<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Prompt-Caching on Chen Kai Blog</title><link>https://www.chenk.top/en/tags/prompt-caching/</link><description>Recent content in Prompt-Caching on Chen Kai Blog</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 04 Apr 2026 09:00:00 +0000</lastBuildDate><atom:link href="https://www.chenk.top/en/tags/prompt-caching/index.xml" rel="self" type="application/rss+xml"/><item><title>LLM Engineering (9): Prompting at Production Scale</title><link>https://www.chenk.top/en/llm-engineering/09-prompting/</link><pubDate>Sat, 04 Apr 2026 09:00:00 +0000</pubDate><guid>https://www.chenk.top/en/llm-engineering/09-prompting/</guid><description>&lt;p>A prompt that works on 100 examples in a notebook can fail on 10% of inputs in production for reasons unrelated to cleverness. This chapter covers prompting as an engineering task: where chain-of-thought helps (and where it doesn&amp;rsquo;t), how prompt caching affects costs, how to combine few-shot, chain-of-thought, and self-consistency without using every trick, and how to defend against jailbreaks and injections that production traffic will generate within a week of launch.&lt;/p></description></item></channel></rss>