Admiral Seguros (Admiral Group, Spain) logo

Tractable AI motor claims appraisal (Admiral Seguros)

by Admiral Seguros (Admiral Group, Spain) · Primary insurer

Market unit: ES

no ratings

Admiral Seguros, the Spanish unit of the UK-based Admiral Group, uses Tractable's computer vision for straight-through motor claims, initially for its Qualitas Auto and Balumba brands. Customers photograph the vehicle damage via a web-app link at first notice of loss; the AI assesses the damage and builds a repair estimate within seconds, so a claim can move to a settlement offer without an appraiser. Admiral Seguros was announced in September 2020 as the first Spanish insurer to use AI for vehicle damage assessment. Tractable reports 12,000 touchless claims in 2021, 90% of estimates processed without appraiser input and 98% of claims completed in under 15 minutes; 70-75% of customers who receive the link complete the claim (vendor-reported).

Machine learning and predictive analyticsComputer visionMotor vehicle insurance
Compare this solution

1 free view left this month

AI capability and maturity

AI capability level

UnderstandGenerateReasonDecideActCollaborate

See more information and theoretical background

Business context

Purpose of use

Assess motor damage from customer photos and produce repair estimates so claims move from notification to settlement offer without an appraiser.

Value chain steps
Claims management
Insurance branches
Motor vehicle insurance
Application scope
Customer-facing
Business criticality
Business critical
Country or market unit
ES

Value and impact

Added value category
Cost reductionCustomer experience improvementEfficiency gain
Estimated time savings

98% of qualifying claims completed in under 15 minutes

Estimated weekly case volume
231
Quality gain

96% accuracy compared with human appraisers

Technical details

AI category
Machine learning and predictive analyticsComputer vision
Technology stack
Tractable
Interfaces used

Customer web-app link for photo upload

Architectural insights

Tractable computer vision classifies damage from smartphone photos, applies certainty scores and generates repair estimates; touchless flow from notification to settlement offer

Automation level
4/5

Compliance and governance

EU AI Act risk category
Minimal risk
EU AI Act role
Deployer
Relevant policies
EU Artificial Intelligence ActGeneral Data Protection Regulation
Data used

Customer photos of vehicle damage submitted via a web-app link

Metadata

Development type
Scaled application
Go-live date
Sep 30, 2020
License model
Software as a service

Publications over time

When this solution was reported on. Rumors are unverified mentions.

Community

Average rating

0.0 · no ratings

Comments

Log in to join the discussion.

No comments yet. Be the first to comment.

Related solutions

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.

Machine learning and predictive analyticsAnomaly detectionProperty insurance
DecideAI Development Index (ADI) 16/36
no ratings02414
Helvetia Baloise (Baloise) logo
Spitch voice assistant (Baloise Switzerland)

by Helvetia Baloise (Baloise)

CH

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.

Natural language processingConversational AIProperty insuranceMotor vehicle insurance
UnderstandAI Development Index (ADI) 16/36
no ratings02612

NiQA is an AI-driven digital assistant of UNIQA for claims reporting, documented on UNIQA's Hungarian website. It listens to the customer's description, identifies the damage type and fills in the claim form in the background, verifies incoming information in real time, analyses uploaded photos as they arrive and checks submitted documents, alerting users to missing items. It currently covers burst pipes, water damage and broken glass and is being extended to further roles; trade press names Intuitech as technology partner.

Natural language processingComputer visionProperty insurance
Understand
no ratings41620