<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Notes on Jens Heise</title><link>https://jensheise.com/notes/</link><description>Recent content in Notes on Jens Heise</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Tue, 09 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://jensheise.com/notes/index.xml" rel="self" type="application/rss+xml"/><item><title>Requirements engineering is prompt engineering</title><link>https://jensheise.com/notes/requirements-engineering-is-prompt-engineering/</link><pubDate>Tue, 09 Jun 2026 00:00:00 +0000</pubDate><guid>https://jensheise.com/notes/requirements-engineering-is-prompt-engineering/</guid><description>&lt;p&gt;People say LLMs need too much steering, that they can&amp;rsquo;t comprehend problems. As someone who spent most of their academic pursuits on Requirements Engineering, let me tell you something: humans are also very bad at following instructions and understanding problems.&lt;/p&gt;
&lt;p&gt;50+ years of RE research basically concern themselves with human-to-human prompt engineering.&lt;/p&gt;</description></item><item><title>Delegation vs comprehension</title><link>https://jensheise.com/notes/delegation-vs-comprehension/</link><pubDate>Wed, 06 May 2026 00:00:00 +0000</pubDate><guid>https://jensheise.com/notes/delegation-vs-comprehension/</guid><description>&lt;p&gt;The inherent tension of agentic coding is between delegation and comprehension. If I need to fully understand, I cannot delegate — at least not with the expectation of saving time.&lt;/p&gt;
&lt;p&gt;The question will be: how to build agentic development environments and processes that let you delegate without losing control? They must establish trust.&lt;/p&gt;</description></item></channel></rss>