<?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 Controlling Agent access to Tools and Tool access to Data Operations in Lakebase Discussions</title>
    <link>https://community.databricks.com/t5/lakebase-discussions/controlling-agent-access-to-tools-and-tool-access-to-data/m-p/152906#M80</link>
    <description>&lt;P&gt;I am building an agentic workflow.&amp;nbsp; This is a multi agent workflow - Plan, Reason, Act and Synthesize. Each agent has its own access to tools to take ACTIONS on data. Some of these agents are READ only, some can WRITE/UPDATE&lt;BR /&gt;&lt;BR /&gt;All data is resident within Unity Catalog when the initial access can be granted.&amp;nbsp;&lt;BR /&gt;&lt;BR /&gt;When the workflow executes and agents come up with dynamic plans I want to control the type of ACTIONS take on the data based on policy contraints. These are runtime Actions I want to control and monitor.&amp;nbsp; Some agents have read only access, some can write (to specific datasets), some can move data (under some conditions).&amp;nbsp;&lt;BR /&gt;&lt;BR /&gt;Is there a best practices approach to control agentic worflows at runtime?&amp;nbsp;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;/P&gt;</description>
    <pubDate>Wed, 01 Apr 2026 13:15:40 GMT</pubDate>
    <dc:creator>smithsonian</dc:creator>
    <dc:date>2026-04-01T13:15:40Z</dc:date>
    <item>
      <title>Controlling Agent access to Tools and Tool access to Data Operations</title>
      <link>https://community.databricks.com/t5/lakebase-discussions/controlling-agent-access-to-tools-and-tool-access-to-data/m-p/152906#M80</link>
      <description>&lt;P&gt;I am building an agentic workflow.&amp;nbsp; This is a multi agent workflow - Plan, Reason, Act and Synthesize. Each agent has its own access to tools to take ACTIONS on data. Some of these agents are READ only, some can WRITE/UPDATE&lt;BR /&gt;&lt;BR /&gt;All data is resident within Unity Catalog when the initial access can be granted.&amp;nbsp;&lt;BR /&gt;&lt;BR /&gt;When the workflow executes and agents come up with dynamic plans I want to control the type of ACTIONS take on the data based on policy contraints. These are runtime Actions I want to control and monitor.&amp;nbsp; Some agents have read only access, some can write (to specific datasets), some can move data (under some conditions).&amp;nbsp;&lt;BR /&gt;&lt;BR /&gt;Is there a best practices approach to control agentic worflows at runtime?&amp;nbsp;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;/P&gt;</description>
      <pubDate>Wed, 01 Apr 2026 13:15:40 GMT</pubDate>
      <guid>https://community.databricks.com/t5/lakebase-discussions/controlling-agent-access-to-tools-and-tool-access-to-data/m-p/152906#M80</guid>
      <dc:creator>smithsonian</dc:creator>
      <dc:date>2026-04-01T13:15:40Z</dc:date>
    </item>
  </channel>
</rss>

