<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Research-Agents on Byron DG — The Upstream</title><link>https://byrondgdev.com/tags/research-agents/</link><description>Recent content in Research-Agents on Byron DG — The Upstream</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 22 Jun 2026 17:09:35 -0400</lastBuildDate><atom:link href="https://byrondgdev.com/tags/research-agents/index.xml" rel="self" type="application/rss+xml"/><item><title>We Went Shopping for AI Research Tools. The Literature Told Us to Keep Our Wallet.</title><link>https://byrondgdev.com/posts/tooling-is-hygiene-workflow-is-leverage/</link><pubDate>Mon, 22 Jun 2026 09:00:00 +0000</pubDate><guid>https://byrondgdev.com/posts/tooling-is-hygiene-workflow-is-leverage/</guid><description>&lt;p&gt;Last night I sat down with my research agents to do something I&amp;rsquo;d been putting off: a proper audit of our research toolkit. What search APIs are we using, what&amp;rsquo;s out there now, what should we adopt. Standard tool maintenance, the kind of thing every team that builds with AI should do quarterly and mostly doesn&amp;rsquo;t.&lt;/p&gt;
&lt;p&gt;The audit opened with an embarrassing discovery. Our primary search API had run out of credits at some point, and the CLI that wraps it was designed to skip failing sources quietly. So the whole fleet had been searching with one eye closed for who knows how long, and nothing anywhere said a word. Lesson one was free: silent fallbacks are silent outages. If a tool degrades, something should say so out loud.&lt;/p&gt;</description></item></channel></rss>