<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI Coding Agents on Bruce on AI Engineering</title><link>http://www.heyuan110.com/tags/ai-coding-agents/</link><description>Recent content in AI Coding Agents on Bruce on AI Engineering</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 16 Jun 2026 11:00:00 +0800</lastBuildDate><atom:link href="http://www.heyuan110.com/tags/ai-coding-agents/index.xml" rel="self" type="application/rss+xml"/><item><title>Context Engineering for Coding Agents 2026: What Works</title><link>http://www.heyuan110.com/posts/ai/2026-06-16-context-engineering-2026/</link><pubDate>Tue, 16 Jun 2026 11:00:00 +0800</pubDate><guid>http://www.heyuan110.com/posts/ai/2026-06-16-context-engineering-2026/</guid><description>&lt;p&gt;&lt;img src="http://www.heyuan110.com/posts/ai/2026-06-16-context-engineering-2026/cover.webp"
 alt="Context engineering for coding agents 2026: budgeting the context window"
 
 loading="lazy"
 decoding="async"
 fetchpriority="low"
 width="1200"
 height="630"
/&gt;
&lt;/p&gt;
&lt;p&gt;Here is the uncomfortable truth about coding agents in 2026: the model is rarely the bottleneck. What decides whether Claude Code, Codex, or Cursor lands a clean multi-file refactor or spins for an hour is what you put in front of it. Anthropic&amp;rsquo;s 2026 Agentic Coding report calls context engineering &amp;ldquo;the load-bearing skill of 2026,&amp;rdquo; and the numbers back it up — teams with well-maintained context files ship with 40% fewer errors and complete tasks 55% faster than teams without.&lt;/p&gt;</description></item></channel></rss>