AI for photo based damage assessment in insurance claims

Ping An uses its own computer vision technology to assess vehicle damage from images and video in its auto insurance claims. The group says this image based damage assessment cuts claims processing from hours to minutes, and reports 95% accuracy for its vehicle damage video assessment tools. Ping An presents the capability as part of a wider proprietary AI portfolio across insurance, healthcare and finance, alongside voiceprint identity checks and NLU voice robots for customer service.

ZhongAn Insurance published its 2025 claims service annual report, describing how it built AI into the whole claims chain. In health insurance, more than 45% of claims are reviewed and closed automatically. In motor insurance, the "ZhongAn Auto Insurance" mini program combines an NFC emergency service, video claims review and "motor insurance AI damage assessment", which together cut the time to settle claims under 10,000 yuan to as little as 13.3 minutes, with damage assessment taking as little as 116 seconds. The company also uses large and smaller specialised models to automate image diagnosis, liability decisions and medical record extraction in pet and accident insurance, and AI image recognition, voice analysis and automated review against organised insurance fraud.

In multiple countries where it operates, MAPFRE collaborates with ControlExpert on a deep learning algorithm that automatically verifies car damage in real time from photos taken when a policyholder takes out a motor policy. MAPFRE's global head of innovation, Miguel Ángel Rodríguez Cobos, names this among the company's uses of AI: detecting damage in images of vehicles when a policy is taken out, and throughout the claims process. No quantified accuracy, time saving or cost outcome for this specific use is disclosed.

Covéa, the French mutual group behind the MAAF, MMA and GMF brands, has used Tractable's AI since 2018 to analyse photos of vehicle damage in real time, so that its partner repairers receive instant assessments instead of waiting on administrative steps after an accident. In April 2026 the two renewed the partnership for three years. Covéa's head of the auto networks division says more than 160,000 claims have been finalized since the collaboration began.

Foyer, a Luxembourg insurer, announced in May 2026 that it has formalised a partnership with Tractable to identify damage automatically from photographs for minor motor incidents. The aim is immediate analysis of the damage the policyholder reports, faster handling of the simplest claims and fewer visits to the garage. No outcome figures were published.

Porto Seguro launched a technology based vehicle inspection in the Porto app at the end of 2025, in which the customer records a guided 360 degree video and photos of the car. An AI model analyzes the images to assess the vehicle's condition in the prior inspection and, for claims, the damage or theft reported, combining that with policy data to accept, decline or request a small repair. With the AI, the claims analysis time fell from four to seven days to one to two days, and four of the seven main processes in the claims area are now integrated with AI.

Tokio Marine & Nichido Fire Insurance uses Shift Technology's claims intake and claims fraud detection solutions, extended with generative AI that extracts data from structured and unstructured sources such as images and documents. The system highlights the points handlers should check for consistency across estimates, damage photos and claim statements, which makes reviews more efficient and more standardized, including during the surge of claims after large disasters, and it helps detect suspicious claims, which tend to rise after such events. No figures were published.

In March 2022 Tractable and PZU, Poland's largest insurer, announced that policyholders can submit smartphone photos of car damage when they report an accident. Tractable's AI assesses the damage and calculates the repair cost, the claim handler can share the result within minutes, and the policyholder can accept a cash settlement instead of waiting days. PZU had worked with Tractable since 2017 and already used its AI to check how body shops carry out repairs, processing several hundred thousand claims with its AI based tools. No outcome figures for the photo journey were published.

Admiral Seguros, the Spanish business of Admiral Group, sends motor claimants a link to a web app in which they photograph the damage, and Tractable's AI produces the repair estimate within minutes. Tractable reports that Admiral Seguros processed 12,000 touchless claims this way in 2021, that 90% of claim estimates were processed without human appraisers and that 98% of claims were completed in less than 15 minutes.

Sompo Japan, one of Japan's leading property and casualty insurers, announced in August 2021 that it would become the first insurer in the Japanese market to use AI to calculate approximate vehicle repair costs. The AI Estimating solution analyses photos of accident damage submitted through a policyholder's smartphone and quickly calculates an approximate repair cost, so customers can decide how to take their claim forward. Sompo planned to launch the solution in Japan in October 2021 after successful trials.

Ageas, a UK motor insurer, uses Tractable's AI to support the tasks a human assessor would normally carry out when evaluating vehicle damage: identifying which parts are affected, and generating a full repair, paint and labour estimate. Policyholders submit photos by smartphone when they report an accident and can receive next steps within minutes, even during the initial call to the insurer. After successful UK trials in 2019, Ageas and Tractable announced in March 2020 that they would scale the technology to resolve thousands of claims every month.

Warta, one of Poland's largest insurers and part of the Talanx Group, uses Tractable's computer vision to visually check how every claim across its Polish repair network is repaired, after a 2019 pilot and full deployment from early 2020. Previously Warta could only send a portion of claims for manual visual review before repairs could begin; the AI now checks all of them in real time, approving cases without anomalies immediately and flagging anomalies to engineers with the supporting photos.