Matthew Ragone is a financial planner and CERTIFIED FINANCIAL PLANNER professional whose work at Range includes turning planners’ working methods into reusable AI instructions. He and his colleagues built planner-authored agent skills without writing code: while a planner is on one client’s call, an agent can prepare another household’s cash-flow or insurance analysis. The planner reviews every recommendation before it reaches the client.
A career across finance and content production
Matthew began his financial-services career in Merrill Lynch’s advisor-development program in 2018. He worked in production and content at Barstool Sports from 2021 to 2022, returned to Merrill in 2023 as a wealth-management specialist, and joined Range in November 2025. His employment history records those transitions without establishing a single motivation connecting them.
Range combines financial planning, investment management, tax services and estate planning within a flat-fee membership. In announcing his move, Matthew expressed enthusiasm for the firm’s vision of changing wealth management.
Capturing decisions, questions and stopping rules
Matthew’s approach to building financial-planning agents begins with a repeated workflow whose output the planner knows how to judge. Teaching the agent requires explaining why a planner opens a document, what to check first and which unanswered questions prevent the analysis from proceeding. A list of clicks leaves out the reasoning that makes the procedure useful.
The skills he and his colleagues developed capture those decisions alongside explicit limits. For cash-flow and insurance analyses, the agent prepares a draft; a professional reviews it before any recommendation goes to a client. The instruction that an agent must never send recommendations itself belongs in the skill alongside the analytical procedure.
Matthew also treats testing and maintenance as part of the work. He recommends trying a skill against real cases five to ten times before shipping it. Those trials can expose missing questions and confident mistakes. Each skill then needs a named owner to keep its instructions aligned with the firm’s practices, plus a separate reviewer.
Six months into the effort, Matthew reported 24 skills across Range, including 17 in planning, with sales, product and marketing adopting the approach without a mandate. That spread leaves an unresolved question in his account: how to check quality at scale when assessing an output still requires professional judgment.
At Range, planners turned their own judgment into reusable agent skills. The method starts with familiar work, captures the questions behind each decision, and keeps both client recommendations and shared skills under human review.
An agent can prepare another client’s analysis while a planner is on a call, but a planner reviews every recommendation and controls delivery.
Start with repeated, relatively simple work whose quality the author can judge quickly. Teach it through real cases and explain why each action matters.
Run five to ten real cases before sharing, correct missing questions and confident mistakes, and assign both a maintenance owner and an independent reviewer.
▶ Watch ↗