DEU-001

KIRA (AI for Risk-Based Employer Audits)

Download PDF
Germany Europe & Central Asia High income Pilot / Controlled Trial Phase Confirmed

Deutsche Rentenversicherung Bund (DRV Bund)

At a Glance

What it does Anomaly and change detection — Compliance and integrity
Who runs it Deutsche Rentenversicherung Bund (DRV Bund)
Programme KIRA (AI for Risk-Based Employer Audits)
Confidence Confirmed
Deployment Status Pilot / Controlled Trial Phase
Key Risks Model-related risks
Key Outcomes Expected / early-reported: more efficient screening of large data volumes, better targeting of audit focus and potential increase in detection of irregularities.
Source Quality 6 sources — Government website / press release, Report (multilateral / development partner), News article / media

KIRA — Künstliche Intelligenz für risikoorientierte Arbeitgeberprüfungen (Artificial Intelligence for Risk-Oriented Employer Audits) — is an AI-based decision-support system developed by Deutsche Rentenversicherung Bund (DRV Bund), Germany's federal pension insurance agency, to assist auditors in conducting statutory employer audits (Betriebsprüfungen). The system represents DRV Bund's first operational deployment of artificial intelligence and was developed with funding from the Bundesministerium für Arbeit und Soziales (BMAS), the German Federal Ministry of Labour and Social Affairs.

Germany's social insurance system requires that all employers correctly calculate and remit contributions for pension, unemployment, health, and long-term care insurance on behalf of their employees. The Betriebsprüfdienst (employer audit service) of Deutsche Rentenversicherung is legally mandated to verify employer compliance, with each business subject to an audit every four years. This results in approximately 400,000 employer audits per year, conducted by roughly 1,700 audit staff. On average, auditors have less than one day per audit to review the full body of documentation for a given employer, forcing them to rely on experience-based sampling and ad hoc prioritisation of audit focus areas. The demographic transition and growing skills shortages in Germany's public sector are expected to further strain this capacity in coming years. Annual back-payment demands resulting from audits already run into the high hundreds of millions of euros, underscoring the fiscal significance of the audit function.

KIRA addresses this capacity challenge by scanning all digitally available employer data — including payroll records, contribution filings, and data submitted through the electronically supported audit process (elektronisch unterstützte Betriebsprüfung, euBP) — to identify anomalous patterns, irregularities, and outliers. The system searches for unusual contribution levels (both unusually high and unusually low), missing documentation, inconsistent payroll patterns, and other indicators that may signal errors, non-compliance, or potential fraud such as bogus self-employment (Scheinselbständigkeit). Based on these analyses, KIRA generates risk scores on a criticality scale of 1 to 10 for each employer case, ranking them by likelihood and severity of irregularity. These scores help auditors decide which cases can be processed quickly and where the time saved should be reinvested into deeper, more thorough examination. KIRA also marks the specific locations within employer documentation where anomalies have been identified, directing auditors to the most relevant sections.

The underlying model is a traditional (classical) machine learning system trained on anonymised historical data from previous employer audits, including structured employer records, contribution data, and prior audit outcomes. The 2025 ISSA TechByte appendix adds concrete implementation detail that was not present in the earlier public-facing DRV pages: DRV's stack includes Python tooling such as Kedro, PyTorch, TensorFlow, SciPy, scikit-learn, Random Forest and XGBoost, with Angular/Node.js interfaces, Oracle/SQL data infrastructure, and Apache web services. The data are anonymised before model training to comply with data protection requirements, and the TechByte notes that extensive preparatory work was required to create an anonymised database and secure the internal development environment. All data remain within the DRV pension insurance network infrastructure and do not leave this closed system, ensuring domestic data residency. The model is continuously refined based on feedback from auditors who assess the quality and relevance of KIRA's flagged anomalies, creating an iterative improvement loop.

A core design principle of KIRA is human-in-the-loop oversight. The system provides risk scores and indications, but DRV auditors retain full decision-making authority and perform all legal assessments. KIRA does not make binding determinations about employer compliance, assess penalties, or issue enforcement actions. The auditor decides whether and how to act on the information KIRA provides. This design ensures that the AI serves as a prioritisation and decision-support tool rather than an autonomous decision-maker.

DRV Bund began testing KIRA in January 2025 within the audit service in a controlled pilot phase. The full-scale, nationwide rollout is planned for 2026. According to DRV Bund, employers should not experience any direct change in the audit process as a result of KIRA's deployment — other than that audits may be completed more quickly. However, independent professional advisory firms including EY and Grant Thornton have noted that KIRA is likely to increase the detection risk for employers with compliance issues, and have recommended that employers proactively ensure their social insurance contribution processes are up to date and compliant. EY has specifically noted the heightened risk of detecting bogus self-employment arrangements.

The project received significant institutional recognition in September 2024, when DRV Bund won both the first prize and the public choice award at the 23rd eGovernment-Wettbewerb (eGovernment Competition) in the category 'Digitalisierungsschub durch KI und moderne Infrastruktur' (Digitalisation Push through AI and Modern Infrastructure). This award recognises innovative digital transformation projects in the German public sector and confirms the project's maturity and institutional support.

The TechByte appendix also clarifies the development model more precisely than the earlier public materials: technically, DRV relied heavily on an external development partner while building internal know-how, and the project required sustained coordination with IT security, data protection, staff representatives, accessibility specialists, and business-domain experts. KIRA still fits a sovereign-AI pattern in operational terms because model hosting and data remain inside the German public pension-insurance environment, but it was not a purely in-house build from the outset.

Expected and early-reported outcomes include more efficient screening of large data volumes, better targeting of audit focus areas, and potential increases in the detection of contribution irregularities. The TechByte appendix reports self-declared early KPIs that are materially stronger than the earlier public sources: approximately 50 per cent of audit cases can be deprioritised as inconspicuous, while the missed financial impact from incorrect classification is reported at less than 1 per cent. These are institutional self-reports rather than independent evaluations, so they strengthen the case for operational maturity but do not eliminate the need for external validation.

Classifications follow the DCI AI Hub Taxonomy. Hover over field labels for definitions.

Social Protection Functions

Implementation/delivery chain
Accountability mechanisms primaryManagement of contributions and withdrawals
SP Pillar (Primary) The social protection branch: social assistance, social insurance, or labour market programmes. Social insurance
Programme Name KIRA (AI for Risk-Based Employer Audits)
Programme Type The type of social protection programme, classified under social assistance, social insurance, or labour market programmes. View in glossary Old age, survivors and disability pensions
System Level Where in the social protection system the AI is applied: policy level, programme design, or implementation/delivery chain. View in glossary Implementation/delivery chain
Programme Description Statutory social insurance employer audits (Betriebsprüfung) conducted by Deutsche Rentenversicherung Bund. DRV auditors verify that employers correctly calculate and remit social insurance contributions (pension, unemployment, health, and long-term care insurance). KIRA uses AI to scan digitally available employer data, identify anomalous contribution and payroll patterns, and generate risk scores to help auditors prioritise cases and focus their reviews, addressing the challenge of approximately 400,000 audits per year with limited staff.
Implementation Type How the AI output is produced: Classical ML, Deep learning, Foundation model, or Hybrid. Affects validation, compute requirements, and governance profile. View in glossary Classical ML
Lifecycle Stage Current stage in the AI lifecycle, from problem identification through to monitoring, maintenance and decommissioning. View in glossary Integration and Deployment
Model Provenance Origin of the AI model: developed in-house, adapted from open-source, commercial/proprietary, or accessed via third-party API. View in glossary Developed in-house
Compute Environment Where the AI system runs: on-premise, government cloud, commercial cloud, or edge/device. View in glossary On-premise
Sovereignty Quadrant Classification of data and compute sovereignty: I (Sovereign), II (Federated/Hybrid), III (Cloud with safeguards), or IV (Shared Innovation Zone). View in glossary I — Sovereign AI Zone
Data Residency Where the data used by the AI system is stored: domestic, regional, or international. View in glossary Domestic
Cross-Border Transfer Whether data crosses national borders, and if so, whether documented safeguards are in place. View in glossary None
Decision Criticality The rights impact of the decision the AI supports. High criticality requires HITL oversight; moderate requires HOTL; low may operate HOOTL. View in glossary Moderate
Human Oversight Type Level of human involvement: Human-in-the-Loop (active review), Human-on-the-Loop (monitoring), or Human-out-of-the-Loop (periodic audit). View in glossary HITL
Development Process Whether the AI system was developed fully in-house, through a mix of in-house and third-party, or fully by an external provider. View in glossary Mix of in-house and third-party
Highest Risk Category The most significant structural risk source identified: data, model, operational, governance, or market/sovereignty risks. View in glossary Model-related risks
Risk Assessment Status Whether a formal risk assessment, informal assessment, or independent audit has been conducted for this system. Informal assessment

Risk Dimensions

Operational and system integration risks

Impact Dimensions

Autonomy, human dignity and due process
  • Data minimisation controls
  • Human oversight protocol
CategorySensitivityCross-System LinkageAvailabilityKey Constraints
Administrative data from other sectorsSpecial categoryLinks data across multiple systemsCurrently available and usedAnonymised before model training; data remain within DRV / pension-insurance network infrastructure; subject to German Federal Data Protection Act (BDSG) and GDPR; cooperation with data-protection officers required
Financial and payments data: programme operationsSpecial categoryLinks data across multiple systemsCurrently available and usedAnonymised before model training; data remain within DRV / pension-insurance network infrastructure; subject to German Federal Data Protection Act (BDSG) and GDPR; cooperation with data-protection officers required

Deutsche Rentenversicherung (2024) 'KIRA — Künstliche Intelligenz für risikoorientierte Arbeitgeberprüfungen', summa summarum Lexikon. Available at: https://www.deutsche-rentenversicherung.de/DRV/DE/Experten/Arbeitgeber-und-Steuerberater/summa-summarum/Lexikon/K/kira.html (Accessed: 19 March 2026).

View source Government website / press release

Deutsche Rentenversicherung Bund (2024) Künstliche Intelligenz entlastet Mitarbeitende und schützt das Sozialversicherungssystem — KIRA Digitalstrategie. Available at: https://www.deutsche-rentenversicherung.de/Bund/DE/Ueber-uns/Digitalstrategie/KIRA.html (Accessed: 19 March 2026).

View source Government website / press release

Deutsche Rentenversicherung Bund (2024) 'DRV Bund gewinnt eGovernment-Wettbewerb für KI-Projekt', Pressemitteilung, 6 September. Available at: https://www.deutsche-rentenversicherung.de/Bund/DE/Presse/Pressemitteilungen/pressemitteilungen_aktuell/2024/2024-09-06-eGovernment-Preis-Kira.html (Accessed: 19 March 2026).

View source Government website / press release

International Social Security Association (ISSA) (2025). AI applications in social security: Building evidence and insights from the TechByte. Geneva: ISSA. Available at: https://www.issa.int/node/281122 (Accessed: 30 March 2026).

View source Report (multilateral / development partner)

Grant Thornton Deutschland (2024) 'KI für die DRV-Betriebsprüfung: Wie KIRA ab 2025 Prozesse optimiert', Grant Thornton Themen. Available at: https://www.grantthornton.de/themen/2024/ki-fuer-die-drv-betriebspruefung-wie-kira-ab-2025-prozesse-optimiert/ (Accessed: 19 March 2026).

View source News article / media

Adam, N. (2024) 'DRV: Betriebsprüfung mit KI(RA)', EY Deutschland — News zum internationalen Mitarbeitereinsatz, 5 November 2024. Available at: https://www.ey.com/de_de/technical/news-zum-internationalen-mitarbeitereinsatz/drv-betriebspruefung-mit-kira (Accessed: 19 March 2026).

View source News article / media
Deployment Status How far the system has progressed into real-world operational use, from concept/exploration through to scaled and institutionalised. View in glossary Pilot / Controlled Trial Phase
Year Initiated The year the AI system was first initiated or development began. 2025
Scale / Coverage The scale and geographic or population coverage of the deployment. National — approximately 400,000 employer audits per year across Germany (pre-production)
Funding Source The source(s) of funding for the AI system development and deployment. Bundesministerium für Arbeit und Soziales (BMAS) — German Federal Ministry of Labour and Social Affairs
Technical Partners External technology vendors, academic partners, or development partners involved. DRV Bund within a BMAS-funded project, with heavy external development support according to the ISSA TechByte appendix; specific partner name not disclosed in public-facing retained sources
Outcomes / Results Expected / early-reported: more efficient screening of large data volumes, better targeting of audit focus and potential increase in detection of irregularities. The 2025 ISSA TechByte appendix reports self-declared early KPIs that around 50% of audit cases can be deprioritised as inconspicuous and that missed financial impact from incorrect classification is below 1%. Full independent impact evaluation not yet published.

How to Cite

DCI AI Hub (2026). 'KIRA (AI for Risk-Based Employer Audits)', AI Hub AI Tracker, case DEU-001. Digital Convergence Initiative. Available at: https://socialprotectionai.org/use-case/DEU-001 [Accessed: 1 April 2026].

Change History

Created 30 Mar 2026, 08:38
by v2-import (import)