Recently, I used v0 by Vercel to build a CRE Loan Sizing application that turns lending assumptions into loan proceeds, constraint checks, and decision metrics. This article walks through the full build lifecycle—from writing the initial prompt and approving v0’s plan to reviewing formulas, refining the interface, testing outputs, and publishing the finished app—plus the actual unedited prompt used to create it for easy reference.

This article explores a practical lesson from attempting to build a financial model using AI. While AI tools can accelerate financial modeling and create impressive structures, they still rely heavily on the clarity and completeness of user instructions. The piece draws parallels with onboarding junior analysts, highlights where AI adds value (formatting, structure), where it falls short (judgment, assumptions), and why domain expertise remains critical—especially in complex

AI can now build clean, institutional-quality multifamily underwriting models in minutes—complete with dashboards, metrics, and largely accurate math. But the real challenge begins with iteration. This article explores where AI excels (speed, structure, coverage) and where it breaks (refinement, debugging, nuanced logic), highlighting why domain expertise remains essential and why AI is best used as a starting point—not a replacement.