Learning学习

What I have been working at lately is how to lead AI agents through to a finished result.

That has taken me into application development, automated workflows, research and deployment. I usually start with a concrete project, then learn what I need as I encounter each problem.

Generating a result is only the first step. Someone still has to judge whether the requirements are clear, the sources are reliable and the result solves the problem. When a model says it is done, I check what it has actually completed.

I define the requirements, choose an approach and review the result, while agents carry out the work and implement the code. My experience in B2B sales helps with understanding needs and moving projects forward; my computer science background helps me engage with the technical work.

AI is a powerful lever: it lets me take on work well beyond my original field. I am willing to try ideas in public and improve them using the results and feedback. You can find several of those projects in Things Made.

这段时间我在钻研的，是怎样带着 AI Agent 把事情真正做完。

应用开发、自动化工作流、资料研究、部署，我通常从一个具体项目出发，遇到问题再去学需要的东西。

生成结果只是第一步。需求有没有说清楚，资料和来源靠不靠谱，做出来的东西能不能解决问题，都需要人来判断。模型说完成了，我还要亲自看看它做到了哪一步。

我负责明确需求、选择方案和检查结果，组织 Agent 完成执行与代码实现。过去做 ToB 销售时积累的需求沟通和项目推进经验，以及计算机专业的基础，都能在这个过程中派上用场。

AI 是很大的杠杆，让我能把能力延伸到原来专业之外的更多领域。我愿意公开尝试，也会根据实际结果和反馈继续改进。作品集里有几个这样做出来的项目。