<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Peripatos — lessons</title><description>New lessons on Peripatos: AI-assisted learning for developers, with calibrated thinking at the core.</description><link>https://peripatos.dev/</link><language>en</language><item><title>Jev: The Model That Answers Instead of Writes</title><link>https://peripatos.dev/courses/jev-fundamentals/s01e01-jev-answers-instead-of-prose/</link><guid isPermaLink="true">https://peripatos.dev/courses/jev-fundamentals/s01e01-jev-answers-instead-of-prose/</guid><description>Read a Jev request and answer as fluently as a function signature: the three question primitives (Noul, Choice, Score), request and answer anatomy, fan-out economics, and a worked rubric-to-questions example.</description><pubDate>Wed, 23 Sep 2026 00:00:00 GMT</pubDate></item><item><title>Jev State and Typed Questions</title><link>https://peripatos.dev/courses/jev-fundamentals/s01e02-jev-state-and-typed-questions/</link><guid isPermaLink="true">https://peripatos.dev/courses/jev-fundamentals/s01e02-jev-state-and-typed-questions/</guid><description>Author the two things you write by hand in every Jev request — the state and the questions. The three question types up close, criteria that define your answer space, independence by design, and a complete worked request.</description><pubDate>Wed, 23 Sep 2026 00:00:00 GMT</pubDate></item><item><title>Confidence, Calibration &amp; Composite Scoring</title><link>https://peripatos.dev/courses/jev-fundamentals/s01e03-jev-confidence-calibration-composite/</link><guid isPermaLink="true">https://peripatos.dev/courses/jev-fundamentals/s01e03-jev-confidence-calibration-composite/</guid><description>What Jev&apos;s confidence numbers promise, threshold routing, uncertainty gates for torn answers (margin, low confidence, torn distributions), composite scoring with weights in code, and measuring calibration instead of trusting it.</description><pubDate>Wed, 23 Sep 2026 00:00:00 GMT</pubDate></item></channel></rss>