SituationA Top‑Tier Insurance Company struggled to manage its $69M technology fleet. Manual plant surveys took 7–9 weeks and delivered inconsistent results (≈75% accuracy), delaying support and weakening compliance and license governance.
TaskReplace manual surveys with an automated, ML‑based “spidering” inventory engine that continuously discovers, validates, and reports on assets with high confidence at enterprise scale.
Action
  • Designed a distributed discovery engine to automatically crawl infrastructure and endpoints.
  • Applied machine learning to normalize asset signatures, remove duplicates, and flag anomalies.
  • Integrated license and configuration collection into the same pipeline for unified compliance and support data.
  • Delivered dashboards & reports for IT, Finance, and Compliance to act on in near real‑time.
Result
  • Cut survey cycle time from ~8 weeks to 2 hours.
  • Improved asset accuracy from ~75% to 99.92%.
  • Enabled proactive license tracking, compliance validation, and smoother support handoffs.
Return
  • Brought the $69M fleet under precise, auditable management.
  • Freed thousands of staff‑hours per survey cycle; reduced audit and licensing risk.
  • Improved financial control and optimized vendor spend through accurate entitlement data.
YieldTransformed asset management from a reactive, manual burden into a real‑time strategic capability—strengthening compliance, reducing operational risk, and demonstrating the tangible value of automation + ML in IT operations.
Overview