智能体
x.com ·
@latentspacepod
播客笔记：提示词取决于领域词汇，MCP 相当于无头 API
Latent.Space 转述听众 yan5xu 的播客笔记：提示词的关键在于心智模型是否匹配以及是否具备足够领域词汇，而非写更长的指令；不懂领域的人难以把 AI 从 60-70 分推到 95 分。笔记还提出 MCP 相当于无头 API、artifact 是短生命周期 UI，agent 可跨 MCP 组合，并类比为 agent 原生的软件架构。
AI推荐理由 转述播客听众关于提示词与 agent 架构的笔记，提出两个可讨论观点：提示词效果取决于心智模型匹配与领域词汇量，以及 MCP 相当于无头 API、artifact 是短生命周期 UI、agent 组合 UI。属个人经验总结而非实证结论，但观点对 agent 开发有参考价值。
60
浏览 334
点赞 1
评论 0
转发 1
正文
[@AnthropicAI](https://x.com/AnthropicAI)[@trq212](https://x.com/trq212) great notes! [x.com/yan5xu/status/…](https://x.com/yan5xu/status/2105317252476420263?s=20)
yan5xu@yan5xu
some notes of mine after this ep
1. prompting is two things: does your mental model match, and do you have enough domain vocabulary
not about writing longer instructions. you need an accurate read on what the model can one-shot vs what has to be broken into steps. and you need the words for the problem domain. non-designer says "give me 8 mockups", designer says fonts, ref sites, components. the gap is vocabulary.
2. brutal paradox here
lots of people want to use AI for stuff they don't understand. but if you don't have the domain vocab, the people who actually do the work will out-prompt you. vocab comes from having done it. AI gets you to 60-70. getting from 70 to 95 still needs the domain knowledge.
3. MCP is just a headless API. Artifact is a short-lived UI. they compose across MCPs.
brain / hands / surface reads to me as the agent-native version of classic software architecture. if this works out, building software goes from writing frontends to writing MCP servers, and agents compose the UI. basically: build a piece of software for agents to use, wrap the business logic inside.
[🔗 View Quoted Tweet](https://x.com/yan5xu/status/2105317252476420263)