让金融规划师亲手编写 Agent：Range 的五步方法

简要描述Brief Description

我们让财务规划师来编写智能体——Matthew Ragone，RangeWe Let Our Financial Planners Write the Agents — Matthew Ragone， Range

目录Table of Contents

• 正在构建自己的智能体的财务规划师
  Financial planners building their own agents
• 规划者正在参加另一个通话时起草内容
  Drafting while the planner is on another call
• 选择一个你能够评估的工作流
  Pick a workflow you can judge
• 传授判断力，并封装限制条件
  Teach the judgment and package the limits
• 测试真实案例，指定负责人和审核人
  Test real cases, assign owners and reviewers

正在构建自己的智能体的理财规划师Financial planners building their own agents

大家好，我是 Matt Rigon，在 Range 担任理财规划师。我想向大家展示，我们的理财规划师是如何最终写出我们每天使用的智能体的——顺便说一句，我们这些理财规划师没有一个人会写代码。这是一份构建指南，讲的是我们一步步如何做到的，这样你就可以把它带回自己的团队、公司等地方。我先简单介绍一下自己，因为这关系到你会如何听这场分享。我不是工程师，而是一名注册理财规划师，每天都和客户讨论现金流、税务、保险、退休、遗产规划等等。我还负责推动 Range 规划团队采用 AI。Range 是一家提供一站式财富管理服务的公司。你听到的大多数智能体分享，都是来自打造平台的人；而这场分享来自平台的另一端，也就是你们把平台交给的人。Hi everyone, I'm Matt Rigon and I'm a financial planner at Range. I want to show you how our financial planners ended up writing the agents that we use every day and none of us the financial planners for that matter write code. This is the build guide. How we did it step by step so you can take it back to your own teams, companies, etc. So, a quick bit about me because it matters for how you'll hear this talk. I'm not an engineer. I'm a certified financial planner and I spend my days with clients talking about cash flow, taxes, insurance, retirement, estate, you name it. I also lead the AI adoption for the planning team at Range, which is an all-in-one wealth management company. Most agent talks you'll hear come from the people who built the platform. This talk comes from someone on the other side, the people you hand the platform to.

我们身处受监管的行业。输出内容是给真实客户的财务建议，而且审核环节不是可选项。所以，这不是供应商的推销，而是一种方法，也是我们实际验证有效的方法。我们从大家最初都会尝试的方式入手：把 AI 当作聊天机器人。我会写一条客户消息，把它粘贴进去，让它帮我表达得更清楚或更友好一些。这确实有用。它时不时能帮我省下几分钟，但所有工作仍然是我手动完成的。我只是做得快了一点。转变。We work in a regulated business. The output is financial advice to real clients. And the review step is not optional. So, this isn't a vendor pitch. It's a method and it's what actually worked for us. We started where everyone starts AI as a chatbot. I'd write a client message, paste it in, and ask it to make it a little clearer or friendlier. And that was useful. It saved me a few minutes here and there, but I was still doing all of the work manually. I was just doing it a little bit faster. The change

规划人员正在接听另一通电话时起草内容Drafting while the planner is on another call

真正重要的变化是在后来才出现的。我们后来想明白了这一点。比如，规划师的瓶颈从来都不是打字速度，而是我们一次只能身处一个地方。如果我正在和一位客户通话，就没法同时为另一位客户制定方案。打字更快并不能解决这个问题。真正能解决问题的，是我在别处忙着时也能进行的工作。 那么，现在我的一天是这样的：我正在和一位客户通话的同时，一名智能代理正在为另一位客户起草完整的现金流分析或保险分析。通话结束后，我打开草稿，仔细审核，按需修改，然后把建议发给客户。 我想特别强调最后这一步：智能代理不会发送任何内容。客户看到的每一条建议，都必须先由规划师审核。that actually mattered came later. Here's what we figured out. A planner's constraint was never typing speed, for example. It's that we can only be in one place at a time. If I'm on a call with a client, I'm not building someone else's plan. Writing faster doesn't fix that problem. What fixes it is work that happens while I'm somewhere else. So, here's what a day looks like now. I'm on a call with one client. At the same time, an agent is drafting a full cash flow analysis or an insurance analysis for a different client. When the call ends, I open that draft. I fully review it, adjust what needs to be adjusted, and send the client their recommendations. I want to be really clear about that last step. The agent doesn't send anything. A planner reviews every single recommendation before a client sees it.

变化在于，初稿不再需要我坐在它面前盯着。要做到这一点，靠一个好提示词远远不够。不过，有两件事必须成立。第一，智能体必须在工作实际发生的地方工作，而不是待在一个独立的聊天窗口里，让我把内容复制粘贴进去。第二，它必须了解我们是怎么做的，而不只是泛泛地了解财务规划。模型本身已经懂财务规划，但智能体需要知道 Range 是怎么做的：我们先看什么、哪些情况总会标出来，以及具体建议该怎么措辞。这种结合就是所谓的技能：把我们公司完成某一项具体工作的方式写下来，让智能体照着执行。What changed is that the first draft no longer needs me sitting in front of it. Getting there took a lot more than a good prompt. However, two things had to be true. First, the agent has to work where the work lives, not in a separate chat window I'm copying and pasting it into. Second, it has to know how we do it, not how financial planning works in general. The model already knows that, but the agent needs to know how range does it. What we look at first, what we always flag, how we phrase a specific recommendation. That combination is what a skill is. Our firm's way of doing one specific piece of work written down so an agent can follow it.

选择一个你能够评估的工作流Pick a workflow you can judge

这场演讲的主要内容，就是如何打造一个这样的工具。分五步：挑选、教学、打包、测试，然后发布。这些步骤都不需要编写代码。每一步都要求你非常了解这项工作，这也正是为什么应该由实际做这项工作的人来打造它。第一步，挑选一项你会反复执行的工作流程。你最初可能会想挑最炫、最耗时、最复杂的工作。不要挑那种你每周都会做、已经知道怎样才算做得好，而且一眼就能看出草稿好坏的工作。此外，我们建议一开始选择一些不太复杂、但需要大量手工操作的工作流程。对我们来说，这包括现金流分析和保险审核。至少对我们 Range 来说，这些工作需要最多的手工操作。The bulk of this talk is how you build one. Five steps. Pick, teach, pack, test, and then ship. None of them require writing code. Every one of them requires knowing the work really well, which is exactly why the people doing the work should also be the ones building it. Step one, pick a workflow you repeat. Your initial instinct is to go for the flashiest work, whatever's taking the most amount of time and the most complex. Don't pick something you do every week where you already know what good looks like, where you can spot a bad draft at a glance. Additionally, we recommend choosing some of the least complex workflows to start, but some that require the most manual work. For us, that meant things like cash flow analysis and insurance reviews. Just for us here at range, that required the most manual work.

如果你无法快速判断输出，就无法测试它，也无法信任它。所以要寻找两个】【。And if you can't judge the output quickly, you can't test it and you can't trust it. So look for two

传授判断力，并将限制条件打包。Teach the judgment and package the limits

事情。你经常这样做，也知道该如何判断。第二步，给它看几个你过去交付过的方案的真实案例。选取几个实际客户案例，从头到尾带它走一遍工作流程。过程中，把你的判断过程大声讲出来。不要只说“接下来我打开过去的文件”，还要说明你为什么打开它、在找什么，以及什么情况会让你停下来提问。这样的讲解才是关键。步骤很容易写下来，真正让成果体现你们公司的特色、而不是泛泛建议的，是判断力。第三步，把它封装成一项技能。技能不只是步骤清单。有两件事最重要：开始之前必须提出的问题。它需要了解什么？哪些事情应该向我确认，而不是自作主张地猜测？以及它必须遵守的限制：哪些事情绝不能自行处理。things. You do it often and you know how to judge it. Step two, show it several real cases for previous plans you've delivered. Take several actual client cases and walk through the work start to finish. And as you do it, narrate your judgment out loud. Not just next I open the pastub, why you're opening it, what you're looking for, what would make you stop and ask a question. That narration is the whole game. The steps are easy to write down. The judgment is what makes it your firm's work instead of generic advice. Step three, pack it into a skill. A skill isn't just a lip a list of steps. Two things matter most. The questions it must ask before it starts. What does it need to know? What should it confirm with me instead of simply guessing? And the limits it must respect. What it never does on its own.

在我们的体系中，最重要的一点是，它绝不会向客户发送任何内容。它会先起草内容，再由规划器决定是否发送，或是否需要调整。如果你只写步骤，得到的东西就只会自行运行。如果你写出问题并设定限制，就能得到值得信赖的东西。可以把技能想成一份食谱。一旦 Claude 学会了如何执行这项技能，它就会按指令重复你的流程。In our world, the big one is that it never sends anything to a client. It drafts and then a planner decides if it gets sent or needs to be adjusted. If you only write the steps, you get something that simply just runs on its own. If you write the questions and set the limits, you can get something you can trust. Think of a skill as a recipe. Once Claude knows how to do the skill, it will repeat your process on command.

测试真实案例，指定负责人和审核人员Test real cases, assign owners and reviewers

第四步，在其他人看到之前，拿真实案例运行五到十次。这是大家都想跳过的一步。每次运行都会让你发现这项技能尚不了解的东西：一个边缘案例、一个它本该提出的问题，或一个它听起来信心十足却答错了的地方。你需要修正它、保存这项技能，然后一次又一次地重新运行。运行五到十次听起来很多，但比起把一个尚未成熟的技能交给团队里的15、20甚至100人之后再收拾残局，这要省事得多。 第五步，发布时明确一位负责人和一位审阅者。负责人负责让它保持最新。我们的流程会变，税务规则也会变；三月份还正确的技能，到十二月可能就错了。团队依赖它之前，由审阅者进行检查，而且审阅者必须是作者之外的其他人。就像计划一样，不能给自己的工作打分。Step number four, run it five or 10 times on real cases before anyone else sees it. This is the step everyone wants to skip. Every run teaches you something the skill didn't know yet. An edge case, a question it should have asked, a spot where it sounded confident and was wrong. You need to fix it, save the skill, and run it again and again and again. Five to 10 runs sounds like a lot, but it's a lot less work than cleaning up after you hand a halfbaked skill to 15, 20, 100 people in your team. Step five, ship it with an owner and a reviewer. The owner keeps it current. Our processes change, tax rules change, and a skill that was right in March can be wrong by December. The reviewer checks it before the team relies on it. And it's someone other than the author. Same as a plan, you don't grade your own work.

一旦其他人开始依赖某项技能，就必须有人对此负责。这就是巧妙的个人捷径与团队可以据此继续构建的东西之间的区别。那么，我们目前进展如何？六个月下来，公司里共有 24 项技能，其中 17 项正用于规划。还有一点是我没想到的：这种做法扩展到了销售、产品和市场营销部门，而且完全没有任何强制要求。没人发过备忘录。大家看到规划人员在做什么，便开始构建自己的智能体。这些技能全都是由规划人员、市场营销人员和销售人员编写并维护的，而不是开发人员或工程师。领域专家开始为自己的细分领域构建技能后，有几件事发生了变化。技能变得具体得多了。例如，最了解保险的人，最适合构建保险技能。Once other people depend on a skill, somebody has to be accountable for it. That's the difference between a clever personal shortcut and something a team can build on. So, where are we at currently? Six months in, we have 24 skills across the company and 17 of them are in planning. And here's the part I didn't expect. It spread to sales, product, marketing, all without a mandate. Nobody sent a memo. People saw what the planners were doing and started building their own agents. Every one of those skills was written and is maintained by planners, marketers, and salespeople, not developers or engineers. A couple of things changed once subject matter experts started building for their own niche. The skills got a lot more specific. The person who knows insurance, for example, best builds the insurance skill.

最懂税务、税务法规和税法的人，应该负责构建税务智能体。审查也就自然而然地出现了。我们本来就会互相审查彼此的计划，这就是规划工作的方式。现在，我们也用同样的方式互相审查彼此的技能。这是同一种习惯，只不过要审查的对象换了。那么，为什么这件事现在很重要？因为瓶颈已经变了。模型能不能起草现金流分析，这个问题已经有了答案：能。还没解决的是什么？谁来记录你们公司是怎么做这件事的？谁来在它发布前测试它？一旦另外15个人开始依赖它，又由谁来负责？如果有人要求你把智能体推广到工程团队之外，你很快就会遇到这些问题。目前这方面的实际数据还不多，但这就是我们在 Range 的做法。好了，就到这里。非常感谢大家聆听这场演讲。The person who best knows tax, tax code, tax law should be building the tax one. and a review came naturally. We already review each other's plans and that's just how planning works. So now we review each other's skills in that same way. It's the same habit, just a new thing to review. So why does this matter right now? Because the bottleneck has moved. Whether a model can draft a cash flow analysis, that question's already been settled. It can. What's not settled? Who writes down how your firm does it? who tests it before it ships, who owns it once 15 other people depend on it. If you're being asked to push agents out past the engineering org, you're about to hit these exact questions. There isn't much field data on this yet, but this is how we've done it here at Range. So, that's it. Thank you so much for listening to this talk.

我是来自 Range 的 Matt Rigon，您可以通过 mattrange.com 联系我。祝您今天愉快。I'm Matt Rigon from Range and you can reach me for at mattrange.com. Have a great day.