<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Why we didn't build one big Genie Room in Genie Hub</title>
    <link>https://community.databricks.com/t5/genie-hub/why-we-didn-t-build-one-big-genie-room/m-p/168116#M57</link>
    <description>&lt;P&gt;&lt;STRONG&gt;When we started, the obvious move looked like one big Genie Room&lt;/STRONG&gt; — put everything in, let people ask anything. We went a different way, and it's held up, so I wanted to share the reasoning rather than the conclusion.&lt;/P&gt;
&lt;P&gt;This was for a UK enterprise Finance function, and we split it in two:&lt;/P&gt;
&lt;UL&gt;
&lt;LI&gt;&lt;STRONG&gt;Narrow, trusted rooms. Two rooms — one operational, one financial — each pointed at a single objective.&lt;/STRONG&gt; &lt;STRONG&gt;A Genie Room is at its best around 7 tables; it copes with 30&lt;/STRONG&gt;; it struggles at 100. Keeping each room tight is what makes the answers trustworthy.&lt;/LI&gt;
&lt;LI&gt;&lt;STRONG&gt;One blended, exploratory room.&lt;/STRONG&gt; A separate space across finance, operations and HR (SAP, SAP Analytics Cloud, Workday) for the cross-functional questions no single system can answer alone.&lt;/LI&gt;
&lt;/UL&gt;
&lt;P&gt;The rule we landed on: let the question set the scope — narrow when you need trust, broad when you're exploring. And put access controls in at the start, not as a retrofit.&lt;/P&gt;
&lt;P&gt;Curious how others are drawing that line.&lt;/P&gt;</description>
    <pubDate>Wed, 09 Sep 2026 17:02:32 GMT</pubDate>
    <dc:creator>Valeria_Koz_DBX</dc:creator>
    <dc:date>2026-09-09T17:02:32Z</dc:date>
    <item>
      <title>Why we didn't build one big Genie Room</title>
      <link>https://community.databricks.com/t5/genie-hub/why-we-didn-t-build-one-big-genie-room/m-p/168116#M57</link>
      <description>&lt;P&gt;&lt;STRONG&gt;When we started, the obvious move looked like one big Genie Room&lt;/STRONG&gt; — put everything in, let people ask anything. We went a different way, and it's held up, so I wanted to share the reasoning rather than the conclusion.&lt;/P&gt;
&lt;P&gt;This was for a UK enterprise Finance function, and we split it in two:&lt;/P&gt;
&lt;UL&gt;
&lt;LI&gt;&lt;STRONG&gt;Narrow, trusted rooms. Two rooms — one operational, one financial — each pointed at a single objective.&lt;/STRONG&gt; &lt;STRONG&gt;A Genie Room is at its best around 7 tables; it copes with 30&lt;/STRONG&gt;; it struggles at 100. Keeping each room tight is what makes the answers trustworthy.&lt;/LI&gt;
&lt;LI&gt;&lt;STRONG&gt;One blended, exploratory room.&lt;/STRONG&gt; A separate space across finance, operations and HR (SAP, SAP Analytics Cloud, Workday) for the cross-functional questions no single system can answer alone.&lt;/LI&gt;
&lt;/UL&gt;
&lt;P&gt;The rule we landed on: let the question set the scope — narrow when you need trust, broad when you're exploring. And put access controls in at the start, not as a retrofit.&lt;/P&gt;
&lt;P&gt;Curious how others are drawing that line.&lt;/P&gt;</description>
      <pubDate>Wed, 09 Sep 2026 17:02:32 GMT</pubDate>
      <guid>https://community.databricks.com/t5/genie-hub/why-we-didn-t-build-one-big-genie-room/m-p/168116#M57</guid>
      <dc:creator>Valeria_Koz_DBX</dc:creator>
      <dc:date>2026-09-09T17:02:32Z</dc:date>
    </item>
  </channel>
</rss>

