如何从一个提示词运行300个AI Agent。大多数人都会跳过的10个工作流

Here is what happens every single day.

这就是每天都在发生的事情。

Save this :)

保存这个 :)

Most people still use AI the way they used Google in 2010: type a query, read the answer, type the next one.A single thread you feed one item at a time.

大多数人使用 AI 的方式仍然和 2010 年使用 Google 一样：输入查询，阅读答案，再输入下一个。这是一个单线程，你一次只喂给它一个项目。

But a model that can plan and call tools doesn't have to be used one item at a time. Hand it 100 PDFs and the obvious move isn't to walk through them in sequence: it's to open 100 of them at once, one reader per file, and have a coordinator stitch the readings back together. The prompt stays the same length. The work fans out behind it. You go from a single thread to a fan: one instruction in, a hundred workers spawned, one assembled deliverable out.

但是，一个能够规划和调用工具的模型不必每次只处理一个项目。给它 100 份 PDF，最明显的做法不是按顺序逐一处理：而是一次性打开 100 份，每个文件分配一个读取器，然后让一个协调器将读取结果拼接起来。提示词的长度保持不变。工作在其背后扇形展开。你从单线程变成了扇形展开：输入一条指令，生成一百个工作节点，输出一个组装好的交付物。

That is the whole shift, and it is the difference between reading 100 papers over a weekend and reading them over a coffee. The rest of this is the cost math, the setup, the prompts, the repos, the workflows, and the places where this quietly falls apart.

这就是整个转变，它就像是在一个周末读完100篇论文与喝杯咖啡的功夫读完100篇论文之间的区别。剩下的内容则是成本计算、环境搭建、提示词、代码库、工作流，以及这个系统悄然崩溃的地方。

The Real Cost Picture

真实的成本全貌

This is where most people give up before they start. They assume running 300 agents must cost a fortune. It does not.

这是大多数人在开始之前就放弃的地方。他们假设运行 300 个代理一定会花费巨资。事实并非如此。

Take a real task: 100 PDF research papers analyzed into a single literature review with citations.

拿一个真实的任务来说：将 100 篇 PDF 研究论文分析整合成一篇带有引用的单一文献综述。

Sequential approach with Claude Opus 4.8: Roughly 6 hours of agent wall time at $5 per million input tokens and $25 per million output. Estimated cost: $40 to $60 per run depending on document length. Plus your time supervising.

使用 Claude Opus 4.8 的顺序方法：代理实际运行时间大约 6 小时，输入 token 价格为每百万 5 美元，输出为每百万 25 美元。预估成本：每次运行 40 到 60 美元，具体取决于文档长度。再加上你监督的时间。

Parallel approach with the Kimi K2.6 agent swarm: 100 agents spin up simultaneously, each handli...