<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>External on AI Agents News</title>
    <link>https://aiagentsnews.top/tags/external/</link>
    <description>Recent content in External on AI Agents News</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Sat, 25 Jul 2026 12:45:19 +0000</lastBuildDate>
    <atom:link href="https://aiagentsnews.top/tags/external/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Agent architecture: five components before scaling</title>
      <link>https://aiagentsnews.top/posts/agent-architecture-five-components-before-scaling/</link>
      <pubDate>Mon, 20 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agent-architecture-five-components-before-scaling/</guid>
      <description>Avoid infinite loops by defining the five components an effective agent requires. Learn how retrieval, tools, and memory prevent chaotic outputs.</description>
    </item>
    <item>
      <title>Tool interfaces beat static training cutoffs</title>
      <link>https://aiagentsnews.top/posts/tool-interfaces-beat-static-training-cutoffs/</link>
      <pubDate>Sun, 19 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/tool-interfaces-beat-static-training-cutoffs/</guid>
      <description>Executable functions let models bypass training cutoffs to fetch live data, preventing hallucinations when users request current events or facts.</description>
    </item>
    <item>
      <title>Agentic testing: Stop false Shopify failures now</title>
      <link>https://aiagentsnews.top/posts/agentic-testing-stop-false-shopify-failures-now/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agentic-testing-stop-false-shopify-failures-now/</guid>
      <description>By 2030, 80% of enterprise software will be multimodal. Learn to validate agent reasoning with component isolation and trajectory analysis.</description>
    </item>
    <item>
      <title>Function calling turns LLMs into real agents</title>
      <link>https://aiagentsnews.top/posts/function-calling-turns-llms-into-real-agents/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/function-calling-turns-llms-into-real-agents/</guid>
      <description>Learn how function calling converts vague intent into structured JSON requests, enabling agents to fetch external data instead of guessing.</description>
    </item>
    <item>
      <title>Grok function calling: atomic tool calls explained</title>
      <link>https://aiagentsnews.top/posts/grok-function-calling-atomic-tool-calls-explained/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/grok-function-calling-atomic-tool-calls-explained/</guid>
      <description>Grok 4.3 returns tool calls in single chunks, enabling atomic parsing. Learn how strict JSON schemas and local execution secure external data flows.</description>
    </item>
    <item>
      <title>Function calling: turning static AI into action</title>
      <link>https://aiagentsnews.top/posts/function-calling-turning-static-ai-into-action/</link>
      <pubDate>Mon, 06 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/function-calling-turning-static-ai-into-action/</guid>
      <description>Learn how function calling converts natural language into structured JSON for 3 specific use cases: actions, knowledge, and capabilities.</description>
    </item>
    <item>
      <title>Tool use patterns: how agents run external code</title>
      <link>https://aiagentsnews.top/posts/tool-use-patterns-how-agents-run-external-code/</link>
      <pubDate>Sun, 05 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/tool-use-patterns-how-agents-run-external-code/</guid>
      <description>Learn how the tool use pattern lets agents bypass static data limits by executing external code and querying 177,000 tracked tools safely.</description>
    </item>
    <item>
      <title>Agent prompt injections: Stop trusting README files</title>
      <link>https://aiagentsnews.top/posts/agent-prompt-injections-stop-trusting-readme-files/</link>
      <pubDate>Tue, 23 Jun 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agent-prompt-injections-stop-trusting-readme-files/</guid>
      <description>Mitchell Hashimoto seeds AGENTS.md with traps to prove agents blindly trust external text. Learn why 1 corrupted file causes RCE.</description>
    </item>
    <item>
      <title>Agent runtime beats clever prompt engineering</title>
      <link>https://aiagentsnews.top/posts/agent-runtime-beats-clever-prompt-engineering/</link>
      <pubDate>Tue, 23 Jun 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agent-runtime-beats-clever-prompt-engineering/</guid>
      <description>Most agent projects fail by 2027 due to bad architecture. Learn why static prompts collapse and how an external loop fixes real tasks.</description>
    </item>
  </channel>
</rss>
