AI classification of incoming documents (ERGO)
by ERGO Group (Munich Re) · Primary insurer
Market unit: DE
ERGO Group uses AI to classify incoming customer submissions in Germany, so that documents and requests can be routed to the right processing step without manual sorting. According to ERGO's statements to procontra (November 2025), the automatic classification rate rose from 50% to over 90%, and more than 60 million document pages are processed a year. ERGO also reported about 120 AI use cases group-wide, intended among other things to absorb workload peaks such as pandemic and flu-season surges or climate-related large-loss events. Vendor, models and go-live date are not disclosed in the source.
1 free view left this month
AI capability and maturity
AI capability level
Business context
- Value chain steps
- Portfolio administrationClaims managementCustomer service
- Insurance branches
- Property insuranceSupplementary health insuranceIndividual life insurance
- Application scope
- Internal only
- Country or market unit
- DE
Value and impact
- Added value category
- Efficiency gainCost reduction
Technical details
- AI category
- Natural language processingMachine learning and predictive analytics
Compliance and governance
- EU AI Act risk category
- Minimal risk
- EU AI Act role
- Deployer
- Relevant policies
- EU Artificial Intelligence ActGeneral Data Protection Regulation
Metadata
- Development type
- Scaled application
Publications over time
When this solution was reported on. Rumors are unverified mentions.
Community
Average rating
Comments
Log in to join the discussion.
No comments yet. Be the first to comment.
Related solutions
Swiss Re applies AI to review and manage contract wordings across its in-force reinsurance business, led by Group Underwriting's Contracts & Wordings Services and P&C Reinsurance underwriting. An existing Swiss Re application combines keyword search with conversational AI so that underwriters and contract specialists can query large contract volumes, while GenAI-enabled analytics identify wording patterns, accumulations and discrepancies across portfolios. Swiss Re stated in June 2026 that these capabilities are being introduced incrementally into production and are still at an early stage. No metrics are published beyond the baseline that a 2020 COVID-19 wording review of tens of thousands of contracts took about 45 days. Underwriters remain responsible for interpretation and decisions.
ZFinder is a fraud-detection model developed in-house by Zurich Seguros (Spain) that combines big data and machine learning, comparing each claim with thousands of similar claims and improving with every analysis. Zurich applied it first to home insurance (announced June 2018), with plans to extend it to other lines under the supervision of its internal investigation team. Zurich reported that automatic fraud detection doubled after launch and that in 76% of claims investigated via ZFinder a loss adjuster's work was not essential. The most common fraud types it found were simulated claims (47%), claims for excluded cover (22%) and concealed pre-existing damage (17%). No newer figures were found.
Since September 2021 Baloise has used a virtual voice assistant, developed with Spitch and NTT DATA, in its Swiss non-life customer service. Callers state their concern in standard German or Swiss German dialect instead of using the phone menu; the assistant recognises the intent, mainly claims notifications, and transfers the call with an on-screen text summary for the agent. At launch about 40% of German-language non-life enquiries passed through the assistant and 85% of callers reached the right expert at the first attempt; French was planned for a later stage. Spitch's case study (updated April 2025) describes a hybrid on-premise and cloud setup. Status after the December 2025 Helvetia Baloise merger is not documented.