<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - Agentic AI Architecture</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ Agentic AI Architecture feed</description>
    <item>
      <title>Uber’s Legal AI Agent Cuts Contract Review Time by 20% with Rules and RAG</title>
      <link>https://www.infoq.com/news/2026/11/uber-legal-redlining-agent/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Agentic+AI+Architecture</link>
      <description>&lt;img src="https://www.infoq.com/styles/static/images/logo/logo_bigger.jpg"/&gt;&lt;p&gt;Uber’s Legal Redlining Agent reviews contract changes in Microsoft Word using RAG, historical lawyer feedback, and deterministic policy rules. Built with LangGraph, OpenSearch, and Redis, the system reports more than 20% lower average contract review time and 91% accuracy in AI-generated decisions. Uber is exploring agentic harnesses, skills, legal ontologies, and knowledge graphs.&lt;/p&gt; &lt;i&gt;By Leela Kumili&lt;/i&gt;</description>
      <category>Software Engineering</category>
      <category>OpenSearch</category>
      <category>Claude</category>
      <category>Legal Matters</category>
      <category>Agentic AI Architecture</category>
      <category>Artificial Intelligence</category>
      <category>Microsoft Office</category>
      <category>Retrieval-Augmented Generation</category>
      <category>Uber</category>
      <category>Redis</category>
      <category>Architecture &amp; Design</category>
      <category>Development</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>news</category>
      <pubDate>Mon, 16 Nov 2026 14:37:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/11/uber-legal-redlining-agent/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Agentic+AI+Architecture</guid>
      <dc:creator>Leela Kumili</dc:creator>
      <dc:date>2026-11-16T14:37:00Z</dc:date>
      <dc:identifier>/news/2026/11/uber-legal-redlining-agent/en</dc:identifier>
    </item>
    <item>
      <title>Article: Governed Autonomous Intelligence for Mission-Critical Utility</title>
      <link>https://www.infoq.com/articles/utility-governed-autonomous-intelligence-ai/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Agentic+AI+Architecture</link>
      <description>&lt;img src="https://res.infoq.com/articles/utility-governed-autonomous-intelligence-ai/en/headerimage/utility-governed-autonomous-intelligence-ai-header-1793368487796.jpg"/&gt;&lt;p&gt;The article describes an architecture for agentic AI in regulated utility operations. Agents reason and propose actions, but a deterministic policy gate and a governed tool gateway control execution, with human approval where required. It covers an AWS reference implementation, grounding in runbooks, governed prediction, outcome validation, audit evidence, and phased autonomy.&lt;/p&gt; &lt;i&gt;By Purnang Borah&lt;/i&gt;</description>
      <category>Observability</category>
      <category>Agentic AI Architecture</category>
      <category>Governance</category>
      <category>AI Architecture</category>
      <category>Operating Systems</category>
      <category>Operations management</category>
      <category>Operational Intelligence</category>
      <category>Large language models</category>
      <category>Architecture &amp; Design</category>
      <category>article</category>
      <pubDate>Mon, 16 Nov 2026 11:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/articles/utility-governed-autonomous-intelligence-ai/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Agentic+AI+Architecture</guid>
      <dc:creator>Purnang Borah</dc:creator>
      <dc:date>2026-11-16T11:00:00Z</dc:date>
      <dc:identifier>/articles/utility-governed-autonomous-intelligence-ai/en</dc:identifier>
    </item>
    <item>
      <title>Google Open Sources Ambient Quality Agent (AQuA) to Diagnose Production AI Agent Failures</title>
      <link>https://www.infoq.com/news/2026/11/google-ambient-agent-prod/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Agentic+AI+Architecture</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/11/google-ambient-agent-prod/en/headerimage/generatedHeaderImage-1792894383462.jpg"/&gt;&lt;p&gt;Google has open-sourced AQuA, a reference implementation that analyzes production AI agent sessions, verifies recurring failure patterns, and investigates root causes against deployed source snapshots. In a 32-session replay, developers reduced seat selection bypasses from 15 sessions to two and dietary preference omissions from seven to zero after prompt changes.&lt;/p&gt; &lt;i&gt;By Leela Kumili&lt;/i&gt;</description>
      <category>Observability</category>
      <category>Google</category>
      <category>Agentic AI Architecture</category>
      <category>AI Architecture</category>
      <category>Quality</category>
      <category>Monitoring</category>
      <category>Architecture &amp; Design</category>
      <category>Development</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>news</category>
      <pubDate>Fri, 13 Nov 2026 13:53:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/11/google-ambient-agent-prod/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Agentic+AI+Architecture</guid>
      <dc:creator>Leela Kumili</dc:creator>
      <dc:date>2026-11-13T13:53:00Z</dc:date>
      <dc:identifier>/news/2026/11/google-ambient-agent-prod/en</dc:identifier>
    </item>
    <item>
      <title>JioHotstar Benchmarks Knowledge Bases for AI Coding Agents</title>
      <link>https://www.infoq.com/news/2026/11/jiohotstar-codingagent-retrieval/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Agentic+AI+Architecture</link>
      <description>&lt;img src="https://www.infoq.com/styles/static/images/logo/logo_bigger.jpg"/&gt;&lt;p&gt;JioHotstar evaluated 6 approaches to code retrieval for AI coding agents using SWE, CodeScale Bench, and an internal question-answering harness. Structural search performed well on concrete tasks, while semantic retrieval helped with ambiguous requirements. The findings highlight trade-offs in accuracy, token use, and tool design, underscoring the need to match retrieval tools to task types.&lt;/p&gt; &lt;i&gt;By Leela Kumili&lt;/i&gt;</description>
      <category>Agentic AI Architecture</category>
      <category>Architecture</category>
      <category>Model Context Protocol (MCP)</category>
      <category>AI coding agents</category>
      <category>Software Engineering</category>
      <category>Search</category>
      <category>Retrieval-Augmented Generation</category>
      <category>Benchmark</category>
      <category>Architecture &amp; Design</category>
      <category>Development</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>news</category>
      <pubDate>Wed, 11 Nov 2026 14:28:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/11/jiohotstar-codingagent-retrieval/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Agentic+AI+Architecture</guid>
      <dc:creator>Leela Kumili</dc:creator>
      <dc:date>2026-11-11T14:28:00Z</dc:date>
      <dc:identifier>/news/2026/11/jiohotstar-codingagent-retrieval/en</dc:identifier>
    </item>
    <item>
      <title>Article: Agentic AI Architecture: Current Challenges and Future Opportunities</title>
      <link>https://www.infoq.com/articles/agentic-ai-architecture-challenges-opportunities/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Agentic+AI+Architecture</link>
      <description>&lt;img src="https://res.infoq.com/articles/agentic-ai-architecture-challenges-opportunities/en/headerimage/agentic-ai-architecture-challenges-opportunities-header-1793709540690.jpg"/&gt;&lt;p&gt;Agentic AI architecture extends microservices and cloud-native architectures with AI agents that work with context, memory, and protocols such as MCP and A2A. The article covers bounded-context integration, task-dependent coordination strategies, new security risks, and observability needs. It expects gradual adoption alongside existing architectures, with platforms absorbing common components.&lt;/p&gt; &lt;i&gt;By Rafał Gancarz&lt;/i&gt;</description>
      <category>Agentic AI Architecture</category>
      <category>Model Context Protocol (MCP)</category>
      <category>Retrieval-Augmented Generation</category>
      <category>Large language models</category>
      <category>Context Engineering</category>
      <category>Architecture &amp; Design</category>
      <category>article</category>
      <pubDate>Mon, 09 Nov 2026 10:52:00 GMT</pubDate>
      <guid>https://www.infoq.com/articles/agentic-ai-architecture-challenges-opportunities/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Agentic+AI+Architecture</guid>
      <dc:creator>Rafał Gancarz</dc:creator>
      <dc:date>2026-11-09T10:52:00Z</dc:date>
      <dc:identifier>/articles/agentic-ai-architecture-challenges-opportunities/en</dc:identifier>
    </item>
  </channel>
</rss>
