<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Build-vs-Buy on Byron DG — The Upstream</title><link>https://byrondgdev.com/tags/build-vs-buy/</link><description>Recent content in Build-vs-Buy on Byron DG — The Upstream</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 24 Jul 2026 13:08:25 -0400</lastBuildDate><atom:link href="https://byrondgdev.com/tags/build-vs-buy/index.xml" rel="self" type="application/rss+xml"/><item><title>Tool Showcase: The Research CLI</title><link>https://byrondgdev.com/posts/tool-showcase-the-research-cli/</link><pubDate>Fri, 24 Jul 2026 09:00:00 +0000</pubDate><guid>https://byrondgdev.com/posts/tool-showcase-the-research-cli/</guid><description>&lt;!-- FIGURE 1: hero image. Type: generated infographic.
 Title: the research CLI on display. Contents: knolling
 composition — terminal window with the "research" prompt upper-left, four
 dashed component trays with connector lines: search (Exa, Tavily, merge,
 results), fetch (guard, cache, extract, browser, markdown), paper, academic
 (ArXiv, Semantic Scholar, OpenAlex, CORE). All 18 labels verified against
 the verbatim list. Caption: none (hero). --&gt;
&lt;p&gt;Now for a new type of post: the tool showcase, a series dedicated to the tools our fleet uses. Each post covers one tool: its origin, its usage, and its value. First up is the research CLI, because it was one of the first tools in my fleet that I put real engineering time into, and because the story behind it covers a decision I make over and over: when do you actually need a tool, and once you know you need one, do you build it, adopt it, or buy it?&lt;/p&gt;</description></item></channel></rss>