<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>evallog</title><description>Log, compare and inspect your LLM evals. Self-hosted.</description><link>https://evallog.ai/</link><item><title>Which prompt technique actually cuts documentation hallucinations?</title><link>https://evallog.ai/evals/tactics-across-doc-types/</link><guid isPermaLink="true">https://evallog.ai/evals/tactics-across-doc-types/</guid><description>Nine prompt techniques, each a single controlled change off one baseline, measured on Javadoc, inline comments, OpenAPI, README and four diagram formats.</description><pubDate>Sun, 21 Jun 2026 00:00:00 GMT</pubDate></item></channel></rss>