Document Processing · Risk Management · Security and Compliance
DXC needed to reduce insurance document backlogs and automate highly regulated underwriting and claims decisions without losing auditability, policy fidelity, or human oversight.
Reported impact
DXC cut claims-document backlogs from days to minutes, classified documents in under a second, embedded new regulatory rules in days instead of 12 to 18 months, and stood up a regulated benefits calculation in eight hours that was 80 percent right on the first pass.
DXC built Assure, an orchestration layer on the Claude Platform, to insert Claude into every layer of its insurance software portfolio. Claims submissions and policy documents arrive from email, fax, paper, phone, and OCR processes, then Claude classifies and reasons over them, including hundred-page commercial claims files. Assure keeps every action logged, traceable, and replayable for regulators, and routes work across model tiers so frontier models are reserved for the hardest files. DXC also uses Claude to encode new regulations and decision logic into purpose-built Smart Apps, such as a workers' compensation weekly earnings calculator that combines legislation, documented rules, system algorithms, and DXC calculators. Because Assure is API-driven and tied to DXC's existing platforms, carriers can connect without custom setups while keeping compliance and governance built into the flow.
Submissions and claims arrive through email, fax, paper, phone, and OCR channels, Assure routes them to Claude for classification and reasoning, Smart Apps apply insurance logic or regulatory calculations, and every action is logged so carriers and regulators can replay the decision path end to end.
Claude now runs inside every layer of it, from reading claims documents to logging every action an agent takes for regulators.
Cut claims document backlogs from days to minutes, with documents classified in under a second
The share of the calculation requiring human judgment has already dropped from 70% to 20%
The workers’ comp Smart App running on Claude was 80% right on the first pass.
We fed Claude the regulations, the legislation, documented rules, our system algorithms, and our own DXC calculators
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Google Cloud Sample Archived · Sep 17, 2026 Parsewise For risk specialists in the financial services and insurance industries, reading can feel like a full-time job. Whether assessing an insurance claim or approving a loan, these subject matter experts must search through… 29% lower error rate than best-performing LLM on grounded-reasoning benchmark Gemini · Gemini 3.0 Flash · Gemini 3.5 Flash 
AWS Sample Apr 17, 2024 Chunghwa Telecom Furthermore, Chunghwa Telecom needed a platform with robust security controls. To improve artificial intelligence (AI) data security and governance, the company migrated its generative AI projects to AWS. The first generative AI solution, the SDLC assistant, has saved developers an estimated 13 percent of their… Amazon Bedrock · Amazon Polly AWS Sample Apr 15, 2024 InfoCert Training and deploying these models was a lengthy, costly process, which limited access to this set of capabilities to larger companies. While InfoCert was searching for a way to streamline such ML integrations, AWS… Additionally, InfoCert expects to reduce financial overhead by 80 percent for startup, development, and… Amazon Bedrock 
