Artificial Intelligence

Planners with no code built 17 agents

Range planner Matt Ragone says 20 planners with no code built 17 live skills, all gated by human review.

StartupHub.ai Staff

By StartupHub.ai Staff, reviewed by Daniel Singer, Editor

2 min read

Matt Ragone, a financial planner who leads AI adoption for the planning team at Range, told AI Engineer how 20 planners with zero coding background built 17 planning skills now used daily, Ragone said.

Planners with no code built 17 agents - AI Engineer
Planners with no code built 17 agents, AI Engineer

He wrote no code.

The shift came in late January and early February with Claude Co-work, Ragone said. He could stay on a client call while an agent drafted a cash flow analysis, an insurance review and a tax review in Range systems, where members connect accounts, insurance documents, mortgages and investments. He then reviewed, adjusted and approved the output before anything moved. Every skill is barred from sending to a member without review by a certified financial planner, he said, because Range is a regulated RIA and the advice affects real clients.

His method was five steps: pick, teach, pack, test and ship, he said. Pick a daily or weekly workflow, show two to five real cases including edge cases, narrate why a pay stub line matters, pack the prompts and limits into a skill, test on five to 10 real cases and then ship with an owner and a reviewer. The team had already standardized how it delivers insurance, investment and retirement advice in Notion and Google Docs, he said, so Claude could reference those pages instead of giving generic answers.

Others shaped the work. Co-founder David Kusaydis created the AI Council as a roundtable of heavy users across support, marketing and planning, Ragone said. Colleague Joe reviews insurance skills Ragone owns, and the CPA and tax teams own tax content while Ragone advises on skill design. The talk was listed among Inference Weekly candidates for the week of Nov. 8, per that list, six to eight months after Ragone said the experiment started, with 24 skills firmwide and a Slack agent called Ranger in active build.

Ragone argued the expert should build the skill, not the engineer. Engineers understand their realm, he said, but an insurance specialist catches what a generalist planner misses. He gave no error rates, no hours saved and no client load data to test his goal of moving a planner from three to four people a day to 100 a day with agents as managers. Who retests 24 skills when tax law shifts, and what breaks first?

Mentioned in this story

Markets

Sources

Get the free daily brief every morning

Every morning the day's AI news, new AI startups and new funding rounds. Free and takes a few minutes to read, unsubscribe at any time.

Join 64,000 other subscribers.

TopicsRangeMatt RagoneClaude Co-workRangerDavid KusaydisRIACFP

StartupHub.ai Staff

Written by

StartupHub.ai Staff

Editorial team

The staff writers of StartupHub.ai, ranging from investment analysts to avid AI tool users, early adopters and critical enthusiasts. Backgrounds span engineering, business and the arts. We hold every piece to rigorous standards of research and review.

Daniel Singer

Written by

Daniel Singer

Editor, reviewed this article

Daniel Singer is an AI expert who has been writing about, covering and building AI technology since 2018.

Test your Agent Readiness now

Paste your website. How well ChatGPT, Claude and the other agents can read and use a site, in about a minute.

Watch

The videos behind the news, one flip at a time

The feed mixes the videos from our articles with startup demos and you flip through them like TV channels for free with no signup.