<?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 to deploy an Agent in Generative AI</title>
    <link>https://community.databricks.com/t5/generative-ai/how-to-deploy-an-agent/m-p/151091#M1706</link>
    <description>&lt;P&gt;&lt;SPAN&gt;Hi everyone,&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;I’m currently developing several Databricks Agents using a custom Claude skill to integrate Databricks Asset Bundles (DABs), Mosaic AI frameworks, and LangGraph.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;My current workflow is the following:&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;UL&gt;&lt;LI&gt;&lt;SPAN&gt;I develop the agents locally.&lt;/SPAN&gt;&lt;/LI&gt;&lt;LI&gt;&lt;SPAN&gt;For deployment, I trigger a CI/CD pipeline (GitHub or Azure DevOps).&lt;/SPAN&gt;&lt;/LI&gt;&lt;LI&gt;&lt;SPAN&gt;The pipeline runs databricks bundle deploy and then executes a notebook responsible for registering the agent and its artifacts.&lt;/SPAN&gt;&lt;/LI&gt;&lt;/UL&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;In my mind this seemed like the correct approach, since agent deployment usually involves steps like MLflow model registration and artifact logging, which require some form of execution (notebook, job, or script).&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;However, I started wondering if there might be a more direct way to deploy agents without relying on a pipeline step that executes a notebook.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;My assumption is that this execution step is always required because the agent needs to be registered along with its artifacts and configuration, but I’d be curious to hear how others are handling this.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;How are you deploying your agents in practice?&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Are you also using CI/CD pipelines that run notebooks or scripts for registration, or have you adopted a different pattern for deploying agents?&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Thanks in advance for any insights&lt;/SPAN&gt;&lt;/P&gt;</description>
    <pubDate>Mon, 16 Mar 2026 23:48:32 GMT</pubDate>
    <dc:creator>Ale_Armillotta</dc:creator>
    <dc:date>2026-03-16T23:48:32Z</dc:date>
    <item>
      <title>How to deploy an Agent</title>
      <link>https://community.databricks.com/t5/generative-ai/how-to-deploy-an-agent/m-p/151091#M1706</link>
      <description>&lt;P&gt;&lt;SPAN&gt;Hi everyone,&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;I’m currently developing several Databricks Agents using a custom Claude skill to integrate Databricks Asset Bundles (DABs), Mosaic AI frameworks, and LangGraph.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;My current workflow is the following:&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;UL&gt;&lt;LI&gt;&lt;SPAN&gt;I develop the agents locally.&lt;/SPAN&gt;&lt;/LI&gt;&lt;LI&gt;&lt;SPAN&gt;For deployment, I trigger a CI/CD pipeline (GitHub or Azure DevOps).&lt;/SPAN&gt;&lt;/LI&gt;&lt;LI&gt;&lt;SPAN&gt;The pipeline runs databricks bundle deploy and then executes a notebook responsible for registering the agent and its artifacts.&lt;/SPAN&gt;&lt;/LI&gt;&lt;/UL&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;In my mind this seemed like the correct approach, since agent deployment usually involves steps like MLflow model registration and artifact logging, which require some form of execution (notebook, job, or script).&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;However, I started wondering if there might be a more direct way to deploy agents without relying on a pipeline step that executes a notebook.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;My assumption is that this execution step is always required because the agent needs to be registered along with its artifacts and configuration, but I’d be curious to hear how others are handling this.&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;How are you deploying your agents in practice?&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Are you also using CI/CD pipelines that run notebooks or scripts for registration, or have you adopted a different pattern for deploying agents?&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Thanks in advance for any insights&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Mon, 16 Mar 2026 23:48:32 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/how-to-deploy-an-agent/m-p/151091#M1706</guid>
      <dc:creator>Ale_Armillotta</dc:creator>
      <dc:date>2026-03-16T23:48:32Z</dc:date>
    </item>
    <item>
      <title>Re: How to deploy an Agent</title>
      <link>https://community.databricks.com/t5/generative-ai/how-to-deploy-an-agent/m-p/151165#M1712</link>
      <description>&lt;P&gt;Hey, your approach is a common pattern. But there has been a recent shift where we now recommend creating the agents as databricks apps instead. This allows you to not do pipeline execution steps. Here are a couple of articles you may find helpful.&lt;/P&gt;
&lt;P&gt;&lt;A href="https://www.databricks.com/blog/custom-agents-now-available-databricks" target="_blank"&gt;https://www.databricks.com/blog/custom-agents-now-available-databricks&lt;/A&gt;&lt;/P&gt;
&lt;P&gt;&lt;A href="https://docs.databricks.com/aws/en/generative-ai/agent-framework/migrate-agent-to-apps" target="_blank"&gt;https://docs.databricks.com/aws/en/generative-ai/agent-framework/migrate-agent-to-apps&lt;/A&gt;&lt;/P&gt;
&lt;P&gt;Let me know if you need anything else.&lt;/P&gt;
&lt;P&gt;&lt;BR /&gt;Thanks,&lt;BR /&gt;&lt;BR /&gt;Emma&lt;/P&gt;</description>
      <pubDate>Tue, 17 Mar 2026 16:38:48 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/how-to-deploy-an-agent/m-p/151165#M1712</guid>
      <dc:creator>emma_s</dc:creator>
      <dc:date>2026-03-17T16:38:48Z</dc:date>
    </item>
    <item>
      <title>Re: How to deploy an Agent</title>
      <link>https://community.databricks.com/t5/generative-ai/how-to-deploy-an-agent/m-p/151186#M1713</link>
      <description>&lt;P&gt;Hi&amp;nbsp;&lt;a href="https://community.databricks.com/t5/user/viewprofilepage/user-id/176516"&gt;@emma_s&lt;/a&gt;&amp;nbsp;.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;Exactly, for this reason I opened the discussion. I saw this recent approach and I didn't know this.&amp;nbsp;&lt;/P&gt;&lt;P&gt;I'll try also this new approach.&lt;/P&gt;</description>
      <pubDate>Tue, 17 Mar 2026 21:16:31 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/how-to-deploy-an-agent/m-p/151186#M1713</guid>
      <dc:creator>Ale_Armillotta</dc:creator>
      <dc:date>2026-03-17T21:16:31Z</dc:date>
    </item>
  </channel>
</rss>

