<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Testing on René Zander | AI Automation Consultant</title><link>https://renezander.com/tags/testing/</link><description>Recent content in Testing on René Zander | AI Automation Consultant</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 05 May 2026 05:30:00 +0000</lastBuildDate><atom:link href="https://renezander.com/tags/testing/index.xml" rel="self" type="application/rss+xml"/><item><title>Your AI Workflow Doesn't Need Better Prompts. It Needs Less AI.</title><link>https://renezander.com/blog/your-ai-workflow-needs-less-ai/</link><pubDate>Tue, 05 May 2026 05:30:00 +0000</pubDate><guid>https://renezander.com/blog/your-ai-workflow-needs-less-ai/</guid><description>&lt;p>The first stage of AI work is prompting.&lt;/p>
&lt;p>The last stage is removing the model from most of the workflow.&lt;/p>
&lt;p>That sounds backwards.&lt;/p>
&lt;p>It is not.&lt;/p>
&lt;p>When a workflow is new, the LLM is useful because the work is still ambiguous. You are discovering what good looks like. You try a prompt, read the output, adjust the examples, change the tone, add constraints, and run it again.&lt;/p>
&lt;p>That is a good use of AI.&lt;/p></description></item></channel></rss>