http://mayf3.github.io/tags/workflow/Recent content in Workflow on My HomeHugo -- gohugo.iozh-cnFri, 24 Jul 2026 08:00:00 +0800http://mayf3.github.io/post/2026-07-24-how-75-ai-agents-collaborate-five-layer-evolution/Fri, 24 Jul 2026 08:00:00 +0800http://mayf3.github.io/post/2026-07-24-how-75-ai-agents-collaborate-five-layer-evolution/Someone asked me: “You’ve got 75 AI agents (as of mid-July, counting both active and experimental ones). How do they actually interact? When Agent A finishes something, how does Agent B pick it up?” Great question. Because I didn’t have a clue at the start either. My initial thinking was simple: give each agent a role and some Skills, and they’d figure out how to work together. Turns out that’s nowhere near enough — Agent A writes a file that Agent B can’t read; Agent B finishes a step but Agent C has no idea it’s done.http://mayf3.github.io/post/2026-05-25-agent-constraints-three-layer-system/Mon, 25 May 2026 08:00:00 +0800http://mayf3.github.io/post/2026-05-25-agent-constraints-three-layer-system/大语言模型天生不靠谱。上一篇文章聊了为什么需要 Agent 编排。这篇聊编排的核心：怎么约束 Agent 的行为。 跑了大半年 Agent 系统，我最大的体会：prompt 靠不住http://mayf3.github.io/post/2026-05-23-ai-agent-content-pipeline-en/Sat, 23 May 2026 10:00:00 +0800http://mayf3.github.io/post/2026-05-23-ai-agent-content-pipeline-en/I Only Do Two Things Now Record thoughts. Review drafts. And finally click publish. Recording thoughts means speaking into my phone. Reviewing means reading finished articles in Feishu documents and leaving comments paragraph by paragraph. Clicking publish is the very last step. Everything else — topic selection, writing, multi-round review, distribution — is handled by a team of AI agents. I call this system the “Content Collaboration Pipeline.” It’s not fully automatic.