<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Posts on BBD blog</title><link>https://blog.bluebyday.com/posts/</link><description>Recent content in Posts on BBD blog</description><generator>Hugo</generator><language>en-us</language><managingEditor>-@- (Author)</managingEditor><webMaster>-@- (Author)</webMaster><lastBuildDate>Mon, 01 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.bluebyday.com/posts/index.xml" rel="self" type="application/rss+xml"/><item><title>Good LLM Dev and Usage Patterns</title><link>https://blog.bluebyday.com/posts/good-llm-dev-and-usage/</link><pubDate>Mon, 01 Jun 2026 00:00:00 +0000</pubDate><author>-@- (Author)</author><guid>https://blog.bluebyday.com/posts/good-llm-dev-and-usage/</guid><description>&lt;h2 id="introduction"&gt;Introduction&lt;/h2&gt;
&lt;p&gt;This is a list of patterns regarding usage of LLMs (Large Language Models) that I&amp;rsquo;ve observed result in positive outcomes. I&amp;rsquo;ve split them into two categories:&lt;/p&gt;
&lt;ul&gt;
&lt;li&gt;Usage, for patterns used in systems that are partly agentic, i.e. the system utilizes LLMs during its operation. The examples given are focused on coding agents, but they are generally applicable.&lt;/li&gt;
&lt;li&gt;Development, for patterns used during software development&lt;/li&gt;
&lt;/ul&gt;
&lt;p&gt;If the category split feels arbitrary, feel free to ignore the (ir)relevant headings.&lt;/p&gt;</description></item></channel></rss>