Challenge
Evaluating a secondary loan portfolio meant manually building investment-committee-ready company pages across 50-100+ borrowers per deal, pulling from loan tapes, memos, and call notes with no unified data layer — capping the firm's total throughput at roughly 300 applications a year.
Solution
Nimble Gravity built a unified data platform on Microsoft Fabric paired with an agentic pipeline — running on Azure AI Foundry with a deployed Claude model for the strongest performance on analyzing and summarizing the portfolio of companies — that classifies, extracts, and validates deal data, then drafts fully-cited company pages with analysts in the loop.
Results
60-70% less analyst effort per portfolio
freeing time for judgment, not data assembly
3.3x more deal throughput targeted
from ~300 to 1,000+ portfolio applications reviewed each year, with no added headcount
85%+ extraction accuracy, analyst-verified
validated across 100+ production runs, with full issuer identification before any figure reaches the Investment Committee
Now expanding beyond Credit Secondaries
into Private and Liquid Credit
