<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Khang Publication</title><description>Field notes on building AI systems, agent workflows, evaluations, and applied analytics.</description><link>https://www.im-khang.com/</link><language>en-us</language><item><title>How I Evaluated an Ecommerce Analytics Agent: Answers, SQL, Tool Use, and Safety</title><link>https://www.im-khang.com/blogs/how-i-evaluated-an-ecommerce-analytics-agent-answers-sql-tool-use-and-safety/</link><guid isPermaLink="true">https://www.im-khang.com/blogs/how-i-evaluated-an-ecommerce-analytics-agent-answers-sql-tool-use-and-safety/</guid><description>A public Olist case study covering answer quality, tool use, SQL safety, and the limits of local agent evaluations.</description><pubDate>Wed, 16 Sep 2026 00:00:00 GMT</pubDate></item><item><title>How Archify Turns Codebase Maps Into Reviewed Technical Artifacts</title><link>https://www.im-khang.com/blogs/archify-codebase-maps-reviewed-technical-artifacts/</link><guid isPermaLink="true">https://www.im-khang.com/blogs/archify-codebase-maps-reviewed-technical-artifacts/</guid><description>A research-based guide to Archify&apos;s typed diagram workflow for AI-assisted codebases.</description><pubDate>Tue, 01 Sep 2026 00:00:00 GMT</pubDate></item></channel></rss>