<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Research on The Agency</title><link>https://athan-dial.github.io/agency/tags/research/</link><description>Recent content in Research on The Agency</description><generator>Hugo</generator><language>en</language><copyright>© 2026 Athan Dial</copyright><lastBuildDate>Mon, 06 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://athan-dial.github.io/agency/tags/research/index.xml" rel="self" type="application/rss+xml"/><item><title>AI research that actually cites sources</title><link>https://athan-dial.github.io/agency/dispatches/ai-research-that-actually-cites-sources/</link><pubDate>Mon, 06 Apr 2026 00:00:00 +0000</pubDate><guid>https://athan-dial.github.io/agency/dispatches/ai-research-that-actually-cites-sources/</guid><description>A fake citation in a product brief forced the switch: parallel pulls from PubMed, preprints, and trials, then tables with DOIs I can open before I repeat a number.</description></item><item><title>Parallel research with subagents</title><link>https://athan-dial.github.io/agency/playbooks/parallel-research-with-subagents/</link><pubDate>Mon, 06 Apr 2026 00:00:00 +0000</pubDate><guid>https://athan-dial.github.io/agency/playbooks/parallel-research-with-subagents/</guid><description>Helps you send 3–4 researcher subagents at one question in parallel, merge overlaps and gaps, and land a single citable brief instead of serial chat.</description></item><item><title>Run a literature review from your desk</title><link>https://athan-dial.github.io/agency/playbooks/literature-review-from-your-desk/</link><pubDate>Mon, 06 Apr 2026 00:00:00 +0000</pubDate><guid>https://athan-dial.github.io/agency/playbooks/literature-review-from-your-desk/</guid><description>Helps you produce a defendable brief by searching PubMed, preprints, and trials in parallel, then locking claims to verifiable DOIs and NCT IDs.</description></item></channel></rss>