mitbestimmung) rights under Section 87(1) No. 6 of the Works Constitution Act for the deployment of technical systems. The Decision Layer with Human-in-the-Loop architecturally enforces human review for decisions subject to co-determination.
GDPR-compliant by design. All data remains on your infrastructure. No data transfer to third parties. The EU AI Act adds requirements for transparency and human oversight.
4-6 weeks. Discovery: 1 week. Build: 3-4 weeks. On your infrastructure.
Talk to us about a specific use case in your organisation.
Schedule a consultation