<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Free AI Planning Tools on René Zander | Context Layer for AI Agents</title><link>https://renezander.com/tools/</link><description>Recent content in Free AI Planning Tools on René Zander | Context Layer for AI Agents</description><generator>Hugo</generator><language>en</language><lastBuildDate>Wed, 30 Sep 2026 12:00:00 +0000</lastBuildDate><atom:link href="https://renezander.com/tools/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Solution Shape</title><link>https://renezander.com/tools/ai-solution-shape/</link><pubDate>Sat, 25 Jul 2026 12:00:00 +0000</pubDate><guid>https://renezander.com/tools/ai-solution-shape/</guid><description>&lt;p>&lt;strong>Next step:&lt;/strong> once the shape is clear, write down what the AI may do on its own and who approves the rest. The &lt;a href="https://renezander.com/tools/ai-decision-rights/">AI Decision Rights Map&lt;/a> turns that into a table, in your browser.&lt;/p></description></item><item><title>AI Decision Rights Map</title><link>https://renezander.com/tools/ai-decision-rights/</link><pubDate>Wed, 30 Sep 2026 12:00:00 +0000</pubDate><guid>https://renezander.com/tools/ai-decision-rights/</guid><description>&lt;p>An &lt;strong>AI decision rights map&lt;/strong> is an approval matrix for AI agents. It lists every action the AI can take and gives each one of four modes: act alone, draft for a person to approve, recommend only, or never. Per action it also records the condition, the named approver and whether the approval is checked again when the action runs.&lt;/p>
&lt;h2 id="the-four-modes">The four modes&lt;/h2>
&lt;table>
 &lt;thead>
 &lt;tr>
 &lt;th>Mode&lt;/th>
 &lt;th>What the AI does&lt;/th>
 &lt;th>Typical actions&lt;/th>
 &lt;/tr>
 &lt;/thead>
 &lt;tbody>
 &lt;tr>
 &lt;td>Act alone&lt;/td>
 &lt;td>Executes without a person, inside a written limit&lt;/td>
 &lt;td>Sorting requests, tagging tickets, small refunds&lt;/td>
 &lt;/tr>
 &lt;tr>
 &lt;td>Draft, a human approves&lt;/td>
 &lt;td>Prepares the action, a named person releases it&lt;/td>
 &lt;td>Customer replies, payments above a limit, master data changes&lt;/td>
 &lt;/tr>
 &lt;tr>
 &lt;td>Recommend only&lt;/td>
 &lt;td>Suggests, a person decides and executes&lt;/td>
 &lt;td>Discounts, supplier choice, write-offs&lt;/td>
 &lt;/tr>
 &lt;tr>
 &lt;td>Never&lt;/td>
 &lt;td>The action is not available to the AI&lt;/td>
 &lt;td>Deleting customer records, changing permissions&lt;/td>
 &lt;/tr>
 &lt;/tbody>
&lt;/table>
&lt;p>In the usual oversight terms, &amp;ldquo;act alone&amp;rdquo; is autonomous, &amp;ldquo;draft&amp;rdquo; is human-in-the-loop with approval before the action, &amp;ldquo;recommend&amp;rdquo; leaves the decision with a person, and &amp;ldquo;never&amp;rdquo; is a hard stop.&lt;/p></description></item></channel></rss>