<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Apache SkyWalking – AI</title>
    <link>https://skywalking.apache.org/tags/ai/</link>
    <description>Recent ai posts from Apache SkyWalking</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-US</language>
    <lastBuildDate>Thu, 15 Oct 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://skywalking.apache.org/tags/ai/feed.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>How Good Are LLM Answers? Bringing Model Quality into SkyWalking Observability</title>
      <link>https://skywalking.apache.org/blog/2026-10-15-llm-as-judge/</link>
      <pubDate>Thu, 15 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/blog/2026-10-15-llm-as-judge/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">peachisai</dc:creator>
      <category>AI</category>
      <category>Metrics</category>
      <category>Tracing</category>
      <description>Learn how the upcoming SkyWalking 11.1.0 release uses LLM-as-Judge to evaluate GenAI span input and output messages asynchronously and connect the results to evaluation records, metrics, and traces.</description>
    </item>
    <item>
      <title>LLM 回答得好不好？SkyWalking 用 LLM-as-Judge 评估线上回答</title>
      <link>https://skywalking.apache.org/zh/2026-10-15-llm-as-judge/</link>
      <pubDate>Thu, 15 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/zh/2026-10-15-llm-as-judge/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">peachisai</dc:creator>
      <category>AI</category>
      <category>Metrics</category>
      <category>Tracing</category>
      <description>SkyWalking 11.1.0 即将支持 LLM-as-Judge：异步评估 GenAI Span 中的输入和输出消息，生成评估记录并关联原始 Trace，SCORE 任务还会产生质量指标。</description>
    </item>
    <item>
      <title>Recorded as the Session Runs, Kept When It Ends: LangGraph on Amazon Bedrock AgentCore</title>
      <link>https://skywalking.apache.org/blog/2026-10-10-ai-sessionizer-agentcore/</link>
      <pubDate>Sat, 10 Oct 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/blog/2026-10-10-ai-sessionizer-agentcore/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Sheng Wu</dc:creator>
      <category>AI</category>
      <category>Engineering</category>
      <category>Community</category>
      <description>Run a LangGraph agent on Amazon Bedrock AgentCore Runtime and record every turn, model prompt, tool call and file change in Apache SkyWalking AI Sessionizer while the session runs, kept after it ends, with no change to the agent&#39;s logic.</description>
    </item>
    <item>
      <title>From Claude Code to Your Own Agent: Capture and Replay LangChain and LangGraph Conversations</title>
      <link>https://skywalking.apache.org/blog/2026-09-23-ai-sessionizer-langchain-langgraph/</link>
      <pubDate>Wed, 23 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/blog/2026-09-23-ai-sessionizer-langchain-langgraph/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Sheng Wu</dc:creator>
      <category>AI</category>
      <category>Engineering</category>
      <category>Community</category>
      <description>Build a LangGraph agent on Amazon Bedrock, point its tracing client at Apache SkyWalking AI Sessionizer, and replay every turn, tool call, sub-agent and model request without changing the application.</description>
    </item>
    <item>
      <title>Beyond Replay: Metrics and Change Detection for Your Claude Code Sessions</title>
      <link>https://skywalking.apache.org/blog/2026-09-12-ai-sessionizer-workspace-changes/</link>
      <pubDate>Sat, 12 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/blog/2026-09-12-ai-sessionizer-workspace-changes/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Sheng Wu</dc:creator>
      <category>AI</category>
      <category>Engineering</category>
      <category>Community</category>
      <description>Understand Claude Code usage across sessions and machines, replay recorded work, and inspect file changes with their tool calls and source evidence.</description>
    </item>
    <item>
      <title>不止于回放：看清 Claude Code 的用量与文件变更</title>
      <link>https://skywalking.apache.org/zh/2026-09-12-ai-sessionizer-workspace-changes/</link>
      <pubDate>Sat, 12 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/zh/2026-09-12-ai-sessionizer-workspace-changes/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">吴晟</dc:creator>
      <category>AI</category>
      <category>Engineering</category>
      <category>Community</category>
      <description>汇总多次会话、多台机器上的 Claude Code 用量，结合对话、工具调用和文件差异，看清智能体做了什么、修改了什么，以及消耗了哪些资源。</description>
    </item>
    <item>
      <title>Replay Claude Code Sessions Without Plugins or Configuration Changes</title>
      <link>https://skywalking.apache.org/blog/2026-09-03-ai-sessionizer-first-look/</link>
      <pubDate>Thu, 03 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/blog/2026-09-03-ai-sessionizer-first-look/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Sheng Wu</dc:creator>
      <category>AI</category>
      <category>Engineering</category>
      <category>Community</category>
      <description>Replay existing Claude Code sessions with Apache SkyWalking AI Sessionizer: explore conversations, tool calls, and child-agent activity without installing a Claude Code plugin or changing its configuration.</description>
    </item>
    <item>
      <title>Meet Horizon UI · The AI Assistant: Ask Your Observability Data in Plain Language</title>
      <link>https://skywalking.apache.org/blog/2026-07-06-horizon-ui-ai-assistant/</link>
      <pubDate>Mon, 06 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/blog/2026-07-06-horizon-ui-ai-assistant/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Sheng Wu</dc:creator>
      <category>Release</category>
      <category>AI</category>
      <category>Cloud Native</category>
      <description>Horizon UI&#39;s new AI Assistant answers questions about your live system with the same charts, topology and tables as the UI — read-only, permission-scoped, and running on a cost-efficient model you bring yourself.</description>
    </item>
    <item>
      <title>认识 Horizon UI · AI Assistant：用日常语言查询你的可观测性数据</title>
      <link>https://skywalking.apache.org/zh/2026-07-06-horizon-ui-ai-assistant/</link>
      <pubDate>Mon, 06 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/zh/2026-07-06-horizon-ui-ai-assistant/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">吴晟</dc:creator>
      <category>Release</category>
      <category>AI</category>
      <category>Cloud Native</category>
      <description>Horizon UI 新增的 AI Assistant 可以用和 UI 相同的图表、拓扑和表格回答运行中系统的问题；它只读、按权限返回结果，并运行在你自己接入的高性价比模型上。</description>
    </item>
    <item>
      <title>Monitoring LLM Applications with SkyWalking 10.4: Insights into Performance and Cost</title>
      <link>https://skywalking.apache.org/blog/2026-04-05-virtual-genai-monitoring/</link>
      <pubDate>Sun, 05 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/blog/2026-04-05-virtual-genai-monitoring/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">YiMing Shao</dc:creator>
      <category>AI</category>
      <category>Metrics</category>
      <description>SkyWalking 10.4 introduces the Virtual GenAI dashboard. This article explores how to use this new feature to monitor and optimize LLM integrations.</description>
    </item>
    <item>
      <title>基于 SkyWalking 10.4 的大模型应用监控：洞察 LLM 的性能与成本</title>
      <link>https://skywalking.apache.org/zh/2026-04-05-virtual-genai-monitoring/</link>
      <pubDate>Sun, 05 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/zh/2026-04-05-virtual-genai-monitoring/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">邵一鸣</dc:creator>
      <category>AI</category>
      <category>Engineering</category>
      <category>Tracing</category>
      <description>SkyWalking 10.4 增加了 Virtual GenAI 观测面板,本文将介绍该新特性的使用。</description>
    </item>
    <item>
      <title>Monitoring Envoy AI Gateway with Apache SkyWalking</title>
      <link>https://skywalking.apache.org/blog/2026-04-02-envoy-ai-gateway-monitoring/</link>
      <pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/blog/2026-04-02-envoy-ai-gateway-monitoring/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Sheng Wu</dc:creator>
      <category>AI</category>
      <category>Cloud Native</category>
      <description>Set up full-stack observability for your AI/LLM traffic using Envoy AI Gateway, SkyWalking OAP 10.4.0, and BanyanDB 0.10.0.</description>
    </item>
    <item>
      <title>用 Apache SkyWalking 监控 Envoy AI Gateway</title>
      <link>https://skywalking.apache.org/zh/2026-04-02-envoy-ai-gateway-monitoring/</link>
      <pubDate>Thu, 02 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/zh/2026-04-02-envoy-ai-gateway-monitoring/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">吴晟</dc:creator>
      <category>AI</category>
      <category>Cloud Native</category>
      <category>Engineering</category>
      <description>基于 Envoy AI Gateway、SkyWalking OAP 10.4.0 和 BanyanDB 0.10.0，搭建面向 AI/LLM 流量的全栈可观测方案。</description>
    </item>
    <item>
      <title>AI Coding 如何重塑软件架构师的工作方式</title>
      <link>https://skywalking.apache.org/zh/2026-03-13-how-ai-changed-the-economics-of-architecture/</link>
      <pubDate>Sun, 15 Mar 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/zh/2026-03-13-how-ai-changed-the-economics-of-architecture/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">吴晟</dc:creator>
      <category>AI</category>
      <category>Profiling</category>
      <category>Cloud Native</category>
      <description>以 SkyWalking GraalVM Distro 为例，聊聊 AI Coding 如何让更好的架构方案更容易被验证、打磨并真正落地。</description>
    </item>
    <item>
      <title>How AI Changed the Economics of Architecture</title>
      <link>https://skywalking.apache.org/blog/2026-03-13-how-ai-changed-the-economics-of-architecture/</link>
      <pubDate>Fri, 13 Mar 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/blog/2026-03-13-how-ai-changed-the-economics-of-architecture/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Sheng Wu</dc:creator>
      <category>Cloud Native</category>
      <category>Profiling</category>
      <category>AI</category>
      <description>A case study in how AI changed the economics of architecture in a mature  project by making better designs cheaper to prototype, validate, and refine.</description>
    </item>
    <item>
      <title>Agentic Vibe Coding in a Mature OSS Project: What Worked, What Didn&#39;t</title>
      <link>https://skywalking.apache.org/blog/2026-03-08-agentic-vibe-coding/</link>
      <pubDate>Sun, 08 Mar 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/blog/2026-03-08-agentic-vibe-coding/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">Sheng Wu</dc:creator>
      <category>AI</category>
      <category>Engineering</category>
      <category>Community</category>
      <description>What happens when you apply agentic AI coding to a mature open-source project with real users, real compatibility contracts, and real consequences? 77K lines changed in 5 weeks — here&#39;s what I learned.</description>
    </item>
    <item>
      <title>在成熟开源大型项目中实践 Agentic Vibe Coding：软件工程与工程控制论还在延续</title>
      <link>https://skywalking.apache.org/zh/2026-03-08-agentic-vibe-coding/</link>
      <pubDate>Sun, 08 Mar 2026 00:00:00 +0000</pubDate>
      <guid>https://skywalking.apache.org/zh/2026-03-08-agentic-vibe-coding/</guid>
      <dc:creator xmlns:dc="http://purl.org/dc/elements/1.1/">吴晟</dc:creator>
      <category>AI</category>
      <category>Engineering</category>
      <category>Community</category>
      <description>当你把 AI 智能体编程应用到一个有真实用户、广泛运用、API 被充分集成的成熟开源项目时，我在 5 周改了 7.7 万行代码，里面到底用到了哪些方法？这是我的实战总结。</description>
    </item>
  </channel>
</rss>
