<?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 State of AI Agents 2026: Lessons on Governance, Evaluations, and Scale in MVP Articles</title>
    <link>https://community.databricks.com/t5/mvp-articles/state-of-ai-agents-2026-lessons-on-governance-evaluations-and/m-p/149219#M85</link>
    <description>&lt;P&gt;The &lt;A href="https://www.databricks.com/resources/ebook/state-of-ai-agents" target="_self"&gt;Databricks State of AI Agents 2026 report&lt;/A&gt; highlights a clear reality: most AI pilots still fail to reach production, and governance and evaluation are the true differentiators.&lt;/P&gt;&lt;P&gt;In my &lt;A href="https://lovelytics.com/post/state-of-ai-agents-2026-lessons-on-governance-evaluation-and-scale/" target="_self"&gt;latest blog&lt;/A&gt;, I break down the key findings and share how we approach agentic systems at Lovelytics through evaluation-led development, deep SME involvement, DSPy-based optimization, and why Databricks provides the right open, governed foundation for production-scale AI.&lt;/P&gt;&lt;P&gt;If you are building or scaling AI agents in 2026, this is a conversation worth having.&lt;/P&gt;</description>
    <pubDate>Tue, 24 Feb 2026 22:52:50 GMT</pubDate>
    <dc:creator>Sudhir_G</dc:creator>
    <dc:date>2026-02-24T22:52:50Z</dc:date>
    <item>
      <title>State of AI Agents 2026: Lessons on Governance, Evaluations, and Scale</title>
      <link>https://community.databricks.com/t5/mvp-articles/state-of-ai-agents-2026-lessons-on-governance-evaluations-and/m-p/149219#M85</link>
      <description>&lt;P&gt;The &lt;A href="https://www.databricks.com/resources/ebook/state-of-ai-agents" target="_self"&gt;Databricks State of AI Agents 2026 report&lt;/A&gt; highlights a clear reality: most AI pilots still fail to reach production, and governance and evaluation are the true differentiators.&lt;/P&gt;&lt;P&gt;In my &lt;A href="https://lovelytics.com/post/state-of-ai-agents-2026-lessons-on-governance-evaluation-and-scale/" target="_self"&gt;latest blog&lt;/A&gt;, I break down the key findings and share how we approach agentic systems at Lovelytics through evaluation-led development, deep SME involvement, DSPy-based optimization, and why Databricks provides the right open, governed foundation for production-scale AI.&lt;/P&gt;&lt;P&gt;If you are building or scaling AI agents in 2026, this is a conversation worth having.&lt;/P&gt;</description>
      <pubDate>Tue, 24 Feb 2026 22:52:50 GMT</pubDate>
      <guid>https://community.databricks.com/t5/mvp-articles/state-of-ai-agents-2026-lessons-on-governance-evaluations-and/m-p/149219#M85</guid>
      <dc:creator>Sudhir_G</dc:creator>
      <dc:date>2026-02-24T22:52:50Z</dc:date>
    </item>
  </channel>
</rss>

