<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI Agents on Yosgi</title><link>https://yosgi.github.io/en/tags/ai-agents/</link><description>Recent content in AI Agents on Yosgi</description><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 29 Jun 2026 09:20:51 +0000</lastBuildDate><atom:link href="https://yosgi.github.io/en/tags/ai-agents/index.xml" rel="self" type="application/rss+xml"/><item><title>Using AI Agents for Asset Recognition and Annotation in 3D Scenes (Part 3)</title><link>https://yosgi.github.io/en/post/using-ai-agents-for-asset-recognition-and-annotation-in-3d-scenes-part-3/</link><pubDate>Sun, 21 Jun 2026 10:00:00 +1200</pubDate><guid>https://yosgi.github.io/en/post/using-ai-agents-for-asset-recognition-and-annotation-in-3d-scenes-part-3/</guid><description>Making scan results land in the right place</description></item><item><title>Using AI Agents for Asset Recognition and Annotation in 3D Scenes (Part 2)</title><link>https://yosgi.github.io/en/post/using-ai-agents-for-asset-recognition-and-annotation-in-3d-scenes-part-2/</link><pubDate>Sat, 20 Jun 2026 19:11:11 +1200</pubDate><guid>https://yosgi.github.io/en/post/using-ai-agents-for-asset-recognition-and-annotation-in-3d-scenes-part-2/</guid><description>How we split 2D detection and 3D verification into two stages to reduce false positives in digital twin asset annotation, and how that revealed the next recall bottleneck</description></item><item><title>Using AI Agents for Asset Recognition and Annotation in 3D Scenes</title><link>https://yosgi.github.io/en/post/using-ai-agents-for-asset-recognition-and-annotation-in-3d-scenes-part-1/</link><pubDate>Fri, 19 Jun 2026 09:46:11 +1200</pubDate><guid>https://yosgi.github.io/en/post/using-ai-agents-for-asset-recognition-and-annotation-in-3d-scenes-part-1/</guid><description>How we turned free-form 3D exploration into measurable coverage scanning and improved valve inventory recall in a digital twin factory from around 40% to around 90%</description></item><item><title>Why Tool and Code Fail Differently in Agent Systems（2）</title><link>https://yosgi.github.io/en/post/why-tool-and-code-fail-differently-in-agent-systems2/</link><pubDate>Mon, 25 May 2026 14:50:20 +1200</pubDate><guid>https://yosgi.github.io/en/post/why-tool-and-code-fail-differently-in-agent-systems2/</guid><description>Tool and Code do not just differ in expressiveness; they also fail at different times. This article explains why multi-round Agent systems amplify that difference.</description></item><item><title>Your Agent Is Not Inconsistent Because It Is Dumb. It Just Has Too Many Tool Paths.</title><link>https://yosgi.github.io/en/post/your-agent-is-not-inconsistent-because-it-is-dumb-it-just-has-too-many-tool-paths/</link><pubDate>Thu, 21 May 2026 18:20:04 +1200</pubDate><guid>https://yosgi.github.io/en/post/your-agent-is-not-inconsistent-because-it-is-dumb-it-just-has-too-many-tool-paths/</guid><description>Multi-tool agents become unreliable when the same task takes different tool paths each time. This article explains why Skills should preserve validated execution paths, not one-off results, and why those Skills need to evolve over time.</description></item></channel></rss>