<?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 How does Genie look under the hood in Generative AI</title>
    <link>https://community.databricks.com/t5/generative-ai/how-does-genie-look-under-the-hood/m-p/157331#M1818</link>
    <description>&lt;P&gt;Hi everybody,&lt;/P&gt;&lt;P&gt;I'm using Genie for some time which is really great. In order to improve and before recommending it more users within our company I need to get more insights on Genie including but not limited to:&lt;BR /&gt;&lt;BR /&gt;&lt;/P&gt;&lt;OL&gt;&lt;LI&gt;Is it correct that the “thinking” part is not being executed on the associated Databricks clusters rather than on a VM (or similar runtime) on appropriate Cloud provider resources managed by Databricks?&lt;/LI&gt;&lt;LI&gt;If so, is there only one LLM ‘execution engine’ as per (Azure) subscription? Or per (Azure) tenant? Or multiple?&lt;/LI&gt;&lt;LI&gt;Is the LLM ‘execution engine’ the same for Genie Spaces and Genie Code?&lt;BR /&gt;Or how many are available within the background?&lt;/LI&gt;&lt;LI&gt;Performance within our enviroment is decreasing month by month. Currently 20 seconds for response on "WHat can you do for me?" &lt;span class="lia-unicode-emoji" title=":disappointed_face:"&gt;😞&lt;/span&gt;&lt;BR /&gt;What can I do to change it? Request change to Databricks account?&lt;/LI&gt;&lt;LI&gt;Which (customized) LLM is used by Genie? GPT or Claude?&lt;/LI&gt;&lt;/OL&gt;&lt;P&gt;Would be great to get insights on this as otherwise using Genie and Databricks more will be difficult.&lt;/P&gt;</description>
    <pubDate>Wed, 20 May 2026 13:12:40 GMT</pubDate>
    <dc:creator>michael365</dc:creator>
    <dc:date>2026-05-20T13:12:40Z</dc:date>
    <item>
      <title>How does Genie look under the hood</title>
      <link>https://community.databricks.com/t5/generative-ai/how-does-genie-look-under-the-hood/m-p/157331#M1818</link>
      <description>&lt;P&gt;Hi everybody,&lt;/P&gt;&lt;P&gt;I'm using Genie for some time which is really great. In order to improve and before recommending it more users within our company I need to get more insights on Genie including but not limited to:&lt;BR /&gt;&lt;BR /&gt;&lt;/P&gt;&lt;OL&gt;&lt;LI&gt;Is it correct that the “thinking” part is not being executed on the associated Databricks clusters rather than on a VM (or similar runtime) on appropriate Cloud provider resources managed by Databricks?&lt;/LI&gt;&lt;LI&gt;If so, is there only one LLM ‘execution engine’ as per (Azure) subscription? Or per (Azure) tenant? Or multiple?&lt;/LI&gt;&lt;LI&gt;Is the LLM ‘execution engine’ the same for Genie Spaces and Genie Code?&lt;BR /&gt;Or how many are available within the background?&lt;/LI&gt;&lt;LI&gt;Performance within our enviroment is decreasing month by month. Currently 20 seconds for response on "WHat can you do for me?" &lt;span class="lia-unicode-emoji" title=":disappointed_face:"&gt;😞&lt;/span&gt;&lt;BR /&gt;What can I do to change it? Request change to Databricks account?&lt;/LI&gt;&lt;LI&gt;Which (customized) LLM is used by Genie? GPT or Claude?&lt;/LI&gt;&lt;/OL&gt;&lt;P&gt;Would be great to get insights on this as otherwise using Genie and Databricks more will be difficult.&lt;/P&gt;</description>
      <pubDate>Wed, 20 May 2026 13:12:40 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/how-does-genie-look-under-the-hood/m-p/157331#M1818</guid>
      <dc:creator>michael365</dc:creator>
      <dc:date>2026-05-20T13:12:40Z</dc:date>
    </item>
  </channel>
</rss>

