如何设置(超简单,3 个文件)
- 安装 Pi
- researcher.md 将此文件放到 ~/.pi/agent/agents/
- report-writer.md 将此文件放到 ~/.pi/agent/agents/
- research.md 将此文件放到 ~/.pi/agent/prompts
为什么选择 Pi
速度飞快、精简轻量,而且 token 效率高
将工作委派给其他智能体的 /research 命令
pi 配置中新增了一个 /research 命令。输入 /research <topic>,你就能得到一份报告,以 Markdown 文件外加一个 HTML 页面的形式输出。主智能体本身并不做研究——而是把工作委派给其他智能体,然后再汇总结果。每个智能体都可以单独配置最适合它的模型。
在视频中,我演示了使用 inclusionai/ling-3.0-flash。它的速度非常快。
工作原理
flowchart LR
U(["/research <topic>"]) e0@--> P["Main agent<br/>checks date + language"]
P e1@--> R1["researcher 1<br/>angle A"]
P e2@--> R2["researcher 2<br/>angle B"]
P e3@--> R3["researcher 3<br/>angle C"]
P e4@--> R4["researcher 4<br/>angle D"]
R1 e5@-- brief --> W["report-writer"]
R2 e6@-- brief --> W
R3 e7@-- brief --> W
R4 e8@-- brief --> W
W e9@--> MD[/"report.md"/]
W e10@--> HTML[/"report.html"/]
e0@{ animate: true }
e1@{ animate: true }
e2@{ animate: true }
e3@{ animate: true }
e4@{ animate: true }
e5@{ animate: true }
e6@{ animate: true }
e7@{ animate: true }
e8@{ animate: true }
e9@{ animate: true }
e10@{ animate: true }
运行效果
以 /research GPT-5 vs Claude 5 for coding 为例。几分钟后,文件夹里会出现两个文件:
2026-09-25-1430-gpt-5-vs-claude-5-comparison.md2026-09-25-1430-gpt-5-vs-claude-5-comparison.html
提示词
Research: $@
1. Date. Run `date`. Never guess the date.
2. Language. Match the topic's language (Chinese stays Chinese).
3. Research. Spawn one or more `researcher` subagents, each with a
distinct angle. Don't research yourself or answer from memory.
Start each task with today's date, the language, and the time
window that counts as current.
4. Report. Spawn a `report-writer` with the findings. It writes a
timestamped .md and a matching .html.
Don't ask me to clarify scope. Make a reasonable call and proceed.
(这是精简版。完整文件是 agent/prompts/research.md。)