<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - AI Architecture - Articles</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ AI Architecture Articles feed</description>
    <item>
      <title>Article: Systemic Approach to Memory, Knowledge, and Context in Agentic AI Architectures</title>
      <link>https://www.infoq.com/articles/agentic-ai-context-memory-knowledge/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=AI+Architecture-articles</link>
      <description>&lt;img src="https://res.infoq.com/articles/agentic-ai-context-memory-knowledge/en/headerimage/agentic-ai-context-memory-knowledge-header-1793173492489.jpg"/&gt;&lt;p&gt;The article argues that reliable agentic AI architecture depends on a context engine that selects, injects, compresses, and expires information before it reaches the model. It separates context, memory, and knowledge, and recommends tiered memory, curated knowledge, and token budgeting. It also covers common anti-patterns, such as context stuffing and stale data loops, with mitigations.&lt;/p&gt; &lt;i&gt;By Adi Polak&lt;/i&gt;</description>
      <category>Agentic AI Architecture</category>
      <category>Large language models</category>
      <category>Context Engineering</category>
      <category>Memory</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>Architecture &amp; Design</category>
      <category>article</category>
      <pubDate>Mon, 02 Nov 2026 11:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/articles/agentic-ai-context-memory-knowledge/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=AI+Architecture-articles</guid>
      <dc:creator>Adi Polak</dc:creator>
      <dc:date>2026-11-02T11:00:00Z</dc:date>
      <dc:identifier>/articles/agentic-ai-context-memory-knowledge/en</dc:identifier>
    </item>
    <item>
      <title>Article: The Evolution of Agentic Harnesses: from Chains to Graph to Code</title>
      <link>https://www.infoq.com/articles/agentic-ai-architecture-harness-evolution/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=AI+Architecture-articles</link>
      <description>&lt;img src="https://res.infoq.com/articles/agentic-ai-architecture-harness-evolution/en/headerimage/agentic-ai-architecture-harness-evolution-header-1792744961862.jpg"/&gt;&lt;p&gt;Agentic LLM systems have moved from linear prompt chains to graph-based workflows and, more recently, code-executing harnesses. Chains are simple but fragile, graphs add branching, retries, and validation, and code harnesses verify outputs through execution. The article advises validating model outputs and choosing the least complex design that meets reliability, speed, and cost needs.&lt;/p&gt; &lt;i&gt;By Karthik Ramgopal&lt;/i&gt;</description>
      <category>Agentic AI Architecture</category>
      <category>Model Context Protocol (MCP)</category>
      <category>Large language models</category>
      <category>Retrieval-Augmented Generation</category>
      <category>LangChain</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>Architecture &amp; Design</category>
      <category>article</category>
      <pubDate>Mon, 26 Oct 2026 11:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/articles/agentic-ai-architecture-harness-evolution/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=AI+Architecture-articles</guid>
      <dc:creator>Karthik Ramgopal</dc:creator>
      <dc:date>2026-10-26T11:00:00Z</dc:date>
      <dc:identifier>/articles/agentic-ai-architecture-harness-evolution/en</dc:identifier>
    </item>
  </channel>
</rss>
