<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agents | Zhang Handuo's Site</title><link>https://handuo.top/tags/agents/</link><atom:link href="https://handuo.top/tags/agents/index.xml" rel="self" type="application/rss+xml"/><description>Agents</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sat, 10 Aug 2024 00:00:00 +0000</lastBuildDate><image><url>https://handuo.top/media/icon_hu_39ba2e8de423d957.png</url><title>Agents</title><link>https://handuo.top/tags/agents/</link></image><item><title>GMate - Agentic Marketing and Commerce</title><link>https://handuo.top/project/gmate/</link><pubDate>Sat, 10 Aug 2024 00:00:00 +0000</pubDate><guid>https://handuo.top/project/gmate/</guid><description>&lt;p&gt;GMate is an AI assistant for social-media marketing and commerce. At Watt, I helped evolve it from a fixed workflow into a closed-loop agent that uses personal preferences, factual data, and structured strategy experience to guide future actions.&lt;/p&gt;
&lt;p&gt;
&lt;figure &gt;
&lt;div class="flex justify-center "&gt;
&lt;div class="w-full" &gt;
&lt;img alt="GMate product screenshot"
srcset="https://handuo.top/project/gmate/screen01_hu_67198d9be06eb15d.webp 320w, https://handuo.top/project/gmate/screen01_hu_57ecb7e39bb672b8.webp 480w, https://handuo.top/project/gmate/screen01_hu_201f4173e4659db1.webp 760w"
sizes="(max-width: 480px) 100vw, (max-width: 768px) 90vw, (max-width: 1024px) 80vw, 760px"
src="https://handuo.top/project/gmate/screen01_hu_67198d9be06eb15d.webp"
width="760"
height="383"
loading="lazy" data-zoomable /&gt;&lt;/div&gt;
&lt;/div&gt;&lt;/figure&gt;
&lt;/p&gt;
&lt;p&gt;For the Xiaohongshu product released in December 2025, I led performance and reliability work, including parallel preloading, end-to-end observability, and retrieval improvements. The product recorded 7,875 uses and 426 active users in its launch month.&lt;/p&gt;
&lt;p&gt;For the TikTok Shop product-selection assistant, I designed a LangGraph-based multi-agent architecture and a browser tool combining DOM access with visual understanding. I also built tracing and retrieval-enhanced evaluation for the agent&amp;rsquo;s reasoning and outputs.&lt;/p&gt;
&lt;p&gt;Earlier work included an event knowledge graph connecting trending topics to more than 20,000 entities and a multimodal content engine for text, image, and video generation.&lt;/p&gt;</description></item></channel></rss>