Matthew Ragone said Range let its financial planners write the agents they use every day, and none of them write code, speaking to AI Engineer.
Ragone is a certified financial planner who leads AI adoption for the planning team at Range, an all-in-one wealth management firm.
The team started with AI as a chatbot for polishing client messages, then shifted to agents that draft work while planners are elsewhere. Ragone said the guardrail is absolute: "The agent doesn't send anything. A planner reviews every single recommendation before a client sees it."
Two things had to be true for that to work, Ragone said. The agent had to work where the work lives, not in a separate chat window, and it had to know how Range does the work, not just generic planning.
He laid out five steps his team uses to turn that into a repeatable skill: pick, teach, pack, test, and ship. Pick a frequent, judgeable workflow like cash flow or insurance reviews. Teach it with several real cases and narrate judgment out loud. Pack it as a skill that asks questions before it starts and respects limits like never emailing a client. Test it five to 10 times on real cases, then ship it with an owner and a separate reviewer who keeps it current as processes and tax rules change.
