August 31, 2026 A Content Pipeline That Doesn't Trust Itself

TL;DR: My AI content pipeline once recorded a claim as “Verified” in two separate gate reports while the cited page said the opposite — both gates had matched the page’s topic, not the claim. Another …

May 22, 2026 Your AI Judge Needs a Judge

TL;DR: Most teams I see ship LLM judges without testing them against human labels. The result: judges that are confidently, consistently wrong on 30%+ of cases. Hamel Husain’s “critique shadowing” met…