<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Victor Melo · Articles</title><description>What I learn taking AI and ML to production, with real code and numbers.</description><link>https://vgmelo.tech/</link><language>en</language><item><title>Brazil&apos;s alphanumeric CNPJ: how to validate the new format (with code)</title><link>https://vgmelo.tech/en/articles/alphanumeric-cnpj/</link><guid isPermaLink="true">https://vgmelo.tech/en/articles/alphanumeric-cnpj/</guid><description>Brazil&apos;s company ID now accepts letters. How the check digit works with ord(c) − 48, what breaks in your systems, and a Python validator.</description><pubDate>Mon, 09 Nov 2026 00:00:00 GMT</pubDate></item><item><title>Champion/challenger in MLflow: promote models on evidence, not faith</title><link>https://vgmelo.tech/en/articles/champion-challenger-in-mlflow/</link><guid isPermaLink="true">https://vgmelo.tech/en/articles/champion-challenger-in-mlflow/</guid><description>How I set up credit model promotion with quality, calibration and fairness gates, MLflow aliases and one-command rollback, plus the type bug that marked the champion as rejected.</description><pubDate>Mon, 09 Nov 2026 00:00:00 GMT</pubDate></item><item><title>When the reasoning model says nothing: the silent agent bug</title><link>https://vgmelo.tech/en/articles/empty-answers-reasoning-models/</link><guid isPermaLink="true">https://vgmelo.tech/en/articles/empty-answers-reasoning-models/</guid><description>A reasoning model returned empty answers and my orchestrator counted them as success. The two causes, the fix (one extra request, then an explicit error) and the tests that catch it.</description><pubDate>Mon, 09 Nov 2026 00:00:00 GMT</pubDate></item><item><title>Observability for AI agents with OpenTelemetry: the minimum that works</title><link>https://vgmelo.tech/en/articles/llm-agent-observability/</link><guid isPermaLink="true">https://vgmelo.tech/en/articles/llm-agent-observability/</guid><description>What to record for every agent run (traces, tokens, cost and latency), how to follow OpenTelemetry&apos;s GenAI conventions, and the bugs that show up when agents run in parallel.</description><pubDate>Mon, 09 Nov 2026 00:00:00 GMT</pubDate></item></channel></rss>