customer_support · finance · workflow
Verisk builds PAAS AI on AWS to deliver 96–98% reduction in premium audit research time
Premium auditors using Verisk's PAAS platform struggled to find accurate information across a large repository of documents, with manual searches being time-consuming, slow, and yielding inconsistent or incomplete results.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User submits audit query
Premium auditors ask questions to quickly retrieve and summarize PAAS documents such as class guides, bulletins, and rating cards.
Tools used
ElastiCacheAmazon BedrockOpenSearchAnthropic's ClaudeClaude HaikuClaude SonnetSnowflake
Outcome
PAAS AI reduced processing time per specialist by 96–98%, transforming hours of manual review into minutes, and enabling Verisk's subject matter experts to focus on more strategic initiatives.
Results
Time saved96–98%
Volume98%
Grounding & classification
Source type: platform led case
32 fields verified against source quotes.
conversational aiknowledge searchragsentiment analysissummarizationknowledge basepolicy documenthuman review describedmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedinsurancecycle time reductionemployee productivitytime savedplatform led caseback office opscustomer supportautonomous resolutionrag answering