Case Study

How Socotra Capital Is Doubling Deal Capacity Using a Custom AI Agent on Microsoft Copilot Studio

Who They Are

Socotra Capital is a Sacramento-based private money lender that raises funds from individual investors and deploys that capital as loans backed by real estate—helping developers, investors, and business owners who can’t get traditional bank financing to acquire, rehabilitate, and reposition properties.

What They Needed

Socotra Capital wanted to scale deal volume significantly without a proportional increase in headcount. To get there, they needed a way to reduce the time their loan committee spent manually gathering and reviewing information for each deal—while keeping sensitive borrower data secure on enterprise-grade infrastructure.

The Roadblock

Every morning, Socotra Capital’s loan committee met to review anywhere from five to fifteen deals—each requiring manual research across three streams of information: borrower documents, publicly available web data, and gated property data. Depending on complexity, a single deal could consume 45 minutes of committee time. Without a consistent process, critical red flags could go unnoticed until late in the process.

The Game Plan

Socotra Capital partnered with Convverge on a nine-month build to create “Agent PAT”—a custom AI agent built on Microsoft Copilot Studio. The agent runs three times per deal:

Pre-Committee Review: Catches red flags before a deal reaches the committee, removing problem deals before anyone has invested significant time.
Loan Committee Meeting: Generates an eight-page document pulling all three data sources, with colour-coded risk indicators, linked source documents, and a direct link to the property on Google Maps.
Final Approval: Produces the official approval document, which can also be shared with potential buyers if the loan is later sold.

Built on Microsoft Copilot Studio‘s enterprise privacy architecture, Agent PAT protects sensitive borrower data, reads scanned documents and photographs, and actively searches the web to surface an “Adverse Findings” section with cited sources.

“Any company serious about growing, whatever vertical they’re in—if you don’t make this investment [into AI], somebody else is. And the company that does is going to take away market share by being faster, more efficient, and more accurate. It does cost on the front end. But the savings on the back end are going to more than pay for it.”

— Roy Malone, President, Socotra Capital

What Changed

The loan committee no longer spends 45 minutes on a single deal. The property is a click away, documents are linked, and risk flags are colour-coded. Their goal is now to get through 20 deals in under an hour. Deals with fatal flaws can be identified and removed in minutes rather than after days of preparation, and every deal now goes through the same structured review process—asking the same questions and checking the same data sources every time.

How It Measures Up

45 minutes per deal reduced for the loan committee
3–6 hours of manual document work saved per deal at the approval stage
Fatal flaws caught in minutes rather than after days of preparation
Goal: 20 deals reviewed in under an hour, doubling current capacity
~$500M in assets under management, with a goal to reach $1 billion

The Takeaway

Agent PAT isn’t just a productivity tool—it’s an infrastructure investment that makes Socotra Capital’s growth ambitions possible. With Phase 2 already planned (a direct integration between Agent PAT and Salesforce), the solution is built to keep reducing manual steps as the business scales.