<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Home</title><description>Opinions on engineering, from a decade of shipping applied AI in places where being wrong was expensive.</description><link>https://inprinciple.sh/</link><item><title>Output is not Signal</title><link>https://inprinciple.sh/blog/output-is-not-signal/</link><guid isPermaLink="true">https://inprinciple.sh/blog/output-is-not-signal/</guid><description>On OpenClaw, the iceberg of tacit knowledge, and which incompleteness you can live with before an agent is truly useful.</description><pubDate>Sun, 19 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Context vs Knowledge Graphs</title><link>https://inprinciple.sh/blog/context-vs-knowledge-graphs/</link><guid isPermaLink="true">https://inprinciple.sh/blog/context-vs-knowledge-graphs/</guid><description>Knowledge graphs masquerading as context graphs, why retrieval-augmented agents fall apart at the seams, and the tri-temporal substrate hiding underneath.</description><pubDate>Tue, 14 Apr 2026 00:00:00 GMT</pubDate></item><item><title>The Case for Context Graphs</title><link>https://inprinciple.sh/blog/the-case-for-context-graphs/</link><guid isPermaLink="true">https://inprinciple.sh/blog/the-case-for-context-graphs/</guid><description>Why the discussion around ontologies, context graphs and structural truth isn&apos;t hype — it&apos;s the inevitable next step in making agents actually useful.</description><pubDate>Fri, 10 Apr 2026 00:00:00 GMT</pubDate></item></channel></rss>