<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Function on AI Agents News</title>
    <link>https://aiagentsnews.top/tags/function/</link>
    <description>Recent content in Function on AI Agents News</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Sun, 26 Jul 2026 10:46:34 +0000</lastBuildDate>
    <atom:link href="https://aiagentsnews.top/tags/function/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Delegation contracts define A2A agent workflows</title>
      <link>https://aiagentsnews.top/posts/agent-delegation-six-distinct-production-patterns/</link>
      <pubDate>Wed, 22 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agent-delegation-six-distinct-production-patterns/</guid>
      <description>A2A delegation is no longer science fiction. It is a production pattern managing bot fleets today.</description>
    </item>
    <item>
      <title>GPT5.6 tool calling: Why the client-owned loop matters</title>
      <link>https://aiagentsnews.top/posts/gpt56-tool-calling-why-the-client-owned-loop-matters/</link>
      <pubDate>Wed, 22 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/gpt56-tool-calling-why-the-client-owned-loop-matters/</guid>
      <description>GPT5.6 returns tool names, not code. Learn why the client-owned function loop and strict schemas are non-negotiable for autonomous systems.</description>
    </item>
    <item>
      <title>Function tools defined: custom code vs sandboxed runtimes</title>
      <link>https://aiagentsnews.top/posts/function-tools-defined-custom-code-vs-sandboxed-runtimes/</link>
      <pubDate>Sun, 19 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/function-tools-defined-custom-code-vs-sandboxed-runtimes/</guid>
      <description>Distinguish custom function tools from sandboxed Code Interpreter runtimes to prevent treating external connections as identical black boxes in agents.</description>
    </item>
    <item>
      <title>Tool use design: enabling real agent actions</title>
      <link>https://aiagentsnews.top/posts/tool-use-design-enabling-real-agent-actions/</link>
      <pubDate>Sun, 19 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/tool-use-design-enabling-real-agent-actions/</guid>
      <description>Learn how the Thought-Action-Observation loop powers 177,000+ tools, shifting agents from static text to modifying external system states safely.</description>
    </item>
    <item>
      <title>Function calling tools: 24 benchmarks explained</title>
      <link>https://aiagentsnews.top/posts/function-calling-tools-24-benchmarks-explained/</link>
      <pubDate>Sat, 18 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/function-calling-tools-24-benchmarks-explained/</guid>
      <description>BenchLM.ai evaluates function calling across 24 agentic benchmarks to measure precision in tool invocation and terminal task execution for AI agents.</description>
    </item>
    <item>
      <title>Delegation contracts define A2A agent workflows</title>
      <link>https://aiagentsnews.top/posts/delegation-contracts-define-a2a-agent-workflows/</link>
      <pubDate>Fri, 17 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/delegation-contracts-define-a2a-agent-workflows/</guid>
      <description>A2A delegation is no longer science fiction. It is a production pattern managing bot fleets today.</description>
    </item>
    <item>
      <title>Agent tools explained: six types for builders</title>
      <link>https://aiagentsnews.top/posts/agent-tools-explained-six-types-for-builders/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agent-tools-explained-six-types-for-builders/</guid>
      <description>Learn how six distinct agent tool categories range from low-risk search to high-risk desktop control, plus why Model Context Protocol matters.</description>
    </item>
    <item>
      <title>Function call data: Managing 346 token overhead</title>
      <link>https://aiagentsnews.top/posts/function-call-data-managing-346-token-overhead/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/function-call-data-managing-346-token-overhead/</guid>
      <description>Function calling adds 346 extra tokens per API call. Learn how strict JSON schemas and namespaces reduce this hidden architectural cost for agents.</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 explained: JSON plans, not code execution</title>
      <link>https://aiagentsnews.top/posts/function-calling-explained-json-plans-not-code-execution/</link>
      <pubDate>Mon, 13 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/function-calling-explained-json-plans-not-code-execution/</guid>
      <description>Learn how function calling uses structured JSON to anchor AI to real data, eliminating hallucinations through a strict four-step execution cycle.</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>React agents vs function calling: 2026 guide</title>
      <link>https://aiagentsnews.top/posts/react-agents-vs-function-calling-2026-guide/</link>
      <pubDate>Sun, 05 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/react-agents-vs-function-calling-2026-guide/</guid>
      <description>Compare ReAct&#39;s iterative reasoning loops against structured function calling for external API access in 2026 agent architectures.</description>
    </item>
    <item>
      <title>Function calling overhead: real token counts</title>
      <link>https://aiagentsnews.top/posts/function-calling-overhead-real-token-counts/</link>
      <pubDate>Fri, 03 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/function-calling-overhead-real-token-counts/</guid>
      <description>Function calling adds 346 tokens per call, inflating costs for high-volume agents. Learn how OpenAPI schemas and Gemini 3.5 Pro manage this overhead.</description>
    </item>
  </channel>
</rss>
