<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Cost-Optimization on emaat</title><link>https://emaat.dk/tags/cost-optimization/</link><description>Recent content in Cost-Optimization on emaat</description><generator>Hugo</generator><language>da-DK</language><lastBuildDate>Wed, 04 Nov 2026 20:36:55 +0100</lastBuildDate><atom:link href="https://emaat.dk/tags/cost-optimization/index.xml" rel="self" type="application/rss+xml"/><item><title>The Advisor Strategy</title><link>https://emaat.dk/articles/the-advisor-strategy/</link><pubDate>Sun, 12 Apr 2026 00:00:00 +0000</pubDate><guid>https://emaat.dk/articles/the-advisor-strategy/</guid><description>&lt;p&gt;&lt;strong&gt;Article:&lt;/strong&gt; &lt;a href="https://claude.com/blog/the-advisor-strategy"&gt;The advisor strategy: Give agents an intelligence boost&lt;/a&gt; by Anthropic&lt;/p&gt;&#10;&lt;h2 id="summary"&gt;Summary&lt;/h2&gt;&#10;&lt;p&gt;Anthropic introduces the advisor strategy — a cost-effective pattern for building AI agents that pairs Claude Opus as an advisor with a smaller model like Sonnet or Haiku as the executor. The smaller model runs the task end-to-end and calls on Opus only for the hard decisions, giving near Opus-level intelligence at close to Sonnet-level cost.&lt;/p&gt;&#10;&lt;p&gt;The executor calls tools, reads results, and iterates toward a solution on its own. When it hits a decision it can&amp;rsquo;t reasonably solve, it consults Opus, which reads the shared context and returns a plan, a correction, or a stop signal — but never calls tools or produces user-facing output. This inverts the usual sub-agent pattern, where a large orchestrator decomposes work for smaller workers: here the small model drives and escalates, with no decomposition, worker pool, or orchestration logic.&lt;/p&gt;</description></item></channel></rss>