Kamalakannan Nandagopal
① 他说过的话
6 条
当我们审视这个问题时,我们意识到,在分布式系统和微服务架构中,API 就是你的上下文层。
指向原始笔记的链接
And when we looked at this, what we realized is in a distributed systems and microservices architecture, APIs are the context layer for you.
—— Kamalakannan Nandagopal · [04:01]
所以智能体的能力只取决于给它们的上下文。
指向原始笔记的链接
So agents are only as good as the context that they’re given.
—— Kamalakannan Nandagopal · [04:30]
但如果你把文档完全交给 LLM 来编写和维护,研究指出,纯由 LLM 维护和编写的文档往往会随时间呈指数级退化。
指向原始笔记的链接
But if you offload documentation purely to LLMs to author and maintain, research points out that purely LLM-maintained and written documentation tends to degrade exponentially over time.
—— Kamalakannan Nandagopal · [02:26]
但我们都知道,skills 和 MCP 的效果只取决于提供给它们的上下文。
指向原始笔记的链接
But we all know skills and MCPs are only as good as the context that they’re provided to.
—— Kamalakannan Nandagopal · [02:44]
但我们心中始终坚守的一个关键原则是:每一条落到上下文图谱上的数据点,都必须扎根于一个硬事实。
指向原始笔记的链接
But one key principle that we had in mind always was every single data point that landed on the context graph always had to be grounded down in a hard truth.
—— Kamalakannan Nandagopal · [05:34]
两周后,开发者回来发现,那个本应发送一个属性的特定属性,现在已经有 15 个属性了。
指向原始笔记的链接
Two weeks later, the developer comes back and finds out that that one particular property, which is supposed to send one attribute, now has 15 attributes.
—— Kamalakannan Nandagopal · [09:57]
② 出现在这些集
1 集
③ 他谈到的
点进去有真内容 —— 本页主要出口
Postman · 编码智能体 · 上下文图 · 微服务 · API · 代码搜索 · 智能体记忆 · Claude Code
