<?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 Monitoring a custom Agent (Responses) serving endpoint with an experiment on the Unity Catalog in Generative AI</title>
    <link>https://community.databricks.com/t5/generative-ai/monitoring-a-custom-agent-responses-serving-endpoint-with-an/m-p/172769#M2205</link>
    <description>&lt;P&gt;Hi,&lt;BR /&gt;&lt;BR /&gt;I have a Langgraph agent deployed in Databricks on a custom serving endpoint of type&amp;nbsp;&lt;SPAN&gt;Agent (Responses).&lt;BR /&gt;So far, I have been tracing this agent on a "classic" monitoring experiment. I was using an ad hoc job to sync those traces to a table in the Unity Catalog. But now, one can create an experiment with a location in the UC directly, which sounds handy for my purpose. However, after I redeploy the agent (I set the mlflow experiment to the new one with UC location before deploying and I set&amp;nbsp;&lt;/SPAN&gt;&lt;SPAN&gt;MLFLOW_EXPERIMENT_ID as en environment variable for the deployed entity) I cannot see any traces in the new experiment.&lt;BR /&gt;The only way I could ever make this work was creating a span from a notebook and running a non deployed agent from there.&lt;BR /&gt;Am I missing something? Has anyone succeeded to make it work who could help me out?&lt;BR /&gt;Thanks in advance for any help or suggestion &lt;span class="lia-unicode-emoji" title=":winking_face:"&gt;😉&lt;/span&gt;&lt;/SPAN&gt;&lt;/P&gt;</description>
    <pubDate>Mon, 12 Oct 2026 11:53:15 GMT</pubDate>
    <dc:creator>FantineM</dc:creator>
    <dc:date>2026-10-12T11:53:15Z</dc:date>
    <item>
      <title>Monitoring a custom Agent (Responses) serving endpoint with an experiment on the Unity Catalog</title>
      <link>https://community.databricks.com/t5/generative-ai/monitoring-a-custom-agent-responses-serving-endpoint-with-an/m-p/172769#M2205</link>
      <description>&lt;P&gt;Hi,&lt;BR /&gt;&lt;BR /&gt;I have a Langgraph agent deployed in Databricks on a custom serving endpoint of type&amp;nbsp;&lt;SPAN&gt;Agent (Responses).&lt;BR /&gt;So far, I have been tracing this agent on a "classic" monitoring experiment. I was using an ad hoc job to sync those traces to a table in the Unity Catalog. But now, one can create an experiment with a location in the UC directly, which sounds handy for my purpose. However, after I redeploy the agent (I set the mlflow experiment to the new one with UC location before deploying and I set&amp;nbsp;&lt;/SPAN&gt;&lt;SPAN&gt;MLFLOW_EXPERIMENT_ID as en environment variable for the deployed entity) I cannot see any traces in the new experiment.&lt;BR /&gt;The only way I could ever make this work was creating a span from a notebook and running a non deployed agent from there.&lt;BR /&gt;Am I missing something? Has anyone succeeded to make it work who could help me out?&lt;BR /&gt;Thanks in advance for any help or suggestion &lt;span class="lia-unicode-emoji" title=":winking_face:"&gt;😉&lt;/span&gt;&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Mon, 12 Oct 2026 11:53:15 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/monitoring-a-custom-agent-responses-serving-endpoint-with-an/m-p/172769#M2205</guid>
      <dc:creator>FantineM</dc:creator>
      <dc:date>2026-10-12T11:53:15Z</dc:date>
    </item>
    <item>
      <title>Re: Monitoring a custom Agent (Responses) serving endpoint with an experiment on the Unity Catalog</title>
      <link>https://community.databricks.com/t5/generative-ai/monitoring-a-custom-agent-responses-serving-endpoint-with-an/m-p/172872#M2207</link>
      <description>&lt;P&gt;When a deployed agent serving endpoint fails to log traces to a Unity Catalog-backed experiment, it is typically due to permissions or environment configuration issues. First, ensure that the service principal running the serving endpoint has explicit USE_CATALOG, USE_SCHEMA, and write permissions on the target Unity Catalog schema. Second, verify that the environment variables passed to the endpoint include MLFLOW_TRACKING_URI=databricks alongside the correct experiment path/name configuration (using MLFLOW_EXPERIMENT_NAME rather than just MLFLOW_EXPERIMENT_ID), as model serving containers require proper tracking URI context to authenticate and route OpenTelemetry/MLflow traces to Unity Catalog.&lt;/P&gt;</description>
      <pubDate>Tue, 13 Oct 2026 04:43:28 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/monitoring-a-custom-agent-responses-serving-endpoint-with-an/m-p/172872#M2207</guid>
      <dc:creator>tamara48wells</dc:creator>
      <dc:date>2026-10-13T04:43:28Z</dc:date>
    </item>
    <item>
      <title>Re: Monitoring a custom Agent (Responses) serving endpoint with an experiment on the Unity Catalog</title>
      <link>https://community.databricks.com/t5/generative-ai/monitoring-a-custom-agent-responses-serving-endpoint-with-an/m-p/172939#M2210</link>
      <description>&lt;P&gt;Hi! Thank you so much for your reply!&lt;BR /&gt;So in the end, just adding&amp;nbsp;&lt;SPAN&gt;MLFLOW_TRACKING_URI as env variables to the entity did the trick. Permissions were already set properly.&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Tue, 13 Oct 2026 10:45:14 GMT</pubDate>
      <guid>https://community.databricks.com/t5/generative-ai/monitoring-a-custom-agent-responses-serving-endpoint-with-an/m-p/172939#M2210</guid>
      <dc:creator>FantineM</dc:creator>
      <dc:date>2026-10-13T10:45:14Z</dc:date>
    </item>
  </channel>
</rss>

