An OpenClaw Personal Finance Research Assistant
A report describes an OpenClaw personal finance assistant designed to organize public financial materials, read announcements, track research views, and support decisions through Feishu, while leaving all trading decisions to the user and avoiding brokerage logins or automated orders. Its architecture combines an OpenClaw Gateway, persistent files, data and calculation tools, and task-specific models. The author reports that a trial verified a delegation path in which DeepSeek Flash handed work to Pro, Pro returned a result, and the main conversation replied. Routine work was assigned to Flash, formal research to Pro, and monetary calculations to fixed programs. Web search in regular business sessions, scheduled delivery, consistent calculation definitions, independent confirmation of the High thinking setting, and DeepSeek Pro’s reliability still require further validation.
The report presents a traceable finance research architecture that combines model delegation, persistent state, external tools, programmatic calculations, and human control over decisions. It also clearly distinguishes the verified delegation path from features that still require end-to-end testing or reliability evaluation.
用 OpenClaw 搭建个人金融助手：从联网查询到双模型协同
我希望有一个能持续整理金融资料、阅读公告、跟踪研究观点的助手：平时可以通过聊天更新资料，在固定时段收到摘要，重要问题再展开研究。交易仍由人决定，助手不登录交易账户，也不自动下单。
真正搭起来后发现，接通模型和飞书只是开始。更难的问题是：搜索结果能不能支撑结论？模型算出来的金额有没有统一口径？任务究竟还在运行，还是已经无声结束？
这篇文章记录一套已经跑通模型委派链路的实现思路，以及目前仍需验证的环节。它不是投资策略，也不包含任何真实持仓、资金规模、个人风险阈值或收益记录。文中的目录和示例均为通用示意。
1. 先把助手的职责定清楚
我把金融助手的工作分成三层：