The Industry Landscape
The Complexity of Underwriting Research
Insurance underwriters typically have longer turnaround times for building research reports due to manual workflows and multitude of data sources. Extended validation cycles and outdated records not only delay report delivery but can also skew risk assessments.
Increasingly, advanced analytics and AI-driven interventions are re-shaping this process. They speed up information retrieval, verify data as it arrives and surface insights that were once hidden in disparate sources. By embracing these technologies within a smart framework combining real-time intelligence with human judgment, insurers can move from uncertainty and delay to swift, confident underwriting decisions.
The Client Challenge
Long Hours, Limited Coverage and Bias
The client recognized that its traditional report-building processes inhibited its ability to lead in a fast-moving market.
Operational inefficiency
Hours-long, manual research sessions sapped employee capacity and delayed critical risk insights, leaving the business a step behind emerging trends.
Cumbersome data management
The team struggled to unify data from numerous, often complex sources, creating gaps that undermined proactive risk management. Furthermore, the process relied on ad-hoc approaches that introduced unintended biases.
To sustain competitive advantage and strengthen capital efficiency, the client needed to transform its underwriting research into a streamlined function that could deliver accurate results at speed. This required more than technology; it called for a partner who could thoughtfully combine Al capabilities with domain expertise to craft a smarter, future-ready operating model.
The Solution
The Multi-agent, AI-powered SKENSE Research Assistant
Stepping in as an insurance analytics partner, WNS Analytics deployed a future-ready solution powered by our intelligent solution engineering capabilities and deep domain expertise. Leveraging SKENSE – our AI-driven data extraction and contextualization product – we implemented a sophisticated multi-agent architecture on Azure to transform the underwriting research process.
This award winning, cloud agnostic solution combined a planner agent with specialized execution agents to orchestrate goal-driven research tasks. A human-led oversight layer was integrated to guide, validate and refine AI outputs, ensuring each report met high standards of accuracy, relevance and domain-specific rigor.
SKENSE is an agentic AI-powered product that empowers organizations to tap into the potential of their unstructured data through accurate extraction and contextualization within domain-specific workflows.
Key elements of the solution:
Planner Agent for Structured Research
- The agent breaks complex underwriting queries into sequenced sub questions.
- It ensures end-to-end coverage and citation tracking.
Execution Agents for Data Extraction and Analysis
- Web-scraping agent retrieves real-time data from multiple online sources.
- Document analysis agent processes and validates PDF, HTML and text files.
- Research query agent creates research queries based on the topic of research for efficient web results.
- Summarization agent condenses findings into clear, unbiased narratives.
Citation and Validation Module
- This module embeds source references in every report.
- It applies Retrieval Augmented Generation (RAG) architecture with vector database lookup to improve factual accuracy.
User Interface and Feedback Loops
- This intuitive portal allows underwriters to submit queries and review draft reports.
- It allows continuous feedback integration for model refinement.
Key solution features
Intelligent data extraction and contextualization
AI agents capable of processing multiple document types
Gen AI-powered report generation
Cloud-agnostic and multi-hyperscaler deployment
RAG architecture with vector database
Secure, multi-agent orchestration
Seamless integration with enterprise applications like Guidewire, Salesforce and Dropbox
Adherence to organizational data policies
The Outcome
Accelerated Underwriting and Operational Efficiency
The deployment of this solution reduced cognitive overload for the underwriting teams and significantly accelerated decision making. By combining a step-wise, multi-agent AI architecture with Azure’s scalable infrastructure, our client is now equipped to drive continuous gains in predictive precision, operational agility and sustainable growth.
Key benefits included:
percent reduction in report generation time, with:
percent reduction in research costs, owing to elimination of manual data collection
percent data relevance and accuracy