A specialty insurer wanted to speed up underwriting decisions but had already spent two years and a substantial budget on a core system replacement project that had stalled, leaving leadership wary of any solution requiring another system overhaul.
Building a Multi-Agent Underwriting Assistant Without Ripping Out the Core System
Service Provided
Capabilities Utilized
Agentic Architecture, Legacy Integration, Underwriting Workflow Design
Client challenge
The underwriting team’s existing policy administration system worked, but pulling together the risk data, loss history, and comparable-policy information needed for a single underwriting decision meant navigating four separate applications by hand — a process taking underwriters 45 minutes to an hour per submission.
Our solution
We designed a multi-agent assistant that sits on top of the existing systems rather than replacing any of them: one agent gathers and normalizes risk data, a second retrieves comparable historical policies and loss experience, and a third assembles everything into a structured underwriting brief with a recommended pricing range. The underwriter makes the final call — the system’s job is to eliminate the manual data-gathering, not the underwriting judgment itself.
Because no core system was touched, the assistant went from design to pilot in ten weeks, avoiding the lengthy procurement and validation cycle a system replacement would have required.
Results
Average time-to-brief for a new submission dropped from roughly 50 minutes to 7 minutes, letting underwriters more than double the number of submissions they could evaluate per day. Quote turnaround time for brokers improved from an average of 3.2 days to same-day for standard risk profiles, contributing to a measurable uptick in bound policies from brokers who had previously deprioritized submissions due to slow turnaround.
Additional Case Studies
Launching a Usage-Based Pricing Model for an AI Developer Platform
An AI developer platform’s flat-tier pricing was leaving money on the table with its largest customers
Establishing an Enterprise AI PMO to Track ROI Across 30 Initiatives
A global enterprise had 30 active AI initiatives across its business units but no consistent way
Building the Product Operating Model for an Agentic SaaS Vendor
A vertical SaaS vendor had shipped an early agentic feature that could autonomously complete customer workflows,
