<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Agents on Chengyu Wang</title><link>https://chengyu.eu/tags/agents/</link><description>Recent content in Agents on Chengyu Wang</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 Chengyu</copyright><lastBuildDate>Fri, 30 Jan 2026 11:00:21 +0000</lastBuildDate><atom:link href="https://chengyu.eu/tags/agents/index.xml" rel="self" type="application/rss+xml"/><item><title>Two Days Deep in Moltbot: AI Is Reshaping the Deploy-Configure-Use Path</title><link>https://chengyu.eu/posts/moltbot-two-days-deploy-configure-use/</link><pubDate>Fri, 30 Jan 2026 11:00:21 +0000</pubDate><guid>https://chengyu.eu/posts/moltbot-two-days-deploy-configure-use/</guid><description>Watching an agent diagnose its own missed schedule, switch itself from passive to active wake mode, and confirm the fix — without me tracing a single step of it myself.</description></item><item><title>From Dragging Nodes to Stating Intent: Claude Skills Is Ending the Old AI Workflow Era</title><link>https://chengyu.eu/posts/claude-skills-vs-ai-workflows/</link><pubDate>Wed, 21 Jan 2026 10:00:12 +0000</pubDate><guid>https://chengyu.eu/posts/claude-skills-vs-ai-workflows/</guid><description>Why describing what you want in plain language and letting Claude auto-apply a Skill beats another afternoon spent wiring up nodes in Dify, n8n, or Coze.</description></item><item><title>Agents vs. Workflows: What's the Actual Difference?</title><link>https://chengyu.eu/posts/agents-vs-workflows/</link><pubDate>Fri, 13 Jun 2025 16:00:16 +0000</pubDate><guid>https://chengyu.eu/posts/agents-vs-workflows/</guid><description>A drag-and-drop OCR-plus-LLM tool got me thinking about where a workflow ends and an agent begins — with a simple three-question test.</description></item><item><title>Building a Smart Customer-Service Agent with Qwen-Agent</title><link>https://chengyu.eu/posts/qwen-agent-smart-customer-service/</link><pubDate>Wed, 11 Jun 2025 11:00:12 +0000</pubDate><guid>https://chengyu.eu/posts/qwen-agent-smart-customer-service/</guid><description>A telecom customer-service example — using Tools for live data lookups and a knowledge base for static rules, with an LLM deciding which to call.</description></item><item><title>LLM Agents 101</title><link>https://chengyu.eu/posts/llm-agents-basics/</link><pubDate>Tue, 30 Jul 2024 00:00:09 +0000</pubDate><guid>https://chengyu.eu/posts/llm-agents-basics/</guid><description>What an &amp;lsquo;agent&amp;rsquo; actually means in the context of large language models, and a worked example in a customer-service setting.</description></item></channel></rss>