We Let Our Financial Planners Write the Agents — Matthew Ragone, Range
Source
youtube.com
Author
AI Engineer
Date
Context
At wealth-management firm Range, planners describe their judgment so an AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → can draft work while they serve another client. In the firm's account of the workflow, an agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → records what to examine, which questions to ask and when to stop. A planner reviews every recommendation before it reaches a client.
The method starts with real cases and explanations of why each document or check matters. Planners then test the instructions repeatedly, correct missing questions and assign both an owner and a separate reviewer. This transfers responsibility for the firm's working methods to the people who know them, while retaining professional review of the resulting advice.
Key takeaways · AI-distilled
Six months in, Ragone reports 24 skills at Range, 17 of them in financial planning, with sales, product and marketing adopting the approach without a mandate.
His five steps: pick a repeated workflow whose output you can judge, teach it with real cases, package the judgment into a skill, test it five to ten times, and ship it with an owner plus a separate reviewer.
Ragone says narrating why a planner opens a document matters more than listing the clicks, and that repeated testing exposes missing questions and confident mistakes.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
video1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Run Code — Kevin Orellana, AWS
videoHow Inference Keeps Up with Our Insatiable Need for Tokens — Cerebras & Gimlet Labs
videoAuth for Agents: Let AI Sign Up for Your Product with auth.md — Michael Grinich, WorkOS
videoDecoupling the Brain from the Hands: Claude Managed Agents (Part 1 of 4) — Anthropic
