How a multiline U.S. property and casualty insurer evaluated OwlVision across Auto, General Liability, Property, Professional, and Surety claims.

Claims professionals often need to review extensive documentation, reconcile information across multiple sources, and translate their findings into structured reports. The time required can vary significantly depending on the line of business, claim complexity, and the adjuster’s familiarity with the file.

To evaluate how AI could support these workflows, a multiline U.S. property and casualty insurer conducted a 45-day proof of concept (POC) with OwlVision across five lines of business: Auto, General Liability, Property, Professional, and Surety.

The POC focused on practical claims workflows, including claim ingestion, claim summaries and insights, Large Loss Report (LLR) generation, and the use of OwlAssist for conversational claim review.

The pilot began in July 2026, with final feedback sessions completed in August. Approximately two to three claims from each line of business were included.

Throughout the POC, Owl worked directly with claims professionals from each line, conducting multiple feedback sessions to review results, gather input, demonstrate enhancements, and evaluate OwlVision against existing claim review processes.

The evaluation focused on four core capabilities:

• Manual claim ingestion
• Claim summaries and insights
• Large Loss Report generation
• OwlAssist

Rather than applying the same output across every claim type, the POC also evaluated how OwlVision could adapt summaries, timelines, templates, and insights to the requirements of individual lines of business.

Large Loss Report preparation emerged as one of the clearest areas of impact during the POC.

Across the claims tested, OwlVision consistently generated approximately 70–80% of the required LLR content, including key claim information such as claim number, date of loss, and policy information.

The remaining work stayed with the claims professional for review, judgment, editing, and required language.

Reviewers also compared OwlVision-generated LLRs with the time typically required to prepare these reports manually. Their in-session estimates showed different levels of potential time savings depending on the line and complexity of the claim.

Across the five lines of business, estimated time savings varied based on the existing process and claim complexity. General Liability professionals estimated approximately four hours saved per report, compared with a typical manual process of three to six hours, or seven to ten hours for complex cases. Surety reviewers estimated an approximately 50% efficiency gain against a six-to-eight-hour manual process, while Property reviewers estimated approximately 50% savings, reducing about one hour of work to roughly 30 minutes. Auto reviewers estimated an approximately 25% efficiency gain. For Professional claims, estimated savings ranged from one to two hours on familiar files to as much as seven to ten hours on inherited or unfamiliar files.

These estimates were provided by participating claims professionals during live POC sessions based on comparisons with their existing manual processes.

One General Liability claims professional described the generated report this way:

“I like the LLR. I think it definitely provides the nuts and bolts... the necessary information that the adjuster would need... the editing is probably gonna be minimal.”

The POC also demonstrated that claim review requirements differ significantly by line of business.

Rather than relying on a single generic claim structure, OwlVision generated line-specific timelines and outputs based on the type of claim being reviewed.

For example, Surety claims included a tailored Bond Timeline, while Professional claims demonstrated the generation of an additional Coverage Analysis Summary Table using DICE Analysis.

As new documentation was added to a claim, OwlVision could ingest the additional information and update the relevant claim summary, timeline, and templates.

This allowed POC participants to evaluate the platform using evolving claim files rather than only static document sets.

Beyond summarization and report generation, OwlVision was evaluated on its ability to identify information within claim files that warranted additional attention.

Each insight included citations to the underlying source documentation so claims professionals could validate the information directly against the claim file.

Examples from the POC included:

General Liability: OwlVision identified contradictory information within claimant accounts, including differences in the reported duration of loss of consciousness.

Professional: The platform identified inconsistencies across property documentation where the same property was listed at different values.

Auto: OwlVision highlighted differences between the parties’ descriptions of an alleged incident, making the conflicting accounts easier to compare.

Surety: The platform provided a breakdown of unpaid subcontractor and supplier claims to help reviewers assess outstanding exposure.

Property: OwlVision identified a discrepancy between the occupancy status stated in the policy declarations and information documented elsewhere in the claim.

These examples varied by line, reflecting the different questions and information claims professionals needed to evaluate within each type of file.

Participants also tested OwlAssist, Owl’s conversational AI capability, throughout the POC.

As the pilot progressed, users increasingly incorporated OwlAssist into their claim review process, asking specific questions about policy information, claim chronology, reporting timelines, correspondence, and medical information.

Examples of questions asked during the POC included:

• “How much is the liability deductible?”
• “Where can I find the insured vehicle on the policy schedule?”
• “How much time between the date of loss and the date the claim was reported?”
• “How quickly were acknowledgment letters sent out in response to the claims?”
• “What was the first date the claimant complained of neck pain?”

The questions illustrate how users moved beyond general summarization and used OwlAssist to locate specific information within the claim documentation.

Feedback was gathered throughout the 45-day pilot as users worked with OwlVision across different claim types.

One Auto claims professional highlighted the value of the claim summary when approaching a file:

“My testing's been very comfortable with the platform. I like the claim summarization... it gives me as an adjuster kind of an efficient way to understand the current file posture.”

Another participant evaluating the platform on Professional claims summarized the experience simply:

“I thought it was a solid A.”

The feedback sessions also provided opportunities for users to identify workflow preferences and areas for refinement, which were incorporated into the evaluation throughout the POC.

Across five lines of business, the 45-day POC evaluated OwlVision against real claim files and existing claims workflows.

The results showed that OwlVision could generate approximately 70–80% of required Large Loss Report content for the claims tested, while claims professionals reported estimated time savings ranging from approximately 25% in Auto to around 50% in Property and Surety, with potentially greater savings in specific complex or unfamiliar-file scenarios.

The POC also demonstrated the ability to generate line-specific timelines and templates, update outputs as additional documentation was ingested, surface discrepancies with citations back to source documents, and support direct claim-file questions through OwlAssist.

Importantly, the workflow maintained the claims professional’s role in reviewing the generated information, applying judgment, making necessary edits, and completing required language.

For the participating teams, the POC provided a practical evaluation of how AI-assisted claim review could fit within existing workflows across multiple lines of business.